From d7a7e81ba74924130926614b2a2d52cf8950aeee Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mine=20=C3=87etinkaya-Rundel?= Date: Sun, 22 Oct 2023 02:12:42 -0400 Subject: [PATCH] Fix refs --- 11-foundations-randomization.qmd | 344 ++++++++++-------- 14-foundations-errors.qmd | 2 +- 16-inference-one-prop.qmd | 2 +- .../01-data-hello/execute-results/html.json | 5 +- .../execute-results/html.json | 5 +- .../fig-opportunity-cost-obs-bar-1.png | Bin 0 -> 82500 bytes .../fig-opportunity-cost-rand-dot-plot-1.png | Bin 0 -> 299429 bytes .../fig-opportunity-cost-rand-hist-1.png | Bin 0 -> 166216 bytes .../figure-html/fig-sex-rand-dot-plot-1.png | Bin 0 -> 196468 bytes .../_11-ex-foundations-randomization.qmd | 245 +++++++------ 10 files changed, 338 insertions(+), 265 deletions(-) create mode 100644 _freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-obs-bar-1.png create mode 100644 _freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-rand-dot-plot-1.png create mode 100644 _freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-rand-hist-1.png create mode 100644 _freeze/11-foundations-randomization/figure-html/fig-sex-rand-dot-plot-1.png diff --git a/11-foundations-randomization.qmd b/11-foundations-randomization.qmd index 5f5137dd..211b5142 100644 --- a/11-foundations-randomization.qmd +++ b/11-foundations-randomization.qmd @@ -42,10 +42,10 @@ We would probably observe a small difference due to *chance*. ::: ::: {.guidedpractice data-latex=""} -If we do not think the side of the room a person sits on in class is related to whether they prefer to read books on screen, what assumption are we making about the relationship between these two variables?[^11-foundations-randomization-1] +If we do not think the side of the room a person sits on in class is related to whether they prefer to read books on screen, what assumption are we making about the relationship between these two variables?[^1] ::: -[^11-foundations-randomization-1]: We would be assuming that these two variables are **independent**\index{independent}. +[^1]: We would be assuming that these two variables are **independent**\index{independent}. ```{r} #| include: false @@ -57,7 +57,7 @@ Throughout this chapter, and those that follow, we provide three different appro Using the methods provided in this chapter, we will be able to draw conclusions beyond the dataset at hand to research questions about larger populations that the samples come from. The first type of variability we will explore comes from experiments where the explanatory variable (or treatment) is randomly assigned to the observational units. -As you learned in Chapter \@ref(data-hello), a randomized experiment can be used to assess whether one variable (the explanatory variable) causes changes in a second variable (the response variable). +As you learned in [Chapter -@sec-data-hello], a randomized experiment can be used to assess whether one variable (the explanatory variable) causes changes in a second variable (the response variable). Every dataset has some variability in it, so to decide whether the variability in the data is due to (1) the causal mechanism (the randomized explanatory variable in the experiment) or instead (2) natural variability inherent to the data, we set up a sham randomized experiment as a comparison. That is, we assume that each observational unit would have gotten the exact same response value regardless of the treatment level. By reassigning the treatments many many times, we can compare the actual experiment to the sham experiment. @@ -69,7 +69,7 @@ Using a few different case studies, let's look more carefully at this idea of a terms_chp_11 <- c(terms_chp_11, "randomization test") ``` -## Sex discrimination case study {#caseStudySexDiscrimination} +## Sex discrimination case study {#sec-caseStudySexDiscrimination} We consider a study investigating sex discrimination in the 1970s, which is set in the context of personnel decisions within a bank. The research question we hope to answer is, "Are individuals who identify as female discriminated against in promotion decisions made by their managers who identify as male?" [@Rosen:1974] @@ -90,26 +90,26 @@ These files were randomly assigned to the bank managers. ::: {.guidedpractice data-latex=""} Is this an observational study or an experiment? -How does the type of study impact what can be inferred from the results?[^11-foundations-randomization-2] +How does the type of study impact what can be inferred from the results?[^2] ::: -[^11-foundations-randomization-2]: The study is an experiment, as subjects were randomly assigned a "male" file or a "female" file (remember, all the files were actually identical in content). +[^2]: The study is an experiment, as subjects were randomly assigned a "male" file or a "female" file (remember, all the files were actually identical in content). Since this is an experiment, the results can be used to evaluate a causal relationship between the sex of a candidate and the promotion decision. ```{r} #| label: sex-discrimination-obs-p -sex_discrimination_props <- sex_discrimination %>% - rename(sex = sex) %>% - count(sex, decision) %>% - group_by(sex) %>% +sex_discrimination_props <- sex_discrimination |> + rename(sex = sex) |> + count(sex, decision) |> + group_by(sex) |> mutate(p = n / sum(n)) -p_male <- sex_discrimination_props %>% - filter(sex == "male", decision == "promoted") %>% +p_male <- sex_discrimination_props |> + filter(sex == "male", decision == "promoted") |> pull(p) -p_female <- sex_discrimination_props %>% - filter(sex == "female", decision == "promoted") %>% +p_female <- sex_discrimination_props |> + filter(sex == "female", decision == "promoted") |> pull(p) p_diff <- p_male - p_female @@ -120,34 +120,39 @@ perc_diff <- label_percent(accuracy = 0.1)(p_diff) ``` For each supervisor both the sex associated with the assigned file and the promotion decision were recorded. -Using the results of the study summarized in Table \@ref(tab:sex-discrimination-obs), we would like to evaluate if individuals who identify as female are unfairly discriminated against in promotion decisions. +Using the results of the study summarized in @tbl-sex-discrimination-obs, we would like to evaluate if individuals who identify as female are unfairly discriminated against in promotion decisions. In this study, a smaller proportion of female identifying applications were promoted than males (`r p_female` versus `r p_male`), but it is unclear whether the difference provides *convincing evidence* that individuals who identify as female are unfairly discriminated against. ```{r} -#| label: sex-discrimination-obs -sex_discrimination %>% - count(decision, sex) %>% - pivot_wider(names_from = decision, values_from = n) %>% - adorn_totals(where = c("col", "row")) %>% - kbl(linesep = "", booktabs = TRUE, caption = "Summary results for the sex discrimination study.") %>% +#| label: tbl-sex-discrimination-obs +#| tbl-cap: | +#| Summary results for the sex discrimination study. + +sex_discrimination |> + count(decision, sex) |> + pivot_wider(names_from = decision, values_from = n) |> + adorn_totals(where = c("col", "row")) |> + kbl(linesep = "", booktabs = TRUE) |> kable_styling(bootstrap_options = c("striped", "condensed"), - latex_options = c("striped", "hold_position"), full_width = FALSE) %>% - add_header_above(c(" " = 1, "decision" = 2, " " = 1)) %>% + latex_options = c("striped", "hold_position"), full_width = FALSE) |> + add_header_above(c(" " = 1, "decision" = 2, " " = 1)) |> column_spec(1:4, width = "7em") ``` -The data are visualized in Figure \@ref(fig:sex-rand-obs) as a set of cards. +The data are visualized in @fig-sex-rand-obs as a set of cards. Note that each card denotes a personnel file (an observation from our dataset) and the colors indicate the decision: red for promoted and white for not promoted. Additionally, the observations are broken up into groups of male and female identifying groups. ```{r} -#| label: sex-rand-obs -#| out.width: 40% -#| fig.cap: The sex discrimination study can be thought of as 48 red and white cards. -#| fig.alt: 48 cards are laid out; 24 indicating male files, 24 indicated female files. Of -#| the 24 male files 3 of the cards are colored white, and 21 of the cards are colored -#| red. Of the female files, 10 of the cards are colored white, and 14 of the cards -#| are colored red. +#| label: fig-sex-rand-obs +#| fig-cap: The sex discrimination study can be thought of as 48 red and white cards. +#| fig-alt: | +#| 48 cards are laid out; 24 indicating male files, 24 indicated female files. +#| Of the 24 male files 3 of the cards are colored white, and 21 of the cards +#| are colored red. Of the female files, 10 of the cards are colored white, +#| and 14 of the cards are colored red. +#| out-width: 40% + knitr::include_graphics("images/sex-rand-01-obs.png") ``` @@ -163,7 +168,7 @@ Since we wouldn't expect the sample proportions to be *exactly* equal, even if t ::: The previous example is a reminder that the observed outcomes in the sample may not perfectly reflect the true relationships between variables in the underlying population. -Table \@ref(tab:sex-discrimination-obs) shows there were 7 fewer promotions for female identifying personnel than for the male personnel, a difference in promotion rates of `r perc_diff` $\left( \frac{21}{24} - \frac{14}{24} = 0.292 \right).$ This observed difference is what we call a **point estimate**\index{point estimate} of the true difference. +@tbl-sex-discrimination-obs shows there were 7 fewer promotions for female identifying personnel than for the male personnel, a difference in promotion rates of `r perc_diff` $\left( \frac{21}{24} - \frac{14}{24} = 0.292 \right).$ This observed difference is what we call a **point estimate**\index{point estimate} of the true difference. The point estimate of the difference in promotion rate is large, but the sample size for the study is small, making it unclear if this observed difference represents discrimination or whether it is simply due to chance when there is no discrimination occurring. Chance can be thought of as the claim due to natural variability; discrimination can be thought of as the claim the researchers set out to demonstrate. We label these two competing claims, $H_0$ and $H_A:$ @@ -217,12 +222,12 @@ If data and the null claim seem to be at odds with one another, and the data see ### Variability of the statistic -Table \@ref(tab:sex-discrimination-obs) shows that 35 bank supervisors recommended promotion and 13 did not. +@tbl-sex-discrimination-obs shows that 35 bank supervisors recommended promotion and 13 did not. Now, suppose the bankers' decisions were independent of the sex of the candidate. Then, if we conducted the experiment again with a different random assignment of sex to the files, differences in promotion rates would be based only on random fluctuation in promotion decisions. -We can actually perform this **randomization**, which simulates what would have happened if the bankers' decisions had been independent of `sex` but we had distributed the file sexes differently.[^11-foundations-randomization-3] +We can actually perform this **randomization**, which simulates what would have happened if the bankers' decisions had been independent of `sex` but we had distributed the file sexes differently.[^3] -[^11-foundations-randomization-3]: The test procedure we employ in this section is sometimes referred to as a **randomization test**. +[^3]: The test procedure we employ in this section is sometimes referred to as a **randomization test**. If the explanatory variable had not been randomly assigned, as in an observational study, the procedure would be referred to as a **permutation test**. Permutation tests are used for observational studies, where the explanatory variable was not randomly assigned.\index{permutation test}. @@ -235,15 +240,18 @@ In the **simulation**\index{simulation}, we thoroughly shuffle the 48 personnel Note that by keeping 35 promoted and 13 not promoted, we are assuming that 35 of the bank managers would have promoted the individual whose content is contained in the file **independent** of the sex indicated on their file. We will deal 24 files into the first stack, which will represent the 24 "female" files. The second stack will also have 24 files, and it will represent the 24 "male" files. -Figure \@ref(fig:sex-rand-shuffle-1) highlights both the shuffle and the reallocation to the sham sex groups. +@fig-sex-rand-shuffle-1 highlights both the shuffle and the reallocation to the sham sex groups. ```{r} -#| label: sex-rand-shuffle-1 -#| out.width: 80% -#| fig.cap: The sex discrimination data is shuffled and reallocated to new groups of +#| label: fig-sex-rand-shuffle-1 +#| fig-cap: | +#| The sex discrimination data is shuffled and reallocated to new groups of #| male and female files. -#| fig.alt: The 48 red and white cards which denote the original data are shuffled and +#| fig-alt: | +#| The 48 red and white cards which denote the original data are shuffled and #| reassigned, 24 to each group indicating 24 male files and 24 female files. +#| out.width: 80% + knitr::include_graphics("images/sex-rand-02-shuffle-1.png") ``` @@ -255,40 +263,44 @@ terms_chp_11 <- c(terms_chp_11, "simulation") ``` Since the randomization of files in this simulation is independent of the promotion decisions, any difference in promotion rates is due to chance. -Table \@ref(tab:sex-discrimination-rand-1) show the results of one such simulation. +@tbl-sex-discrimination-rand-1 show the results of one such simulation. ```{r} -#| label: sex-discrimination-rand-1 +#| label: tbl-sex-discrimination-rand-1 +#| tbl-cap: | +#| Simulation results, where the difference in promotion rates between male +#| and female is purely due to random chance. + sex_discrimination_rand_1 <- tibble( sex = c(rep("male", 24), rep("female", 24)), decision = c(rep("promoted", 18), rep("not promoted", 6), rep("promoted", 17), rep("not promoted", 7)) -) %>% +) |> mutate( sex = fct_relevel(sex, "male", "female"), decision = fct_relevel(decision, "promoted", "not promoted") ) -sex_discrimination_rand_1 %>% - count(decision, sex) %>% - pivot_wider(names_from = decision, values_from = n) %>% - adorn_totals(where = c("col", "row")) %>% - kbl(linesep = "", booktabs = TRUE, caption = "Simulation results, where the difference in promotion rates between male and female is purely due to random chance.") %>% +sex_discrimination_rand_1 |> + count(decision, sex) |> + pivot_wider(names_from = decision, values_from = n) |> + adorn_totals(where = c("col", "row")) |> + kbl(linesep = "", booktabs = TRUE) |> kable_styling(bootstrap_options = c("striped", "condensed"), - latex_options = c("striped", "hold_position"), full_width = FALSE) %>% - add_header_above(c(" " = 1, "decision" = 2, " " = 1)) %>% + latex_options = c("striped", "hold_position"), full_width = FALSE) |> + add_header_above(c(" " = 1, "decision" = 2, " " = 1)) |> column_spec(1:4, width = "7em") ``` ::: {.guidedpractice data-latex=""} -What is the difference in promotion rates between the two simulated groups in Table \@ref(tab:sex-discrimination-rand-1) ? -How does this compare to the observed difference 29.2% from the actual study?[^11-foundations-randomization-4] +What is the difference in promotion rates between the two simulated groups in @tbl-sex-discrimination-rand-1 ? +How does this compare to the observed difference 29.2% from the actual study?[^4] ::: -[^11-foundations-randomization-4]: $18/24 - 17/24=0.042$ or about 4.2% in favor of the male personnel. +[^4]: $18/24 - 17/24=0.042$ or about 4.2% in favor of the male personnel. This difference due to chance is much smaller than the difference observed in the actual groups. -Figure \@ref(fig:sex-rand-shuffle-1-sort) shows that the difference in promotion rates is much larger in the original data than it is in the simulated groups (0.292 \> 0.042). +@fig-sex-rand-shuffle-1-sort shows that the difference in promotion rates is much larger in the original data than it is in the simulated groups (0.292 \> 0.042). The quantity of interest throughout this case study has been the difference in promotion rates. We call the summary value the **statistic** of interest (or often the **test statistic**). When we encounter different data structures, the statistic is likely to change (e.g., we might calculate an average instead of a proportion), but we will always want to understand how the statistic varies from sample to sample. @@ -299,18 +311,21 @@ terms_chp_11 <- c(terms_chp_11, "statistic", "test statistic") ``` ```{r} -#| label: sex-rand-shuffle-1-sort -#| out.width: 100% -#| fig.cap: We summarize the randomized data to produce one estimate of the difference +#| label: fig-sex-rand-shuffle-1-sort +#| out-width: 100% +#| fig-cap: | +#| We summarize the randomized data to produce one estimate of the difference #| in proportions given no sex discrimination. Note that the sort step is only used #| to make it easier to visually calculate the simulated sample proportions. -#| fig.alt: The 48 red and white cards are show in three panels. The first panel represents +#| fig-alt: | +#| The 48 red and white cards are show in three panels. The first panel represents #| the original data and original allocation of the male and female files (in the original #| data there are 3 white cards in the male group and 10 white cards in the female #| group). The second panel represents the shuffled red and white cards that are randomly #| assigned as male and female files. The third panel has the cards sorted according #| to the random assignment of female or male. In the third panel there are 6 white #| cards in the male group and 7 white cards in the female group. + knitr::include_graphics("images/sex-rand-03-shuffle-1-sort.png") ``` @@ -321,19 +336,25 @@ While in this first simulation, we physically dealt out files, it is much more e Repeating the simulation on a computer, we get another difference due to chance under the same assumption: -0.042. And another: 0.208. And so on until we repeat the simulation enough times that we have a good idea of the shape of the *distribution of differences* under the null hypothesis. -Figure \@ref(fig:sex-rand-dot-plot) shows a plot of the differences found from 100 simulations, where each dot represents a simulated difference between the proportions of male and female files recommended for promotion. +@fig-sex-rand-dot-plot shows a plot of the differences found from 100 simulations, where each dot represents a simulated difference between the proportions of male and female files recommended for promotion. ```{r} -#| label: sex-rand-dot-plot -#| fig.cap: (ref:sex-rand-dot-plot-cap) -#| out.width: 100% +#| label: fig-sex-rand-dot-plot +#| fig-cap: | +#| A stacked dot plot of differences from 100 simulations produced under +#| the null hypothesis, $H_0,$ where the simulated sex and decision are +#| independent. Two of the 100 simulations had a difference of at least +#| 29.2%, the difference observed in the study, and are shown as solid +#| blue dots. +#| out-width: 100% + set.seed(37) -sex_discrimination %>% - specify(decision ~ sex, success = "promoted") %>% - hypothesize(null = "independence") %>% - generate(reps = 100, type = "permute") %>% - calculate(stat = "diff in props", order = c("male", "female")) %>% - mutate(stat = round(stat, 3)) %>% +sex_discrimination |> + specify(decision ~ sex, success = "promoted") |> + hypothesize(null = "independence") |> + generate(reps = 100, type = "permute") |> + calculate(stat = "diff in props", order = c("male", "female")) |> + mutate(stat = round(stat, 3)) |> ggplot(aes(x = stat)) + geom_dotplot(binwidth = 0.01) + gghighlight(stat >= 0.292) + @@ -347,19 +368,17 @@ sex_discrimination %>% ) ``` -(ref:sex-rand-dot-plot-cap) A stacked dot plot of differences from 100 simulations produced under the null hypothesis, $H_0,$ where the simulated sex and decision are independent. Two of the 100 simulations had a difference of at least 29.2%, the difference observed in the study, and are shown as solid blue dots. - Note that the distribution of these simulated differences in proportions is centered around 0. Under the null hypothesis our simulations made no distinction between male and female personnel files. Thus, a center of 0 makes sense: we should expect differences from chance alone to fall around zero with some random fluctuation for each simulation. ::: {.workedexample data-latex=""} -How often would you observe a difference of at least `r perc_diff` (`r p_diff`) according to Figure \@ref(fig:sex-rand-dot-plot)? +How often would you observe a difference of at least `r perc_diff` (`r p_diff`) according to @fig-sex-rand-dot-plot? Often, sometimes, rarely, or never? ------------------------------------------------------------------------ -It appears that a difference of at least `r perc_diff` under the null hypothesis would only happen about 2% of the time according to Figure \@ref(fig:sex-rand-dot-plot). +It appears that a difference of at least `r perc_diff` under the null hypothesis would only happen about 2% of the time according to @fig-sex-rand-dot-plot. Such a low probability indicates that observing such a large difference from chance alone is rare. ::: @@ -369,11 +388,11 @@ The difference of 29.2% is a rare event if there really is no impact from listin - If $H_A,$ the **Alternative hypothesis** is true: Sex has an effect on promotion decision, and what we observed was actually due to equally qualified female candidates being discriminated against in promotion decisions, which explains the large difference of 29.2%. -When we conduct formal studies, we reject a null position (the idea that the data are a result of chance only) if the data strongly conflict with that null position.[^11-foundations-randomization-5] +When we conduct formal studies, we reject a null position (the idea that the data are a result of chance only) if the data strongly conflict with that null position.[^5] In our analysis, we determined that there was only a $\approx$ 2% probability of obtaining a sample where $\geq$ 29.2% more male candidates than female candidates get promoted under the null hypothesis, so we conclude that the data provide strong evidence of sex discrimination against female candidates by the male supervisors. In this case, we reject the null hypothesis in favor of the alternative. -[^11-foundations-randomization-5]: This reasoning does not generally extend to anecdotal observations. +[^5]: This reasoning does not generally extend to anecdotal observations. Each of us observes incredibly rare events every day, events we could not possibly hope to predict. However, in the non-rigorous setting of anecdotal evidence, almost anything may appear to be a rare event, so the idea of looking for rare events in day-to-day activities is treacherous. For example, we might look at the lottery: there was only a 1 in 176 million chance that the Mega Millions numbers for the largest jackpot in history (October 23, 2018) would be (5, 28, 62, 65, 70) with a Mega ball of (5), but nonetheless those numbers came up! @@ -392,7 +411,7 @@ Before getting into the nuances of hypothesis testing, let's work through anothe terms_chp_11 <- c(terms_chp_11, "statistical inference") ``` -## Opportunity cost case study {#caseStudyOpportunityCost} +## Opportunity cost case study {#sec-caseStudyOpportunityCost} How rational and consistent is the behavior of the typical American college student? In this section, we'll explore whether college student consumers always consider the following: money not spent now can be spent later. @@ -411,9 +430,9 @@ In this section, we'll explore an experiment conducted by researchers that inves One-hundred and fifty students were recruited for the study, and each was given the following statement: -> *Imagine that you have been saving some extra money on the side to make some purchases, and on your most recent visit to the video store you come across a special sale on a new video. This video is one with your favorite actor or actress, and your favorite type of movie (such as a comedy, drama, thriller, etc.). This particular video that you are considering is one you have been thinking about buying for a long time. It is available for a special sale price of \$14.99. What would you do in this situation? Please circle one of the options below.*[^11-foundations-randomization-6] +> *Imagine that you have been saving some extra money on the side to make some purchases, and on your most recent visit to the video store you come across a special sale on a new video. This video is one with your favorite actor or actress, and your favorite type of movie (such as a comedy, drama, thriller, etc.). This particular video that you are considering is one you have been thinking about buying for a long time. It is available for a special sale price of \$14.99. What would you do in this situation? Please circle one of the options below.*[^6] -[^11-foundations-randomization-6]: This context might feel strange if physical video stores predate you. +[^6]: This context might feel strange if physical video stores predate you. If you're curious about what those were like, look up "Blockbuster". Half of the 150 students were randomized into a control group and were given the following two options: @@ -429,33 +448,36 @@ The remaining 75 students were placed in the treatment group, and they saw a sli > (B) Not buy this entertaining video. Keep the \$14.99 for other purchases. Would the extra statement reminding students of an obvious fact impact the purchasing decision? -Table \@ref(tab:opportunity-cost-obs) summarizes the study results. +@tbl-opportunity-cost-obs summarizes the study results. ::: {.data data-latex=""} The [`opportunity_cost`](http://openintrostat.github.io/openintro/reference/opportunity_cost.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package. ::: ```{r} -#| label: opportunity-cost-obs -opportunity_cost %>% - count(group, decision) %>% - pivot_wider(names_from = decision, values_from = n) %>% - adorn_totals(where = c("col", "row")) %>% - kbl(linesep = "", booktabs = TRUE, caption = "Summary results of the opportunity cost study.") %>% +#| label: tbl-opportunity-cost-obs +#| tbl-cap: Summary results of the opportunity cost study. + +opportunity_cost |> + count(group, decision) |> + pivot_wider(names_from = decision, values_from = n) |> + adorn_totals(where = c("col", "row")) |> + kbl(linesep = "", booktabs = TRUE) |> kable_styling(bootstrap_options = c("striped", "condensed"), - latex_options = c("striped", "hold_position"), full_width = FALSE) %>% - add_header_above(c(" " = 1, "decision" = 2, " " = 1)) %>% + latex_options = c("striped", "hold_position"), full_width = FALSE) |> + add_header_above(c(" " = 1, "decision" = 2, " " = 1)) |> column_spec(1:4, width = "7em") ``` It might be a little easier to review the results using a visualization. -Figure \@ref(fig:opportunity-cost-obs-bar) shows that a higher proportion of students in the treatment group chose not to buy the video compared to those in the control group. +@fig-opportunity-cost-obs-bar shows that a higher proportion of students in the treatment group chose not to buy the video compared to those in the control group. ```{r} -#| label: opportunity-cost-obs-bar -#| fig.cap: Stacked bar plot of results of the opportunity cost study. -#| out.width: 100% +#| label: fig-opportunity-cost-obs-bar +#| fig-cap: Stacked bar plot of results of the opportunity cost study. +#| out-width: 100% #| fig-asp: 0.3 + ggplot(opportunity_cost, aes(y = fct_rev(group), fill = fct_rev(decision))) + geom_bar(position = "fill") + scale_fill_openintro("two") + @@ -467,29 +489,34 @@ ggplot(opportunity_cost, aes(y = fct_rev(group), fill = fct_rev(decision))) + ) ``` -Another useful way to review the results from Table \@ref(tab:opportunity-cost-obs) is using row proportions, specifically considering the proportion of participants in each group who said they would buy or not buy the video. -These summaries are given in Table \@ref(tab:opportunity-cost-obs-row-prop). +Another useful way to review the results from @tbl-opportunity-cost-obs is using row proportions, specifically considering the proportion of participants in each group who said they would buy or not buy the video. +These summaries are given in @tbl-opportunity-cost-obs-row-prop. ```{r} -#| label: opportunity-cost-obs-row-prop -opportunity_cost %>% - count(group, decision) %>% - pivot_wider(names_from = decision, values_from = n) %>% - adorn_percentages(denominator = "row") %>% - adorn_totals(where = "col") %>% - kbl(linesep = "", booktabs = TRUE, caption = "The opportunity cost data are summarized using row proportions. Row proportions are particularly useful here since we can view the proportion of *buy* and *not buy* decisions in each group.") %>% +#| label: tbl-opportunity-cost-obs-row-prop +#| tbl-cap: | +#| The opportunity cost data are summarized using row proportions. Row +#| proportions are particularly useful here since we can view the proportion +#| of *buy* and *not buy* decisions in each group. + +opportunity_cost |> + count(group, decision) |> + pivot_wider(names_from = decision, values_from = n) |> + adorn_percentages(denominator = "row") |> + adorn_totals(where = "col") |> + kbl(linesep = "", booktabs = TRUE) |> kable_styling(bootstrap_options = c("striped", "condensed"), - latex_options = c("striped", "hold_position"), full_width = FALSE) %>% - add_header_above(c(" " = 1, "decision" = 2, " " = 1)) %>% + latex_options = c("striped", "hold_position"), full_width = FALSE) |> + add_header_above(c(" " = 1, "decision" = 2, " " = 1)) |> column_spec(1:4, width = "7em") ``` -We will define a **success**\index{success} in this study as a student who chooses not to buy the video.[^11-foundations-randomization-7] +We will define a **success**\index{success} in this study as a student who chooses not to buy the video.[^7] Then, the value of interest is the change in video purchase rates that results by reminding students that not spending money now means they can spend the money later. -[^11-foundations-randomization-7]: Success is often defined in a study as the outcome of interest, and a "success" may or may not actually be a positive outcome. +[^7]: Success is often defined in a study as the outcome of interest, and a "success" may or may not actually be a positive outcome. For example, researchers working on a study on COVID prevalence might define a "success" in the statistical sense as a patient who has COVID-19. - A more complete discussion of the term **success** will be given in Chapter \@ref(inference-one-prop). + A more complete discussion of the term **success** will be given in [Chapter -@sec-inference-one-prop]. ```{r} #| include: false @@ -506,7 +533,7 @@ Is this 20% difference between the two groups so prominent that it is unlikely t ### Variability of the statistic The primary goal in this data analysis is to understand what sort of differences we might see if the null hypothesis were true, i.e., the treatment had no effect on students. -Because this is an experiment, we'll use the same procedure we applied in Section \@ref(caseStudySexDiscrimination): randomization. +Because this is an experiment, we'll use the same procedure we applied in @sec-caseStudySexDiscrimination: randomization. Let's think about the data in the context of the hypotheses. If the null hypothesis $(H_0)$ was true and the treatment had no impact on student decisions, then the observed difference between the two groups of 20% could be attributed entirely to random chance. @@ -533,30 +560,35 @@ Since the simulated groups are of equal size, we would expect $53 / 2 = 26.5,$ i However, due to random chance, we might also expect to sometimes observe a number a little above or below 26 and 27. ::: -The results of a single randomization is shown in Table \@ref(tab:opportunity-cost-obs-simulated). +The results of a single randomization is shown in @tbl-opportunity-cost-obs-simulated. ```{r} -#| label: opportunity-cost-obs-simulated +#| label: tbl-opportunity-cost-obs-simulated +#| tbl-cap: | +#| Summary of student choices against their simulated groups. The group +#| assignment had no connection to the student decisions, so any difference +#| between the two groups is due to chance. + opportunity_cost_rand_1 <- tibble( group = c(rep("control", 75), rep("treatment", 75)), decision = c( rep("buy video", 46), rep("not buy video", 29), rep("buy video", 51), rep("not buy video", 24) ) -) %>% +) |> mutate( group = as.factor(group), decision = as.factor(decision) ) -opportunity_cost_rand_1 %>% - count(group, decision) %>% - pivot_wider(names_from = decision, values_from = n) %>% - adorn_totals(where = c("col", "row")) %>% - kbl(linesep = "", booktabs = TRUE, caption = "Summary of student choices against their simulated groups. The group assignment had no connection to the student decisions, so any difference between the two groups is due to chance.") %>% +opportunity_cost_rand_1 |> + count(group, decision) |> + pivot_wider(names_from = decision, values_from = n) |> + adorn_totals(where = c("col", "row")) |> + kbl(linesep = "", booktabs = TRUE) |> kable_styling(bootstrap_options = c("striped", "condensed"), - latex_options = c("striped", "hold_position"), full_width = FALSE) %>% - add_header_above(c(" " = 1, "decision" = 2, " " = 1)) %>% + latex_options = c("striped", "hold_position"), full_width = FALSE) |> + add_header_above(c(" " = 1, "decision" = 2, " " = 1)) |> column_spec(1:4, width = "7em") ``` @@ -569,11 +601,11 @@ Just one simulation will not be enough to get a sense of what sorts of differenc ```{r} #| label: opportunity-cost-rand-dist set.seed(25) -opportunity_cost_rand_dist <- opportunity_cost %>% - specify(decision ~ group, success = "not buy video") %>% - hypothesize(null = "independence") %>% - generate(reps = 1000, type = "permute") %>% - calculate(stat = "diff in props", order = c("treatment", "control")) %>% +opportunity_cost_rand_dist <- opportunity_cost |> + specify(decision ~ group, success = "not buy video") |> + hypothesize(null = "independence") |> + generate(reps = 1000, type = "permute") |> + calculate(stat = "diff in props", order = c("treatment", "control")) |> mutate(stat = round(stat, 3)) ``` @@ -585,11 +617,15 @@ And again: `r opportunity_cost_rand_dist$stat[3]`. We'll do this 1,000 times. -The results are summarized in a dot plot in Figure \@ref(fig:opportunity-cost-rand-dot-plot), where each point represents the difference from one randomization. +The results are summarized in a dot plot in @fig-opportunity-cost-rand-dot-plot, where each point represents the difference from one randomization. ```{r} -#| label: opportunity-cost-rand-dot-plot -#| fig.cap: (ref:opportunity-cost-rand-dot-plot-cap) +#| label: fig-opportunity-cost-rand-dot-plot +#| fig-cap: | +#| A stacked dot plot of 1,000 simulated (null) differences produced under +#| the null hypothesis, $H_0.$ Six of the 1,000 simulations had a difference +#| of at least 20%, which was the difference observed in the study. + ggplot(opportunity_cost_rand_dist, aes(x = stat)) + geom_dotplot(binwidth = 0.01, dotsize = 0.165) + gghighlight(stat >= 0.20) + @@ -604,15 +640,15 @@ ggplot(opportunity_cost_rand_dist, aes(x = stat)) + ) ``` -(ref:opportunity-cost-rand-dot-plot-cap) A stacked dot plot of 1,000 simulated (null) differences produced under the null hypothesis, $H_0.$ Six of the 1,000 simulations had a difference of at least 20% , which was the difference observed in the study. - -Since there are so many points and it is difficult to discern one point from the other, it is more convenient to summarize the results in a histogram such as the one in Figure \@ref(fig:opportunity-cost-rand-hist), where the height of each histogram bar represents the number of simulations resulting in an outcome of that magnitude. +Since there are so many points and it is difficult to discern one point from the other, it is more convenient to summarize the results in a histogram such as the one in @fig-opportunity-cost-rand-hist, where the height of each histogram bar represents the number of simulations resulting in an outcome of that magnitude. ```{r} -#| label: opportunity-cost-rand-hist -#| fig.cap: A histogram of 1,000 chance differences produced under the null hypothesis. -#| Histograms like this one are a convenient representation of data or results when -#| there are a large number of simulations. +#| label: fig-opportunity-cost-rand-hist +#| fig-cap: | +#| A histogram of 1,000 chance differences produced under the null hypothesis. +#| Histograms like this one are a convenient representation of data or results +#| when there are a large number of simulations. + ggplot(opportunity_cost_rand_dist, aes(x = stat)) + geom_histogram(binwidth = 0.04) + gghighlight(stat >= 0.20) + @@ -674,11 +710,11 @@ They are simply not convinced of the alternative, that the person is guilty. This is also the case with hypothesis testing: *even if we fail to reject the null hypothesis, we do not accept the null hypothesis as truth*. Failing to find evidence in favor of the alternative hypothesis is not equivalent to finding evidence that the null hypothesis is true. -We will see this idea in greater detail in Section \@ref(decerr). +We will see this idea in greater detail in [Chapter -@sec-decerr]. ### p-value and statistical discernibility -In Section \@ref(caseStudySexDiscrimination) we encountered a study from the 1970's that explored whether there was strong evidence that female candidates were less likely to be promoted than male candidates. +In @caseStudySexDiscrimination we encountered a study from the 1970's that explored whether there was strong evidence that female candidates were less likely to be promoted than male candidates. The research question -- are female candidates discriminated against in promotion decisions? -- was framed in the context of hypotheses: @@ -708,7 +744,7 @@ terms_chp_11 <- c(terms_chp_11, "p-value", "test statistic") ::: {.workedexample data-latex=""} In the sex discrimination study, the difference in discrimination rates was our test statistic. -What was the test statistic in the opportunity cost study covered in Section \@ref(caseStudyOpportunityCost)? +What was the test statistic in the opportunity cost study covered in @sec-caseStudyOpportunityCost)? ------------------------------------------------------------------------ @@ -717,17 +753,17 @@ In each of these examples, the **point estimate** of the difference in proportio ::: When the p-value is small, i.e., less than a previously set threshold, we say the results are **statistically discernible**\index{statistically significant}\index{statistically discernible}. -This means the data provide such strong evidence against $H_0$ that we reject the null hypothesis in favor of the alternative hypothesis.[^11-foundations-randomization-8] +This means the data provide such strong evidence against $H_0$ that we reject the null hypothesis in favor of the alternative hypothesis.[^8] The threshold is called the **discernibility level**\index{hypothesis testing!discernibility level}\index{significance level}\index{discernibility level} and often represented by $\alpha$ (the Greek letter *alpha*). -[^11-foundations-randomization-9] The value of $\alpha$ represents how rare an event needs to be in order for the null hypothesis to be rejected +[^9] The value of $\alpha$ represents how rare an event needs to be in order for the null hypothesis to be rejected . Historically, many fields have set $\alpha = 0.05,$ meaning that the results need to occur less than 5% of the time, if the null hypothesis is to be rejected . The value of $\alpha$ can vary depending on the the field or the application . -[^11-foundations-randomization-8]: Many texts use the phrase "statistically significant" instead of "statistically discernible". +[^8]: Many texts use the phrase "statistically significant" instead of "statistically discernible". We have chosen to use "discernible" to indicate that a precise statistical event has happened, as opposed to a notable effect which may or may not fit the statistical definition of discernible or significant. -[^11-foundations-randomization-9]: Here, too, we have chosen "discernibility level" instead of "significance level" which you will see in some texts. +[^9]: Here, too, we have chosen "discernibility level" instead of "significance level" which you will see in some texts. ```{r} #| include: false @@ -747,7 +783,7 @@ We say that the data provide **statistically discernible**\index{hypothesis test ::: ::: {.workedexample data-latex=""} -In the opportunity cost study in Section \@ref(caseStudyOpportunityCost), we analyzed an experiment where study participants had a 20% drop in likelihood of continuing with a video purchase if they were reminded that the money, if not spent on the video, could be used for other purchases in the future. +In the opportunity cost study in @sec-caseStudyOpportunityCost, we analyzed an experiment where study participants had a 20% drop in likelihood of continuing with a video purchase if they were reminded that the money, if not spent on the video, could be used for other purchases in the future. We determined that such a large difference would only occur 6-in-1,000 times if the reminder actually had no influence on student decision-making. What is the p-value in this study? Would you classify the result as "statistically discernible"? @@ -770,7 +806,7 @@ We've made a video to help clarify *why 0.05*: Sometimes it's also a good idea to deviate from the standard. -We'll discuss when to choose a threshold different than 0.05 in Section \@ref(decerr). +We'll discuss when to choose a threshold different than 0.05 in [Chapter -@sec-decerr]. ::: \clearpage @@ -779,7 +815,7 @@ We'll discuss when to choose a threshold different than 0.05 in Section \@ref(de ### Summary -Figure \@ref(fig:fullrand) provides a visual summary of the randomization testing procedure. +@fig-fullrand provides a visual summary of the randomization testing procedure. \index{randomization test} @@ -789,18 +825,21 @@ terms_chp_11 <- c(terms_chp_11, "randomization test") ``` ```{r} -#| label: fullrand -#| out.width: 100% -#| fig.cap: An example of one simulation of the full randomization procedure from a hypothetical +#| label: fig-fullrand +#| out-width: 100% +#| fig-cap: | +#| An example of one simulation of the full randomization procedure from a hypothetical #| dataset as visualized in the first panel. We repeat the steps hundreds or thousands #| of times. -#| fig.alt: 48 red and white cards are show in three panels. The first panel represents +#| fig-alt: | +#| 48 red and white cards are show in three panels. The first panel represents #| original data and original allocation of Group 1 and Group 2 (in the original data #| there are 7 white cards in Group 1 and 10 white cards in Group 2). The second panel #| represents the shuffled red and white cards that are randomly assigned as Group #| 1 and Group 2. The third panel has the cards sorted according to the random assignment #| of Group 1 and Group 2. In the third panel there are 8 white cards in the Group #| 1 and 9 white cards in Group 2. + knitr::include_graphics("images/fullrand.png") ``` @@ -812,17 +851,18 @@ We can summarize the randomization test procedure as follows: - **Analyze the data.** Choose an analysis technique appropriate for the data and identify the p-value. So far, we have only seen one analysis technique: randomization. Throughout the rest of this textbook, we'll encounter several new methods suitable for many other contexts. - **Form a conclusion.** Using the p-value from the analysis, determine whether the data provide evidence against the null hypothesis. Also, be sure to write the conclusion in plain language so casual readers can understand the results. -Table \@ref(tab:chp11-summary) is another look at the randomization test summary. +@tbl-chp11-summary is another look at the randomization test summary. ```{r} -#| label: chp11-summary -inference_method_summary_table %>% - filter(question != "What are the technical conditions?") %>% - select(question, randomization) %>% - kbl(linesep = "\\addlinespace", booktabs = TRUE, caption = "Summary of randomization as an inferential statistical method.", - col.names = c("Question", "Answer")) %>% +#| label: tbl-chp11-summary +#| tbl-cap: Summary of randomization as an inferential statistical method. + +inference_method_summary_table |> + filter(question != "What are the technical conditions?") |> + select(question, randomization) |> + kbl(linesep = "\\addlinespace", booktabs = TRUE, col.names = c("Question", "Answer")) |> kable_styling(bootstrap_options = c("striped", "condensed"), - latex_options = c("striped", "hold_position"), full_width = TRUE) %>% + latex_options = c("striped", "hold_position"), full_width = TRUE) |> column_spec(1, width = "15em") ``` diff --git a/14-foundations-errors.qmd b/14-foundations-errors.qmd index b9e5f9a1..a1df9e02 100644 --- a/14-foundations-errors.qmd +++ b/14-foundations-errors.qmd @@ -1,4 +1,4 @@ -# Decision Errors {#decerr} +# Decision Errors {#sec-decerr} ```{r} #| include: false diff --git a/16-inference-one-prop.qmd b/16-inference-one-prop.qmd index 74027f1a..63c8e127 100644 --- a/16-inference-one-prop.qmd +++ b/16-inference-one-prop.qmd @@ -4,7 +4,7 @@ source("_common.R") ``` -# Inference for a single proportion {#inference-one-prop} +# Inference for a single proportion {#sec-inference-one-prop} ::: {.chapterintro data-latex=""} Focusing now on statistical inference for categorical data, we will revisit many of the foundational aspects of hypothesis testing from Chapter \@ref(foundations-randomization). diff --git a/_freeze/01-data-hello/execute-results/html.json b/_freeze/01-data-hello/execute-results/html.json index 3e4dc4ed..600407d5 100644 --- a/_freeze/01-data-hello/execute-results/html.json +++ b/_freeze/01-data-hello/execute-results/html.json @@ -1,7 +1,8 @@ { - "hash": "2c11b67a4ada86aef92c743c92fdc28a", + "hash": "2d9d6471b03d92e97a32bf3de34fcd03", "result": { - "markdown": "# Hello data {#sec-data-hello}\n\n\n\n\n\n::: {.chapterintro data-latex=\"\"}\nScientists seek to answer questions using rigorous methods and careful observations.\nThese observations -- collected from the likes of field notes, surveys, and experiments -- form the backbone of a statistical investigation and are called **data**.\nStatistics is the study of how best to collect, analyze, and draw conclusions from data.\nIn this first chapter, we focus on both the properties of data and on the collection of data.\n:::\n\n\n\n\n\n## Case study: Using stents to prevent strokes {#01-data-hello-sec-case-study-stents-strokes}\n\nIn this section we introduce a classic challenge in statistics: evaluating the efficacy of a medical treatment.\nTerms in this section, and indeed much of this chapter, will all be revisited later in the text.\nThe plan for now is simply to get a sense of the role statistics can play in practice.\n\nAn experiment is designed to study the effectiveness of stents in treating patients at risk of stroke [@chimowitz2011stenting].\nStents are small mesh tubes that are placed inside narrow or weak arteries to assist in patient recovery after cardiac events and reduce the risk of an additional heart attack or death.\n\nMany doctors have hoped that there would be similar benefits for patients at risk of stroke.\nWe start by writing the principal question the researchers hope to answer:\n\n> Does the use of stents reduce the risk of stroke?\n\nThe researchers who asked this question conducted an experiment with 451 at-risk patients.\nEach volunteer patient was randomly assigned to one of two groups:\n\n- **Treatment group**. Patients in the treatment group received a stent and medical management. The medical management included medications, management of risk factors, and help in lifestyle modification.\n- **Control group**. Patients in the control group received the same medical management as the treatment group, but they did not receive stents.\n\nResearchers randomly assigned 224 patients to the treatment group and 227 to the control group.\nIn this study, the control group provides a reference point against which we can measure the medical impact of stents in the treatment group.\n\n\\clearpage\n\nResearchers studied the effect of stents at two time points: 30 days after enrollment and 365 days after enrollment.\nThe results of 5 patients are summarized in @tbl-stentStudyResultsDF.\nPatient outcomes are recorded as `stroke` or `no event`, representing whether the patient had a stroke during that time period.\n\n::: {.data data-latex=\"\"}\nThe [`stent30`](http://openintrostat.github.io/openintro/reference/stent30.html) data and [`stent365`](http://openintrostat.github.io/openintro/reference/stent365.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n:::\n\n\n::: {#tbl-stentStudyResultsDF .cell tbl-cap='Results for five patients from the stent study.' fig.asp='0.618'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
patient group 30 days 365 days
1 treatment no event no event
2 treatment stroke stroke
3 treatment no event no event
4 treatment no event no event
5 control no event no event
\n\n`````\n:::\n:::\n\n\nIt would be difficult to answer a question on the impact of stents on the occurrence of strokes for **all** study patients using these *individual* observations.\nThis question is better addressed by performing a statistical data analysis of *all* observations.\n@tbl-stentStudyResultsDFsummary summarizes the raw data in a more helpful way.\nIn this table, we can quickly see what happened over the entire study.\nFor instance, to identify the number of patients in the treatment group who had a stroke within 30 days after the treatment, we look in the leftmost column (30 days), at the intersection of treatment and stroke: 33.\nTo identify the number of control patients who did not have a stroke after 365 days after receiving treatment, we look at the rightmost column (365 days), at the intersection of control and no event: 199.\n\n\n::: {#tbl-stentStudyResultsDFsummary .cell tbl-cap='Descriptive statistics for the stent study.' fig.asp='0.618'}\n::: {.cell-output-display}\n`````{=html}\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
30 days
365 days
Group Stroke No event Stroke No event
Control 13 214 28 199
Treatment 33 191 45 179
Total 46 405 73 378
\n\n`````\n:::\n:::\n\n\n::: {.guidedpractice data-latex=\"\"}\nOf the 224 patients in the treatment group, 45 had a stroke by the end of the first year.\nUsing these two numbers, compute the proportion of patients in the treatment group who had a stroke by the end of their first year.\n(Note: answers to all Guided Practice exercises are provided in footnotes!)[^01-data-hello-1]\n:::\n\n[^01-data-hello-1]: The proportion of the 224 patients who had a stroke within 365 days: $45/224 = 0.20.$\n\nWe can compute summary statistics from the table to give us a better idea of how the impact of the stent treatment differed between the two groups.\nA **summary statistic** is a single number summarizing data from a sample.\nFor instance, the primary results of the study after 1 year could be described by two summary statistics: the proportion of people who had a stroke in the treatment and control groups.\n\n\n\n\n\n- Proportion who had a stroke in the treatment (stent) group: $45/224 = 0.20 = 20\\%.$\n- Proportion who had a stroke in the control group: $28/227 = 0.12 = 12\\%.$\n\nThese two summary statistics are useful in looking for differences in the groups, and we are in for a surprise: an additional 8% of patients in the treatment group had a stroke!\nThis is important for two reasons.\nFirst, it is contrary to what doctors expected, which was that stents would *reduce* the rate of strokes.\nSecond, it leads to a statistical question: do the data show a \"real\" difference between the groups?\n\nThis second question is subtle.\nSuppose you flip a coin 100 times.\nWhile the chance a coin lands heads in any given coin flip is 50%, we probably won't observe exactly 50 heads.\nThis type of variation is part of almost any type of data generating process.\nIt is possible that the 8% difference in the stent study is due to this natural variation.\nHowever, the larger the difference we observe (for a particular sample size), the less believable it is that the difference is due to chance.\nSo, what we are really asking is the following: if in fact stents have no effect, how likely is it that we observe such a large difference?\n\nWhile we do not yet have statistical tools to fully address this question on our own, we can comprehend the conclusions of the published analysis: there was compelling evidence of harm by stents in this study of stroke patients.\n\n**Be careful:** Do not generalize the results of this study to all patients and all stents.\nThis study looked at patients with very specific characteristics who volunteered to be a part of this study and who may not be representative of all stroke patients.\nIn addition, there are many types of stents, and this study only considered the self-expanding Wingspan stent (Boston Scientific).\nHowever, this study does leave us with an important lesson: we should keep our eyes open for surprises.\n\n## Data basics {#01-data-hello-sec-data-basics}\n\nEffective presentation and description of data is a first step in most analyses.\nThis section introduces one structure for organizing data as well as some terminology that will be used throughout this book.\n\n### Observations, variables, and data matrices\n\n@tbl-loan50-df displays six rows of a dataset for 50 randomly sampled loans offered through Lending Club, which is a peer-to-peer lending company.\nThis dataset will be referred to as `loan50`.\n\n::: {.data data-latex=\"\"}\nThe [`loan50`](http://openintrostat.github.io/openintro/reference/loans_full_schema.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n:::\n\nEach row in the table represents a single loan.\nThe formal name for a row is a \\index{case}**case** or \\index{unit of observation}**observational unit**.\nThe columns represent characteristics of each loan, where each column is referred to as a \\index{variable}**variable**.\nFor example, the first row represents a loan of \\$22,000 with an interest rate of 10.90%, where the borrower is based in New Jersey (NJ) and has an income of \\$59,000.\n\n\n\n\n\n::: {.guidedpractice data-latex=\"\"}\nWhat is the grade of the first loan in @tbl-loan50-df?\nAnd what is the home ownership status of the borrower for that first loan?\nReminder: for these Guided Practice questions, you can check your answer in the footnote.[^01-data-hello-2]\n:::\n\n[^01-data-hello-2]: The loan's grade is B, and the borrower rents their residence.\n\nIn practice, it is especially important to ask clarifying questions to ensure important aspects of the data are understood.\nFor instance, it is always important to be sure we know what each variable means and its units of measurement.\nDescriptions of the variables in the `loan50` dataset are given in @tbl-loan-50-variables.\n\n\n::: {#tbl-loan50-df .cell tbl-cap='Six observations from the `loan50` dataset.' fig.asp='0.618'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
loan_amount interest_rate term grade state total_income homeownership
1 22,000 10.90 60 B NJ 59,000 rent
2 6,000 9.92 36 B CA 60,000 rent
3 25,000 26.30 36 E SC 75,000 mortgage
4 6,000 9.92 36 B CA 75,000 rent
5 25,000 9.43 60 B OH 254,000 mortgage
6 6,400 9.92 36 B IN 67,000 mortgage
\n\n`````\n:::\n:::\n\n::: {#tbl-loan-50-variables .cell tbl-cap='Variables and their descriptions for the `loan50` dataset.' fig.asp='0.618'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Variable Description
loan_amount Amount of the loan received, in US dollars.
interest_rate Interest rate on the loan, in an annual percentage.
term The length of the loan, which is always set as a whole number of months.
grade Loan grade, which takes a values A through G and represents the quality of the loan and its likelihood of being repaid.
state US state where the borrower resides.
total_income Borrower's total income, including any second income, in US dollars.
homeownership Indicates whether the person owns, owns but has a mortgage, or rents.
\n\n`````\n:::\n:::\n\n\nThe data in @tbl-loan50-df represent a \\index{data frame}**data frame**, which is a convenient and common way to organize data, especially if collecting data in a spreadsheet.\nA data frame where each row is a unique case (observational unit), each column is a variable, and each cell is a single value is commonly referred to as \\index{tidy data}**tidy data** @wickham2014.\n\n\n\n\n\nWhen recording data, use a tidy data frame unless you have a very good reason to use a different structure.\nThis structure allows new cases to be added as rows or new variables as new columns and facilitates visualization, summarization, and other statistical analyses.\n\n::: {.guidedpractice data-latex=\"\"}\nThe grades for assignments, quizzes, and exams in a course are often recorded in a gradebook that takes the form of a data frame.\nHow might you organize a course's grade data using a data frame?\nDescribe the observational units and variables.[^01-data-hello-3]\n:::\n\n[^01-data-hello-3]: There are multiple strategies that can be followed.\n One common strategy is to have each student represented by a row, and then add a column for each assignment, quiz, or exam.\n Under this setup, it is easy to review a single line to understand the grade history of a student.\n There should also be columns to include student information, such as one column to list student names.\n\n::: {.guidedpractice data-latex=\"\"}\nWe consider data for 3,142 counties in the United States, which includes the name of each county, the state where it resides, its population in 2017, the population change from 2010 to 2017, poverty rate, and nine additional characteristics.\nHow might these data be organized in a data frame?[^01-data-hello-4]\n:::\n\n[^01-data-hello-4]: Each county may be viewed as a case, and there are eleven pieces of information recorded for each case.\n A table with 3,142 rows and 14 columns could hold these data, where each row represents a county and each column represents a particular piece of information.\n\n\\clearpage\n\nThe data described in the Guided Practice above represents the `county` dataset, which is shown as a data frame in @tbl-county-df.\nThe variables as well as the variables in the dataset that did not fit in @tbl-county-df are described in @tbl-county-variables.\n\n\n::: {#tbl-county-df .cell tbl-cap='Six observations and six variables from the `county` dataset.' fig.asp='0.618'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
name state pop2017 pop_change unemployment_rate median_edu
Autauga County Alabama 55,504 1.48 3.86 some_college
Baldwin County Alabama 212,628 9.19 3.99 some_college
Barbour County Alabama 25,270 -6.22 5.90 hs_diploma
Bibb County Alabama 22,668 0.73 4.39 hs_diploma
Blount County Alabama 58,013 0.68 4.02 hs_diploma
Bullock County Alabama 10,309 -2.28 4.93 hs_diploma
\n\n`````\n:::\n:::\n\n::: {#tbl-county-variables .cell tbl-cap='Variables and their descriptions for the `county` dataset.' fig.asp='0.618'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Variable Description
name Name of county.
state Name of state.
pop2000 Population in 2000.
pop2010 Population in 2010.
pop2017 Population in 2017.
pop_change Population change from 2010 to 2017 (in percent).
poverty Percent of population in poverty in 2017.
homeownership Homeownership rate, 2006-2010.
multi_unit Multi-unit rate: percent of housing units that are in multi-unit structures, 2006-2010.
unemployment_rate Unemployment rate in 2017.
metro Whether the county contains a metropolitan area, taking one of the values yes or no.
median_edu Median education level (2013-2017), taking one of the values below_hs, hs_diploma, some_college, or bachelors.
per_capita_income Per capita (per person) income (2013-2017).
median_hh_income Median household income.
smoking_ban Describes the type of county-level smoking ban in place in 2010, taking one of the values none, partial, or comprehensive.
\n\n`````\n:::\n:::\n\n\n::: {.data data-latex=\"\"}\nThe [`county`](http://openintrostat.github.io/usdata/reference/county.html) data can be found in the [**usdata**](http://openintrostat.github.io/usdata) R package.\n:::\n\n### Types of variables {#01-data-hello-variable-types}\n\nExamine the `unemployment_rate`, `pop2017`, `state`, and `median_edu` variables in the `county` dataset.\nEach of these variables is inherently different from the other three, yet some share certain characteristics.\n\nFirst consider `unemployment_rate`, which is said to be a \\index{numerical variable}**numerical** variable since it can take a wide range of numerical values, and it is sensible to add, subtract, or take averages with those values.\nOn the other hand, we would not classify a variable reporting telephone area codes as numerical since the average, sum, and difference of area codes does not have any clear meaning.\nInstead, we would consider area codes as a categorical variable.\n\n\n\n\n\nThe `pop2017` variable is also numerical, although it seems to be a little different than `unemployment_rate`.\nThis variable of the population count can only take whole non-negative numbers (0, 1, 2, ...).\nFor this reason, the population variable is said to be **discrete** since it can only take numerical values with jumps.\nOn the other hand, the unemployment rate variable is said to be **continuous**.\n\n\n\n\n\nThe variable `state` can take up to 51 values after accounting for Washington, DC: Alabama, Alaska, ..., and Wyoming.\nBecause the responses themselves are categories, `state` is called a **categorical** variable, and the possible values (states) are called the variable's **levels** (e.g., District of Columbia, Alabama, Alaska, etc.) .\n\n\n\n\n\nFinally, consider the `median_edu` variable, which describes the median education level of county residents and takes values `below_hs`, `hs_diploma`, `some_college`, or `bachelors` in each county.\nThis variable seems to be a hybrid: it is a categorical variable, but the levels have a natural ordering.\nA variable with these properties is called an **ordinal** variable, while a regular categorical variable without this type of special ordering is called a **nominal** variable.\nTo simplify analyses, any categorical variable in this book will be treated as a nominal (unordered) categorical variable.\n\n\n\n\n::: {.cell fig.asp='0.5'}\n::: {.cell-output-display}\n![Breakdown of variables into their respective types.](01-data-hello_files/figure-html/variables-1.png){fig-alt='Types of variables are broken down into numerical (which can be discrete or continuous) and categorical (which can be ordinal or nominal).' width=90%}\n:::\n:::\n\n\n::: {.workedexample data-latex=\"\"}\nData were collected about students in a statistics course.\nThree variables were recorded for each student: number of siblings, student height, and whether the student had previously taken a statistics course.\nClassify each of the variables as continuous numerical, discrete numerical, or categorical.\n\n------------------------------------------------------------------------\n\nThe number of siblings and student height represent numerical variables.\nBecause the number of siblings is a count, it is discrete.\nHeight varies continuously, so it is a continuous numerical variable.\nThe last variable classifies students into two categories -- those who have and those who have not taken a statistics course -- which makes this variable categorical.\n:::\n\n::: {.guidedpractice data-latex=\"\"}\nAn experiment is evaluating the effectiveness of a new drug in treating migraines.\nA `group` variable is used to indicate the experiment group for each patient: treatment or control.\nThe `num_migraines` variable represents the number of migraines the patient experienced during a 3-month period.\nClassify each variable as either numerical or categorical?[^01-data-hello-5]\n:::\n\n[^01-data-hello-5]: The `group` variable can take just one of two group names, making it categorical.\n The `num_migraines` variable describes a count of the number of migraines, which is an outcome where basic arithmetic is sensible, which means this is a numerical outcome; more specifically, since it represents a count, `num_migraines` is a discrete numerical variable.\n\n### Relationships between variables {#01-data-hello-variable-relations}\n\nMany analyses are motivated by a researcher looking for a relationship between two or more variables.\nA social scientist may like to answer some of the following questions:\n\n> Does a higher-than-average increase in county population tend to correspond to counties with higher or lower median household incomes?\n\n> If homeownership in one county is lower than the national average, will the percent of housing units that are in multi-unit structures in that county tend to be above or below the national average?\n\n> How much can the median education level explain the median household income for counties in the US?\n\nTo answer these questions, data must be collected, such as the `county` dataset shown in @tbl-county-df.\nExamining \\index{summary statistic}**summary statistics** can provide numerical insights about the specifics of each of these questions.\nAlternatively, graphs can be used to visually explore the data, potentially providing more insight than a summary statistic.\n\n\\index{scatterplot}**Scatterplots** are one type of graph used to study the relationship between two numerical variables.\n@fig-county-multi-unit-homeownership displays the relationship between the variables `homeownership` and `multi_unit`, which is the percent of housing units that are in multi-unit structures (e.g., apartments, condos).\nEach point on the plot represents a single county.\nFor instance, the highlighted dot corresponds to County 413 in the `county` dataset: Chattahoochee County, Georgia, which has 39.4% of housing units that are in multi-unit structures and a homeownership rate of 31.3%.\nThe scatterplot suggests a relationship between the two variables: counties with a higher rate of housing units that are in multi-unit structures tend to have lower homeownership rates.\nWe might brainstorm as to why this relationship exists and investigate each idea to determine which are the most reasonable explanations.\n\n\n::: {.cell fig.asp='0.618'}\n::: {.cell-output-display}\n![A scatterplot of homeownership versus the percent of housing units that are in multi-unit structures for US counties. The highlighted dot represents Chattahoochee County, Georgia, which has a multi-unit rate of 39.4\\% and a homeownership rate of 31.3\\%.](01-data-hello_files/figure-html/fig-county-multi-unit-homeownership-1.png){#fig-county-multi-unit-homeownership width=90%}\n:::\n:::\n\n\nThe multi-unit and homeownership rates are said to be associated because the plot shows a discernible pattern.\nWhen two variables show some connection with one another, they are called **associated** variables.\n\n\n\n\n\n::: {.guidedpractice data-latex=\"\"}\nExamine the variables in the `loan50` dataset, which are described in @tbl-loan-50-variables.\nCreate two questions about possible relationships between variables in `loan50` that are of interest to you.[^01-data-hello-6]\n:::\n\n[^01-data-hello-6]: Two example questions: (1) What is the relationship between loan amount and total income?\n (2) If someone's income is above the average, will their interest rate tend to be above or below the average?\n\n::: {.workedexample data-latex=\"\"}\nThis example examines the relationship between the percent change in population from 2010 to 2017 and median household income for counties, which is visualized as a scatterplot in @fig-county-pop-change-med-hh-income.\nAre these variables associated?\n\n------------------------------------------------------------------------\n\nThe larger the median household income for a county, the higher the population growth observed for the county.\nWhile it isn't true that every county with a higher median household income has a higher population growth, the trend in the plot is evident.\nSince there is some relationship between the variables, they are associated.\n:::\n\n\n::: {.cell fig.asp='0.618'}\n::: {.cell-output-display}\n![A scatterplot showing population change against median household income. Owsley County of Kentucky is highlighted, which lost 3.63\\% of its population from 2010 to 2017 and had median household income of \\$22,736.](01-data-hello_files/figure-html/fig-county-pop-change-med-hh-income-1.png){#fig-county-pop-change-med-hh-income width=90%}\n:::\n:::\n\n\nBecause there is a downward trend in @fig-county-multi-unit-homeownership -- counties with more housing units that are in multi-unit structures are associated with lower homeownership -- these variables are said to be **negatively associated**.\nA **positive association** is shown in the relationship between the `median_hh_income` and `pop_change` variables in @fig-county-pop-change-med-hh-income, where counties with higher median household income tend to have higher rates of population growth.\n\n\n\n\n\nIf two variables are not associated, then they are said to be **independent**.\nThat is, two variables are independent if there is no evident relationship between the two.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Associated or independent, not both.**\n\nA pair of variables are either related in some way (associated) or not (independent).\nNo pair of variables is both associated and independent.\n:::\n\n### Explanatory and response variables\n\nWhen we ask questions about the relationship between two variables, we sometimes also want to determine if the change in one variable causes a change in the other.\nConsider the following rephrasing of an earlier question about the `county` dataset:\n\n> If there is an increase in the median household income in a county, does this drive an increase in its population?\n\nIn this question, we are asking whether one variable affects another.\nIf this is our underlying belief, then *median household income* is the **explanatory variable**, and the *population change* is the **response variable** in the hypothesized relationship.[^01-data-hello-7]\n\n[^01-data-hello-7]: In some disciplines, it's customary to refer to the explanatory variable as the **independent variable** and the response variable as the **dependent variable**.\n However, this becomes confusing since a *pair* of variables might be independent or dependent, so we avoid this language.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Explanatory and response variables.**\n\nWhen we suspect one variable might causally affect another, we label the first variable the explanatory variable and the second the response variable.\nWe also use the terms **explanatory** and **response** to describe variables where the **response** might be predicted using the **explanatory** even if there is no causal relationship.\n\n
explanatory variable $\\rightarrow$ *might affect* $\\rightarrow$ response variable
\n\n
For many pairs of variables, there is no hypothesized relationship, and these labels would not be applied to either variable in such cases.\n:::\n\nBear in mind that the act of labeling the variables in this way does nothing to guarantee that a causal relationship exists.\nA formal evaluation to check whether one variable causes a change in another requires an experiment.\n\n### Observational studies and experiments\n\nThere are two primary types of data collection: experiments and observational studies.\n\nWhen researchers want to evaluate the effect of particular traits, treatments, or conditions, they conduct an **experiment**.\nFor instance, we may suspect drinking a high-calorie energy drink will improve performance in a race.\nTo check if there really is a causal relationship between the explanatory variable (whether the runner drank an energy drink or not) and the response variable (the race time), researchers identify a sample of individuals and split them into groups.\nThe individuals in each group are *assigned* a treatment.\nWhen individuals are randomly assigned to a group, the experiment is called a **randomized experiment**.\nRandom assignment organizes the participants in a study into groups that are roughly equal on all aspects, thus allowing us to control for any confounding variables that might affect the outcome (e.g., fitness level, racing experience, etc.).\nFor example, each runner in the experiment could be randomly assigned, perhaps by flipping a coin, into one of two groups: the first group receives a **placebo** (fake treatment, in this case a no-calorie drink) and the second group receives the high-calorie energy drink.\nSee the case study in @sec-case-study-stents-strokes for another example of an experiment, though that study did not employ a placebo.\n\n\n\n\n\nResearchers perform an **observational study** when they collect data in a way that does not directly interfere with how the data arise.\nFor instance, researchers may collect information via surveys, review medical or company records, or follow a **cohort** of many similar individuals to form hypotheses about why certain diseases might develop.\nIn each of these situations, researchers merely observe the data that arise.\nIn general, observational studies can provide evidence of a naturally occurring association between variables, but they cannot by themselves show a causal connection as they do not offer a mechanism for controlling for confounding variables.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Association** $\\neq$ **Causation.**\n\nIn general, association does not imply causation.\nAn advantage of a randomized experiment is that it is easier to establish causal relationships with such a study.\nThe main reason for this is that observational studies do not control for confounding variables, and hence establishing causal relationships with observational studies requires advanced statistical methods (that are beyond the scope of this book).\nWe will revisit this idea when we discuss experiments later in the book.\n:::\n\n\\vspace{10mm}\n\n## Chapter review {#01-data-hello-chp1-review}\n\n### Summary\n\nThis chapter introduced you to the world of data.\nData can be organized in many ways but tidy data, where each row represents an observation and each column represents a variable, lends itself most easily to statistical analysis.\nMany of the ideas from this chapter will be seen as we move on to doing full data analyses.\nIn the next chapter you're going to learn about how we can design studies to collect the data we need to make conclusions with the desired scope of inference.\n\n### Terms\n\nWe introduced the following terms in the chapter.\nIf you're not sure what some of these terms mean, we recommend you go back in the text and review their definitions.\nWe are purposefully presenting them in alphabetical order, instead of in order of appearance, so they will be a little more challenging to locate.\nHowever, you should be able to easily spot them as **bolded text**.\n\n\n::: {.cell fig.asp='0.618'}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
associated experiment ordinal
case explanatory variable placebo
categorical independent positive association
cohort level randomized experiment
continuous negative association response variable
data nominal summary statistic
data frame numerical tidy data
dependent observational study variable
discrete observational unit
\n\n`````\n:::\n:::\n\n\n\\clearpage\n\n## Exercises {#01-data-hello-chp1-exercises}\n\nAnswers to odd-numbered exercises can be found in [Appendix -@sec-exercise-solutions-01].\n\n::: {.exercises data-latex=\"\"}\n1. **Marvel Cinematic Universe films.** The data frame below contains information on Marvel Cinematic Universe films through the Infinity saga (a movie storyline spanning from Ironman in 2008 to Endgame in 2019).\n Box office totals are given in millions of US Dollars.\n How many observations and how many variables does this data frame have?[^_01-ex-data-hello-1]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Length
Gross
Title Hrs Mins Release Date Opening Wknd US US World
1 Iron Man 2 6 5/2/2008 98.62 319.03 585.8
2 The Incredible Hulk 1 52 6/12/2008 55.41 134.81 264.77
3 Iron Man 2 2 4 5/7/2010 128.12 312.43 623.93
4 Thor 1 55 5/6/2011 65.72 181.03 449.33
5 Captain America: The First Avenger 2 4 7/22/2011 65.06 176.65 370.57
... ... ... ... ... ... ... ...
23 Spiderman: Far from Home 2 9 7/2/2019 92.58 390.53 1131.93
\n \n `````\n :::\n :::\n\n2. **Cherry Blossom Run.** The data frame below contains information on runners in the 2017 Cherry Blossom Run, which is an annual road race that takes place in Washington, DC. Most runners participate in a 10-mile run while a smaller fraction take part in a 5k run or walk.\n How many observations and how many variables does this data frame have?[^_01-ex-data-hello-2]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Time
Bib Name Sex Age City / Country Net Clock Pace Event
1 6 Hiwot G. F 21 Ethiopia 3217 3217 321 10 Mile
2 22 Buze D. F 22 Ethiopia 3232 3232 323 10 Mile
3 16 Gladys K. F 31 Kenya 3276 3276 327 10 Mile
4 4 Mamitu D. F 33 Ethiopia 3285 3285 328 10 Mile
5 20 Karolina N. F 35 Poland 3288 3288 328 10 Mile
... ... ... ... ... ... ... ... ... ...
19961 25153 Andres E. M 33 Woodbridge, VA 5287 5334 1700 5K
\n \n `````\n :::\n :::\n\n3. **Air pollution and birth outcomes, study components.** Researchers collected data to examine the relationship between air pollutants and preterm births in Southern California.\n During the study air pollution levels were measured by air quality monitoring stations.\n Specifically, levels of carbon monoxide were recorded in parts per million, nitrogen dioxide and ozone in parts per hundred million, and coarse particulate matter (PM$_{10}$) in $\\mu g/m^3$.\n Length of gestation data were collected on 143,196 births between the years 1989 and 1993, and air pollution exposure during gestation was calculated for each birth.\n The analysis suggested that increased ambient PM$_{10}$ and, to a lesser degree, CO concentrations may be associated with the occurrence of preterm births.\n [@Ritz+Yu+Chapa+Fruin:2000]\n\n a. Identify the main research question of the study.\n\n b. Who are the subjects in this study, and how many are included?\n\n c. What are the variables in the study?\n Identify each variable as numerical or categorical.\n If numerical, state whether the variable is discrete or continuous.\n If categorical, state whether the variable is ordinal.\n\n4. **Cheaters, study components.** Researchers studying the relationship between honesty, age and self-control conducted an experiment on 160 children between the ages of 5 and 15.\n Participants reported their age, sex, and whether they were an only child or not.\n The researchers asked each child to toss a fair coin in private and to record the outcome (white or black) on a paper sheet and said they would only reward children who report white.\n [@Bucciol:2011]\n\n a. Identify the main research question of the study.\n\n b. Who are the subjects in this study, and how many are included?\n\n c. The study's findings can be summarized as follows: *\"Half the students were explicitly told not to cheat, and the others were not given any explicit instructions. In the no instruction group probability of cheating was found to be uniform across groups based on child's characteristics. In the group that was explicitly told to not cheat, girls were less likely to cheat, and while rate of cheating didn't vary by age for boys, it decreased with age for girls.\"* How many variables were recorded for each subject in the study in order to conclude these findings?\n State the variables and their types.\n\n5. **Gamification and statistics, study components.** Gamification is the application of game-design elements and game principles in non-game contexts.\n In educational settings, gamification is often implemented as educational activities to solve problems by using characteristics of game elements.\n Researchers investigating the effects of gamification on learning statistics conducted a study where they split college students in a statistics class into four groups: (1) no reading exercises and no gamification, (2) reading exercises but no gamification, (3) gamification but no reading exercises, and (4) gamification and reading exercises.\n Students in all groups also attended lectures.\n Students in the class were from two majors: Electrical and Computer Engineering (n = 279) and Business Administration (n = 86).\n After their assigned learning experience, each student took a final evaluation comprised of 30 multiple choice question and their score was measured as the number of questions they answered correctly.\n The researchers considered students' gender, level of studies (first through fourth year) and academic major.\n Other variables considered were expertise in the English language and use of personal computers and games, both of which were measured on a scale of 1 (beginner) to 5 (proficient).\n The study found that gamification had a positive effect on student learning compared to traditional teaching methods involving lectures and reading exercises.\n They also found that the effect was larger for females and Engineering students.\n [@Legaki:2020]\n\n a. Identify the main research question of the study.\n\n b. Who were the subjects in this study, and how many were included?\n\n c. What are the variables in the study?\n Identify each variable as numerical or categorical.\n If numerical, state whether the variable is discrete or continuous.\n If categorical, state whether the variable is ordinal.\n\n6. **Stealers, study components.** In a study of the relationship between socio-economic class and unethical behavior, 129 University of California undergraduates at Berkeley were asked to identify themselves as having low or high social class by comparing themselves to others with the most (least) money, most (least) education, and most (least) respected jobs.\n They were also presented with a jar of individually wrapped candies and informed that the candies were for children in a nearby laboratory, but that they could take some if they wanted.\n After completing some unrelated tasks, participants reported the number of candies they had taken.\n [@Piff:2012]\n\n a. Identify the main research question of the study.\n\n b. Who were the subjects in this study, and how many were included?\n\n c. The study found that students who were identified as upper-class took more candy than others.\n How many variables were recorded for each subject in the study in order to conclude these findings?\n State the variables and their types.\n\n \\clearpage\n\n7. \"Figure **Migraine and acupuncture.** A migraine is a particularly painful type of headache, which patients sometimes wish to treat with acupuncture.\n To determine whether acupuncture relieves migraine pain, researchers conducted a randomized controlled study where 89 individuals who identified as female diagnosed with migraine headaches were randomly assigned to one of two groups: treatment or control.\n Forty-three (43) patients in the treatment group received acupuncture that is specifically designed to treat migraines.\n Forty-six (46) patients in the control group received placebo acupuncture (needle insertion at non-acupoint locations).\n Twenty-four (24) hours after patients received acupuncture, they were asked if they were pain free.\n Results are summarized in the contingency table below.\n Also provided is a figure from the original paper displaying the appropriate area (M) versus the inappropriate area (S) used in the treatment of migraine attacks.\n [^_01-ex-data-hello-3] [@Allais:2011]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Pain free?
Group No Yes
Control 44 2
Treatment 33 10
\n \n `````\n :::\n :::\n\n a. What percent of patients in the treatment group were pain free 24 hours after receiving acupuncture?\n\n b. What percent were pain free in the control group?\n\n c. In which group did a higher percent of patients become pain free 24 hours after receiving acupuncture?\n\n d. Your findings so far might suggest that acupuncture is an effective treatment for migraines for all people who suffer from migraines.\n However, this is not the only possible conclusion.\n What is one other possible explanation for the observed difference between the percentages of patients that are pain free 24 hours after receiving acupuncture in the two groups?\n\n e. What are the explanatory and response variables in this study?\n\n8. **Sinusitis and antibiotics.** Researchers studying the effect of antibiotic treatment for acute sinusitis compared to symptomatic treatments randomly assigned 166 adults diagnosed with acute sinusitis to one of two groups: treatment or control.\n Study participants received either a 10-day course of amoxicillin (an antibiotic) or a placebo similar in appearance and taste.\n The placebo consisted of symptomatic treatments such as acetaminophen, nasal decongestants, etc.\n At the end of the 10-day period, patients were asked if they experienced improvement in symptoms.\n The distribution of responses is summarized below.[^_01-ex-data-hello-4]\n [@Garbutt:2012]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Improvement
Group No Yes
Control 16 65
Treatment 19 66
\n \n `````\n :::\n :::\n\n a. What percent of patients in the treatment group experienced improvement in symptoms?\n\n b. What percent experienced improvement in symptoms in the control group?\n\n c. In which group did a higher percentage of patients experience improvement in symptoms?\n\n d. Your findings so far might suggest a real difference in the effectiveness of antibiotic and placebo treatments for improving symptoms of sinusitis.\n However, this is not the only possible conclusion.\n What is one other possible explanation for the observed difference between the percentages patients who experienced improvement in symptoms?\n\n e. What are the explanatory and response variables in this study?\n\n9. **Daycare fines, study components.** Researchers tested the deterrence hypothesis which predicts that the introduction of a penalty will reduce the occurrence of the behavior subject to the fine, with the condition that the fine leaves everything else unchanged by instituting a fine for late pickup at daycare centers.\n For this study, they worked with 10 volunteer daycare centers that did not originally impose a fine to parents for picking up their kids late.\n They randomly selected 6 of these daycare centers and instituted a monetary fine (of a considerable amount) for picking up children late and then removed it.\n In the remaining 4 daycare centers no fine was introduced.\n The study period was divided into four: before the fine (weeks 1--4), the first 4 weeks with the fine (weeks 5-8), the last 8 weeks with fine (weeks 9--16), and the after fine period (weeks 17-20).\n Throughout the study, the number of kids who were picked up late was recorded each week for each daycare.\n The study found that the number of late-coming parents increased discernibly when the fine was introduced, and no reduction occurred after the fine was removed.[^_01-ex-data-hello-5]\n [@Gneezy:2000]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
center week group late_pickups study_period
1 1 test 8 before fine
1 2 test 8 before fine
1 3 test 7 before fine
1 4 test 6 before fine
1 5 test 8 first 4 weeks with fine
... ... ... ... ...
10 20 control 13 after fine
\n \n `````\n :::\n :::\n\n a. Is this an observational study or an experiment?\n Explain your reasoning.\n\n b. What are the cases in this study and how many are included?\n\n c. What is the response variable in the study and what type of variable is it?\n\n d. What are the explanatory variables in the study and what types of variables are they?\n\n \\vspace{5mm}\n\n10. **Efficacy of COVID-19 vaccine on adolescents, study components.** Results of a Phase 3 trial announced in March 2021 show that the Pfizer-BioNTech COVID-19 vaccine demonstrated 100% efficacy and robust antibody responses on 12 to 15 years old adolescents with or without prior evidence of SARS-CoV-2 infection.\n In this trial 2,260 adolescents were randomly assigned to two groups: one group got the vaccine (n = 1,131) and the other got a placebo (n = 1,129).\n While 18 cases of COVID-19 were observed in the placebo group, none were observed in the vaccine group.[^_01-ex-data-hello-6]\n [@Pfizer:2021]\n\n a. Is this an observational study or an experiment?\n Explain your reasoning.\n\n b. What are the cases in this study and how many are included?\n\n c. What is the response variable in the study and what type of variable is it?\n\n d. What are the explanatory variables in the study and what types of variables are they?\n\n \\clearpage\n\n11. **Palmer penguins.** Data were collected on 344 penguins living on three islands (Torgersen, Biscoe, and Dream) in the Palmer Archipelago, Antarctica.\n In addition to which island each penguin lives on, the data contains information on the species of the penguin (*Adelie*, *Chinstrap*, or *Gentoo*), its bill length, bill depth, and flipper length (measured in millimeters), its body mass (measured in grams), and the sex of the penguin (female or male).[^_01-ex-data-hello-7]\n Bill length and depth are measured as shown in the image.\n [^_01-ex-data-hello-8] [@palmerpenguins]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n ![](exercises/images/culmen_depth.png){fig-alt='Bill length and depth marked on an illustration of a penguin head.' width=40%}\n :::\n :::\n\n a. How many cases were included in the data?\n b. How many numerical variables are included in the data? Indicate what they are, and if they are continuous or discrete.\n c. How many categorical variables are included in the data, and what are they? List the corresponding levels (categories) for each.\n\n \\vspace{5mm}\n\n12. **Smoking habits of UK residents.** A survey was conducted to study the smoking habits of 1,691 UK residents.\n Below is a data frame displaying a portion of the data collected in this survey.\n A blank cell indicates that data for that variable was not available for a given respondent.[^_01-ex-data-hello-9]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
amount
sex age marital_status gross_income smoke weekend weekday
1 Female 61 Married 2,600 to 5,200 No
2 Female 61 Divorced 10,400 to 15,600 Yes 5 4
3 Female 69 Widowed 5,200 to 10,400 No
4 Female 50 Married 5,200 to 10,400 No
5 Male 31 Single 10,400 to 15,600 Yes 10 20
... ... ... ... ... ...
1691 Male 49 Divorced Above 36,400 Yes 15 10
\n \n `````\n :::\n :::\n\n a. What does each row of the data frame represent?\n\n b. How many participants were included in the survey?\n\n c. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n \\clearpage\n\n13. **US Airports.** The visualization below shows the geographical distribution of airports in the contiguous United States and Washington, DC. This visualization was constructed based on a dataset where each observation is an airport.[^_01-ex-data-hello-10]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-33-1.png){width=90%}\n :::\n :::\n\n a. List the variables you believe were necessary to create this visualization.\n\n b. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n \\vspace{5mm}\n\n14. **UN Votes.** The visualization below shows voting patterns in the United States, Canada, and Mexico in the United Nations General Assembly on a variety of issues.\n Specifically, for a given year between 1946 and 2019, it displays the percentage of roll calls in which the country voted yes for each issue.\n This visualization was constructed based on a dataset where each observation is a country/year pair.[^_01-ex-data-hello-11]\n\n ::: {.cell fig.asp='0.8'}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-34-1.png){width=90%}\n :::\n :::\n\n a. List the variables used in creating this visualization.\n\n b. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n15. **UK baby names.** The visualization below shows the number of baby girls born in the United Kingdom (comprised of England & Wales, Northern Ireland, and Scotland) who were given the name \"Fiona\" over the years.[^_01-ex-data-hello-12]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-35-1.png){width=90%}\n :::\n :::\n\n a. List the variables you believe were necessary to create this visualization.\n\n b. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n \\vspace{5mm}\n\n16. **Shows on Netflix.** The visualization below shows the distribution of ratings of TV shows on Netflix (a streaming entertainment service) based on the decade they were released in and the country they were produced in.\n In the dataset, each observation is a TV show.[^_01-ex-data-hello-13]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-36-1.png){width=90%}\n :::\n :::\n\n a. List the variables you believe were necessary to create this visualization.\n\n b. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n \\clearpage\n\n17. **Stanford Open Policing.** The Stanford Open Policing project gathers, analyzes, and releases records from traffic stops by law enforcement agencies across the United States.\n Their goal is to help researchers, journalists, and policy makers investigate and improve interactions between police and the public.\n The following is an excerpt from a summary table created based off the data collected as part of this project.\n [@pierson2020large]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Driver
Car
County State Race / Ethnicity Arrest rate Stops / year Search rate
Apache County AZ Black 0.016 266 0.077
Apache County AZ Hispanic 0.018 1008 0.053
Apache County AZ White 0.006 6322 0.017
Cochise County AZ Black 0.015 1169 0.047
Cochise County AZ Hispanic 0.01 9453 0.037
Cochise County AZ White 0.008 10826 0.024
... ... ... ... ... ...
Wood County WI Black 0.098 16 0.244
Wood County WI Hispanic 0.029 27 0.036
Wood County WI White 0.029 1157 0.033
\n \n `````\n :::\n :::\n\n a. What variables were collected on each individual traffic stop in order to create the summary table above?\n\n b. State whether each variable is numerical or categorical.\n If numerical, state whether it is continuous or discrete.\n If categorical, state whether it is ordinal or not.\n\n c. Suppose we wanted to evaluate whether vehicle search rates are different for drivers of different races.\n In this analysis, which variable would be the response variable and which variable would be the explanatory variable?\n\n \\vspace{5mm}\n\n18. **Space launches.** The following summary table shows the number of space launches in the US by the type of launching agency and the outcome of the launch (success or failure).[^_01-ex-data-hello-14]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
1957 - 1999
2000-2018
Failure Success Failure Success
Private 13 295 10 562
State 281 3751 33 711
Startup 0 0 5 65
\n \n `````\n :::\n :::\n\n a. What variables were collected on each launch in order to create to the summary table above?\n\n b. State whether each variable is numerical or categorical.\n If numerical, state whether it is continuous or discrete.\n If categorical, state whether it is ordinal or not.\n\n c. Suppose we wanted to study how the success rate of launches vary between launching agencies and over time.\n In this analysis, which variable would be the response variable and which variable would be the explanatory variable?\n\n \\clearpage\n\n19. **Pet names.** The city of Seattle, WA has an open data portal that includes pets registered in the city.\n For each registered pet, we have information on the pet's name and species.\n The following visualization plots the proportion of dogs with a given name versus the proportion of cats with the same name.\n The 20 most common cat and dog names are displayed.\n The diagonal line on the plot is the $x = y$ line; if a name appeared on this line, the name's popularity would be exactly the same for dogs and cats.[^_01-ex-data-hello-15]\n\n ::: {.cell fig.asp='0.618'}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-39-1.png){width=90%}\n :::\n :::\n\n a. Are these data collected as part of an experiment or an observational study?\n\n b. What is the most common dog name?\n What is the most common cat name?\n\n c. What names are more common for cats than dogs?\n\n d. Is the relationship between the two variables positive or negative?\n What does this mean in context of the data?\n\n \\vspace{5mm}\n\n20. **Stressed out in an elevator.** In a study evaluating the relationship between stress and muscle cramps, half the subjects are randomly assigned to be exposed to increased stress by being placed into an elevator that falls rapidly and stops abruptly and the other half are left at no or baseline stress.\n\n a. What type of study is this?\n\n b. Can this study be used to conclude a causal relationship between increased stress and muscle cramps?\n\n[^_01-ex-data-hello-1]: The [`mcu_films`](http://openintrostat.github.io/openintro/reference/mcu_films.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-2]: The [`run17`](http://openintrostat.github.io/openintro/reference/run17.html) data used in this exercise can be found in the [**cherryblossom**](http://openintrostat.github.io/cherryblossom) R package.\n\n[^_01-ex-data-hello-3]: The [`migraine`](http://openintrostat.github.io/openintro/reference/migraine.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-4]: The [`sinusitis`](http://openintrostat.github.io/openintro/reference/sinusitis.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-5]: The [`daycare_fines`](http://openintrostat.github.io/openintro/reference/daycare_fines.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-6]: The [`biontech_adolescents`](http://openintrostat.github.io/openintro/reference/biontech_adolescents.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-7]: The [`penguins`](https://allisonhorst.github.io/palmerpenguins/reference/penguins.html) data used in this exercise can be found in the [**palmerpenguins**](https://allisonhorst.github.io/palmerpenguins/) R package.\n\n[^_01-ex-data-hello-8]: Artwork by [Allison Horst](https://twitter.com/allison_horst).\n\n[^_01-ex-data-hello-9]: The [`smoking`](http://openintrostat.github.io/openintro/reference/smoking.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-10]: The [`usairports`](http://openintrostat.github.io/airports/reference/usairports.html) data used in this exercise can be found in the [**airports**](http://openintrostat.github.io/airports/) R package.\n\n[^_01-ex-data-hello-11]: The data used in this exercise can be found in the [**unvotes**](https://cran.r-project.org/web/packages/unvotes/index.html) R package.\n\n[^_01-ex-data-hello-12]: The [`ukbabynames`](https://mine-cetinkaya-rundel.github.io/ukbabynames/reference/ukbabynames.html) data used in this exercise can be found in the [**ukbabynames**](https://mine-cetinkaya-rundel.github.io/ukbabynames/) R package.\n\n[^_01-ex-data-hello-13]: The [`netflix_titles`](https://github.com/rfordatascience/tidytuesday/blob/master/data/2021/2021-04-20/readme.md) data used in this exercise can be found in the [**tidytuesdayR**](https://cran.r-project.org/web/packages/tidytuesdayR/index.html) R package.\n\n[^_01-ex-data-hello-14]: The data used in this exercise comes from the [JSR Launch Vehicle Database, 2019 Feb 10 Edition](https://www.openintro.org/go?id=textbook-space-launches-data&referrer=ims0_html).\n\n[^_01-ex-data-hello-15]: The [`seattlepets`](http://openintrostat.github.io/openintro/reference/seattlepets.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n\n:::\n", + "engine": "knitr", + "markdown": "# Hello data {#sec-data-hello}\n\n\n\n\n\n::: {.chapterintro data-latex=\"\"}\nScientists seek to answer questions using rigorous methods and careful observations.\nThese observations -- collected from the likes of field notes, surveys, and experiments -- form the backbone of a statistical investigation and are called **data**.\nStatistics is the study of how best to collect, analyze, and draw conclusions from data.\nIn this first chapter, we focus on both the properties of data and on the collection of data.\n:::\n\n\n\n\n\n## Case study: Using stents to prevent strokes {sec-case-study-stents-strokes}\n\nIn this section we introduce a classic challenge in statistics: evaluating the efficacy of a medical treatment.\nTerms in this section, and indeed much of this chapter, will all be revisited later in the text.\nThe plan for now is simply to get a sense of the role statistics can play in practice.\n\nAn experiment is designed to study the effectiveness of stents in treating patients at risk of stroke [@chimowitz2011stenting].\nStents are small mesh tubes that are placed inside narrow or weak arteries to assist in patient recovery after cardiac events and reduce the risk of an additional heart attack or death.\n\nMany doctors have hoped that there would be similar benefits for patients at risk of stroke.\nWe start by writing the principal question the researchers hope to answer:\n\n> Does the use of stents reduce the risk of stroke?\n\nThe researchers who asked this question conducted an experiment with 451 at-risk patients.\nEach volunteer patient was randomly assigned to one of two groups:\n\n- **Treatment group**. Patients in the treatment group received a stent and medical management. The medical management included medications, management of risk factors, and help in lifestyle modification.\n- **Control group**. Patients in the control group received the same medical management as the treatment group, but they did not receive stents.\n\nResearchers randomly assigned 224 patients to the treatment group and 227 to the control group.\nIn this study, the control group provides a reference point against which we can measure the medical impact of stents in the treatment group.\n\n\\clearpage\n\nResearchers studied the effect of stents at two time points: 30 days after enrollment and 365 days after enrollment.\nThe results of 5 patients are summarized in @tbl-stentStudyResultsDF.\nPatient outcomes are recorded as `stroke` or `no event`, representing whether the patient had a stroke during that time period.\n\n::: {.data data-latex=\"\"}\nThe [`stent30`](http://openintrostat.github.io/openintro/reference/stent30.html) data and [`stent365`](http://openintrostat.github.io/openintro/reference/stent365.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n:::\n\n\n::: {#tbl-stentStudyResultsDF .cell tbl-cap='Results for five patients from the stent study.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
patient group 30 days 365 days
1 treatment no event no event
2 treatment stroke stroke
3 treatment no event no event
4 treatment no event no event
5 control no event no event
\n\n`````\n:::\n:::\n\n\nIt would be difficult to answer a question on the impact of stents on the occurrence of strokes for **all** study patients using these *individual* observations.\nThis question is better addressed by performing a statistical data analysis of *all* observations.\n@tbl-stentStudyResultsDFsummary summarizes the raw data in a more helpful way.\nIn this table, we can quickly see what happened over the entire study.\nFor instance, to identify the number of patients in the treatment group who had a stroke within 30 days after the treatment, we look in the leftmost column (30 days), at the intersection of treatment and stroke: 33.\nTo identify the number of control patients who did not have a stroke after 365 days after receiving treatment, we look at the rightmost column (365 days), at the intersection of control and no event: 199.\n\n\n::: {#tbl-stentStudyResultsDFsummary .cell tbl-cap='Descriptive statistics for the stent study.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
30 days
365 days
Group Stroke No event Stroke No event
Control 13 214 28 199
Treatment 33 191 45 179
Total 46 405 73 378
\n\n`````\n:::\n:::\n\n\n::: {.guidedpractice data-latex=\"\"}\nOf the 224 patients in the treatment group, 45 had a stroke by the end of the first year.\nUsing these two numbers, compute the proportion of patients in the treatment group who had a stroke by the end of their first year.\n(Note: answers to all Guided Practice exercises are provided in footnotes!)[^01-data-hello-1]\n:::\n\n[^01-data-hello-1]: The proportion of the 224 patients who had a stroke within 365 days: $45/224 = 0.20.$\n\nWe can compute summary statistics from the table to give us a better idea of how the impact of the stent treatment differed between the two groups.\nA **summary statistic** is a single number summarizing data from a sample.\nFor instance, the primary results of the study after 1 year could be described by two summary statistics: the proportion of people who had a stroke in the treatment and control groups.\n\n\n\n\n\n- Proportion who had a stroke in the treatment (stent) group: $45/224 = 0.20 = 20\\%.$\n- Proportion who had a stroke in the control group: $28/227 = 0.12 = 12\\%.$\n\nThese two summary statistics are useful in looking for differences in the groups, and we are in for a surprise: an additional 8% of patients in the treatment group had a stroke!\nThis is important for two reasons.\nFirst, it is contrary to what doctors expected, which was that stents would *reduce* the rate of strokes.\nSecond, it leads to a statistical question: do the data show a \"real\" difference between the groups?\n\nThis second question is subtle.\nSuppose you flip a coin 100 times.\nWhile the chance a coin lands heads in any given coin flip is 50%, we probably won't observe exactly 50 heads.\nThis type of variation is part of almost any type of data generating process.\nIt is possible that the 8% difference in the stent study is due to this natural variation.\nHowever, the larger the difference we observe (for a particular sample size), the less believable it is that the difference is due to chance.\nSo, what we are really asking is the following: if in fact stents have no effect, how likely is it that we observe such a large difference?\n\nWhile we do not yet have statistical tools to fully address this question on our own, we can comprehend the conclusions of the published analysis: there was compelling evidence of harm by stents in this study of stroke patients.\n\n**Be careful:** Do not generalize the results of this study to all patients and all stents.\nThis study looked at patients with very specific characteristics who volunteered to be a part of this study and who may not be representative of all stroke patients.\nIn addition, there are many types of stents, and this study only considered the self-expanding Wingspan stent (Boston Scientific).\nHowever, this study does leave us with an important lesson: we should keep our eyes open for surprises.\n\n## Data basics {sec-data-basics}\n\nEffective presentation and description of data is a first step in most analyses.\nThis section introduces one structure for organizing data as well as some terminology that will be used throughout this book.\n\n### Observations, variables, and data matrices\n\n@tbl-loan50-df displays six rows of a dataset for 50 randomly sampled loans offered through Lending Club, which is a peer-to-peer lending company.\nThis dataset will be referred to as `loan50`.\n\n::: {.data data-latex=\"\"}\nThe [`loan50`](http://openintrostat.github.io/openintro/reference/loans_full_schema.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n:::\n\nEach row in the table represents a single loan.\nThe formal name for a row is a \\index{case}**case** or \\index{unit of observation}**observational unit**.\nThe columns represent characteristics of each loan, where each column is referred to as a \\index{variable}**variable**.\nFor example, the first row represents a loan of \\$22,000 with an interest rate of 10.90%, where the borrower is based in New Jersey (NJ) and has an income of \\$59,000.\n\n\n\n\n\n::: {.guidedpractice data-latex=\"\"}\nWhat is the grade of the first loan in @tbl-loan50-df?\nAnd what is the home ownership status of the borrower for that first loan?\nReminder: for these Guided Practice questions, you can check your answer in the footnote.[^01-data-hello-2]\n:::\n\n[^01-data-hello-2]: The loan's grade is B, and the borrower rents their residence.\n\nIn practice, it is especially important to ask clarifying questions to ensure important aspects of the data are understood.\nFor instance, it is always important to be sure we know what each variable means and its units of measurement.\nDescriptions of the variables in the `loan50` dataset are given in @tbl-loan-50-variables.\n\n\n::: {#tbl-loan50-df .cell tbl-cap='Six observations from the `loan50` dataset.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
loan_amount interest_rate term grade state total_income homeownership
1 22,000 10.90 60 B NJ 59,000 rent
2 6,000 9.92 36 B CA 60,000 rent
3 25,000 26.30 36 E SC 75,000 mortgage
4 6,000 9.92 36 B CA 75,000 rent
5 25,000 9.43 60 B OH 254,000 mortgage
6 6,400 9.92 36 B IN 67,000 mortgage
\n\n`````\n:::\n:::\n\n::: {#tbl-loan-50-variables .cell tbl-cap='Variables and their descriptions for the `loan50` dataset.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Variable Description
loan_amount Amount of the loan received, in US dollars.
interest_rate Interest rate on the loan, in an annual percentage.
term The length of the loan, which is always set as a whole number of months.
grade Loan grade, which takes a values A through G and represents the quality of the loan and its likelihood of being repaid.
state US state where the borrower resides.
total_income Borrower's total income, including any second income, in US dollars.
homeownership Indicates whether the person owns, owns but has a mortgage, or rents.
\n\n`````\n:::\n:::\n\n\nThe data in @tbl-loan50-df represent a \\index{data frame}**data frame**, which is a convenient and common way to organize data, especially if collecting data in a spreadsheet.\nA data frame where each row is a unique case (observational unit), each column is a variable, and each cell is a single value is commonly referred to as \\index{tidy data}**tidy data** @wickham2014.\n\n\n\n\n\nWhen recording data, use a tidy data frame unless you have a very good reason to use a different structure.\nThis structure allows new cases to be added as rows or new variables as new columns and facilitates visualization, summarization, and other statistical analyses.\n\n::: {.guidedpractice data-latex=\"\"}\nThe grades for assignments, quizzes, and exams in a course are often recorded in a gradebook that takes the form of a data frame.\nHow might you organize a course's grade data using a data frame?\nDescribe the observational units and variables.[^01-data-hello-3]\n:::\n\n[^01-data-hello-3]: There are multiple strategies that can be followed.\n One common strategy is to have each student represented by a row, and then add a column for each assignment, quiz, or exam.\n Under this setup, it is easy to review a single line to understand the grade history of a student.\n There should also be columns to include student information, such as one column to list student names.\n\n::: {.guidedpractice data-latex=\"\"}\nWe consider data for 3,142 counties in the United States, which includes the name of each county, the state where it resides, its population in 2017, the population change from 2010 to 2017, poverty rate, and nine additional characteristics.\nHow might these data be organized in a data frame?[^01-data-hello-4]\n:::\n\n[^01-data-hello-4]: Each county may be viewed as a case, and there are eleven pieces of information recorded for each case.\n A table with 3,142 rows and 14 columns could hold these data, where each row represents a county and each column represents a particular piece of information.\n\n\\clearpage\n\nThe data described in the Guided Practice above represents the `county` dataset, which is shown as a data frame in @tbl-county-df.\nThe variables as well as the variables in the dataset that did not fit in @tbl-county-df are described in @tbl-county-variables.\n\n\n::: {#tbl-county-df .cell tbl-cap='Six observations and six variables from the `county` dataset.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
name state pop2017 pop_change unemployment_rate median_edu
Autauga County Alabama 55,504 1.48 3.86 some_college
Baldwin County Alabama 212,628 9.19 3.99 some_college
Barbour County Alabama 25,270 -6.22 5.90 hs_diploma
Bibb County Alabama 22,668 0.73 4.39 hs_diploma
Blount County Alabama 58,013 0.68 4.02 hs_diploma
Bullock County Alabama 10,309 -2.28 4.93 hs_diploma
\n\n`````\n:::\n:::\n\n::: {#tbl-county-variables .cell tbl-cap='Variables and their descriptions for the `county` dataset.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Variable Description
name Name of county.
state Name of state.
pop2000 Population in 2000.
pop2010 Population in 2010.
pop2017 Population in 2017.
pop_change Population change from 2010 to 2017 (in percent).
poverty Percent of population in poverty in 2017.
homeownership Homeownership rate, 2006-2010.
multi_unit Multi-unit rate: percent of housing units that are in multi-unit structures, 2006-2010.
unemployment_rate Unemployment rate in 2017.
metro Whether the county contains a metropolitan area, taking one of the values yes or no.
median_edu Median education level (2013-2017), taking one of the values below_hs, hs_diploma, some_college, or bachelors.
per_capita_income Per capita (per person) income (2013-2017).
median_hh_income Median household income.
smoking_ban Describes the type of county-level smoking ban in place in 2010, taking one of the values none, partial, or comprehensive.
\n\n`````\n:::\n:::\n\n\n::: {.data data-latex=\"\"}\nThe [`county`](http://openintrostat.github.io/usdata/reference/county.html) data can be found in the [**usdata**](http://openintrostat.github.io/usdata) R package.\n:::\n\n### Types of variables {variable-types}\n\nExamine the `unemployment_rate`, `pop2017`, `state`, and `median_edu` variables in the `county` dataset.\nEach of these variables is inherently different from the other three, yet some share certain characteristics.\n\nFirst consider `unemployment_rate`, which is said to be a \\index{numerical variable}**numerical** variable since it can take a wide range of numerical values, and it is sensible to add, subtract, or take averages with those values.\nOn the other hand, we would not classify a variable reporting telephone area codes as numerical since the average, sum, and difference of area codes does not have any clear meaning.\nInstead, we would consider area codes as a categorical variable.\n\n\n\n\n\nThe `pop2017` variable is also numerical, although it seems to be a little different than `unemployment_rate`.\nThis variable of the population count can only take whole non-negative numbers (0, 1, 2, ...).\nFor this reason, the population variable is said to be **discrete** since it can only take numerical values with jumps.\nOn the other hand, the unemployment rate variable is said to be **continuous**.\n\n\n\n\n\nThe variable `state` can take up to 51 values after accounting for Washington, DC: Alabama, Alaska, ..., and Wyoming.\nBecause the responses themselves are categories, `state` is called a **categorical** variable, and the possible values (states) are called the variable's **levels** (e.g., District of Columbia, Alabama, Alaska, etc.) .\n\n\n\n\n\nFinally, consider the `median_edu` variable, which describes the median education level of county residents and takes values `below_hs`, `hs_diploma`, `some_college`, or `bachelors` in each county.\nThis variable seems to be a hybrid: it is a categorical variable, but the levels have a natural ordering.\nA variable with these properties is called an **ordinal** variable, while a regular categorical variable without this type of special ordering is called a **nominal** variable.\nTo simplify analyses, any categorical variable in this book will be treated as a nominal (unordered) categorical variable.\n\n\n\n\n::: {.cell}\n::: {.cell-output-display}\n![Breakdown of variables into their respective types.](01-data-hello_files/figure-html/variables-1.png){fig-alt='Types of variables are broken down into numerical (which can be discrete or continuous) and categorical (which can be ordinal or nominal).' width=90%}\n:::\n:::\n\n\n::: {.workedexample data-latex=\"\"}\nData were collected about students in a statistics course.\nThree variables were recorded for each student: number of siblings, student height, and whether the student had previously taken a statistics course.\nClassify each of the variables as continuous numerical, discrete numerical, or categorical.\n\n------------------------------------------------------------------------\n\nThe number of siblings and student height represent numerical variables.\nBecause the number of siblings is a count, it is discrete.\nHeight varies continuously, so it is a continuous numerical variable.\nThe last variable classifies students into two categories -- those who have and those who have not taken a statistics course -- which makes this variable categorical.\n:::\n\n::: {.guidedpractice data-latex=\"\"}\nAn experiment is evaluating the effectiveness of a new drug in treating migraines.\nA `group` variable is used to indicate the experiment group for each patient: treatment or control.\nThe `num_migraines` variable represents the number of migraines the patient experienced during a 3-month period.\nClassify each variable as either numerical or categorical?[^01-data-hello-5]\n:::\n\n[^01-data-hello-5]: The `group` variable can take just one of two group names, making it categorical.\n The `num_migraines` variable describes a count of the number of migraines, which is an outcome where basic arithmetic is sensible, which means this is a numerical outcome; more specifically, since it represents a count, `num_migraines` is a discrete numerical variable.\n\n### Relationships between variables {variable-relations}\n\nMany analyses are motivated by a researcher looking for a relationship between two or more variables.\nA social scientist may like to answer some of the following questions:\n\n> Does a higher-than-average increase in county population tend to correspond to counties with higher or lower median household incomes?\n\n> If homeownership in one county is lower than the national average, will the percent of housing units that are in multi-unit structures in that county tend to be above or below the national average?\n\n> How much can the median education level explain the median household income for counties in the US?\n\nTo answer these questions, data must be collected, such as the `county` dataset shown in @tbl-county-df.\nExamining \\index{summary statistic}**summary statistics** can provide numerical insights about the specifics of each of these questions.\nAlternatively, graphs can be used to visually explore the data, potentially providing more insight than a summary statistic.\n\n\\index{scatterplot}**Scatterplots** are one type of graph used to study the relationship between two numerical variables.\n@fig-county-multi-unit-homeownership displays the relationship between the variables `homeownership` and `multi_unit`, which is the percent of housing units that are in multi-unit structures (e.g., apartments, condos).\nEach point on the plot represents a single county.\nFor instance, the highlighted dot corresponds to County 413 in the `county` dataset: Chattahoochee County, Georgia, which has 39.4% of housing units that are in multi-unit structures and a homeownership rate of 31.3%.\nThe scatterplot suggests a relationship between the two variables: counties with a higher rate of housing units that are in multi-unit structures tend to have lower homeownership rates.\nWe might brainstorm as to why this relationship exists and investigate each idea to determine which are the most reasonable explanations.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![A scatterplot of homeownership versus the percent of housing units that are in multi-unit structures for US counties. The highlighted dot represents Chattahoochee County, Georgia, which has a multi-unit rate of 39.4\\% and a homeownership rate of 31.3\\%.](01-data-hello_files/figure-html/fig-county-multi-unit-homeownership-1.png){#fig-county-multi-unit-homeownership width=90%}\n:::\n:::\n\n\nThe multi-unit and homeownership rates are said to be associated because the plot shows a discernible pattern.\nWhen two variables show some connection with one another, they are called **associated** variables.\n\n\n\n\n\n::: {.guidedpractice data-latex=\"\"}\nExamine the variables in the `loan50` dataset, which are described in @tbl-loan-50-variables.\nCreate two questions about possible relationships between variables in `loan50` that are of interest to you.[^01-data-hello-6]\n:::\n\n[^01-data-hello-6]: Two example questions: (1) What is the relationship between loan amount and total income?\n (2) If someone's income is above the average, will their interest rate tend to be above or below the average?\n\n::: {.workedexample data-latex=\"\"}\nThis example examines the relationship between the percent change in population from 2010 to 2017 and median household income for counties, which is visualized as a scatterplot in @fig-county-pop-change-med-hh-income.\nAre these variables associated?\n\n------------------------------------------------------------------------\n\nThe larger the median household income for a county, the higher the population growth observed for the county.\nWhile it isn't true that every county with a higher median household income has a higher population growth, the trend in the plot is evident.\nSince there is some relationship between the variables, they are associated.\n:::\n\n\n::: {.cell}\n::: {.cell-output-display}\n![A scatterplot showing population change against median household income. Owsley County of Kentucky is highlighted, which lost 3.63\\% of its population from 2010 to 2017 and had median household income of \\$22,736.](01-data-hello_files/figure-html/fig-county-pop-change-med-hh-income-1.png){#fig-county-pop-change-med-hh-income width=90%}\n:::\n:::\n\n\nBecause there is a downward trend in @fig-county-multi-unit-homeownership -- counties with more housing units that are in multi-unit structures are associated with lower homeownership -- these variables are said to be **negatively associated**.\nA **positive association** is shown in the relationship between the `median_hh_income` and `pop_change` variables in @fig-county-pop-change-med-hh-income, where counties with higher median household income tend to have higher rates of population growth.\n\n\n\n\n\nIf two variables are not associated, then they are said to be **independent**.\nThat is, two variables are independent if there is no evident relationship between the two.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Associated or independent, not both.**\n\nA pair of variables are either related in some way (associated) or not (independent).\nNo pair of variables is both associated and independent.\n:::\n\n### Explanatory and response variables\n\nWhen we ask questions about the relationship between two variables, we sometimes also want to determine if the change in one variable causes a change in the other.\nConsider the following rephrasing of an earlier question about the `county` dataset:\n\n> If there is an increase in the median household income in a county, does this drive an increase in its population?\n\nIn this question, we are asking whether one variable affects another.\nIf this is our underlying belief, then *median household income* is the **explanatory variable**, and the *population change* is the **response variable** in the hypothesized relationship.[^01-data-hello-7]\n\n[^01-data-hello-7]: In some disciplines, it's customary to refer to the explanatory variable as the **independent variable** and the response variable as the **dependent variable**.\n However, this becomes confusing since a *pair* of variables might be independent or dependent, so we avoid this language.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Explanatory and response variables.**\n\nWhen we suspect one variable might causally affect another, we label the first variable the explanatory variable and the second the response variable.\nWe also use the terms **explanatory** and **response** to describe variables where the **response** might be predicted using the **explanatory** even if there is no causal relationship.\n\n
explanatory variable $\\rightarrow$ *might affect* $\\rightarrow$ response variable
\n\n
For many pairs of variables, there is no hypothesized relationship, and these labels would not be applied to either variable in such cases.\n:::\n\nBear in mind that the act of labeling the variables in this way does nothing to guarantee that a causal relationship exists.\nA formal evaluation to check whether one variable causes a change in another requires an experiment.\n\n### Observational studies and experiments\n\nThere are two primary types of data collection: experiments and observational studies.\n\nWhen researchers want to evaluate the effect of particular traits, treatments, or conditions, they conduct an **experiment**.\nFor instance, we may suspect drinking a high-calorie energy drink will improve performance in a race.\nTo check if there really is a causal relationship between the explanatory variable (whether the runner drank an energy drink or not) and the response variable (the race time), researchers identify a sample of individuals and split them into groups.\nThe individuals in each group are *assigned* a treatment.\nWhen individuals are randomly assigned to a group, the experiment is called a **randomized experiment**.\nRandom assignment organizes the participants in a study into groups that are roughly equal on all aspects, thus allowing us to control for any confounding variables that might affect the outcome (e.g., fitness level, racing experience, etc.).\nFor example, each runner in the experiment could be randomly assigned, perhaps by flipping a coin, into one of two groups: the first group receives a **placebo** (fake treatment, in this case a no-calorie drink) and the second group receives the high-calorie energy drink.\nSee the case study in @sec-case-study-stents-strokes for another example of an experiment, though that study did not employ a placebo.\n\n\n\n\n\nResearchers perform an **observational study** when they collect data in a way that does not directly interfere with how the data arise.\nFor instance, researchers may collect information via surveys, review medical or company records, or follow a **cohort** of many similar individuals to form hypotheses about why certain diseases might develop.\nIn each of these situations, researchers merely observe the data that arise.\nIn general, observational studies can provide evidence of a naturally occurring association between variables, but they cannot by themselves show a causal connection as they do not offer a mechanism for controlling for confounding variables.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Association** $\\neq$ **Causation.**\n\nIn general, association does not imply causation.\nAn advantage of a randomized experiment is that it is easier to establish causal relationships with such a study.\nThe main reason for this is that observational studies do not control for confounding variables, and hence establishing causal relationships with observational studies requires advanced statistical methods (that are beyond the scope of this book).\nWe will revisit this idea when we discuss experiments later in the book.\n:::\n\n\\vspace{10mm}\n\n## Chapter review {chp1-review}\n\n### Summary\n\nThis chapter introduced you to the world of data.\nData can be organized in many ways but tidy data, where each row represents an observation and each column represents a variable, lends itself most easily to statistical analysis.\nMany of the ideas from this chapter will be seen as we move on to doing full data analyses.\nIn the next chapter you're going to learn about how we can design studies to collect the data we need to make conclusions with the desired scope of inference.\n\n### Terms\n\nWe introduced the following terms in the chapter.\nIf you're not sure what some of these terms mean, we recommend you go back in the text and review their definitions.\nWe are purposefully presenting them in alphabetical order, instead of in order of appearance, so they will be a little more challenging to locate.\nHowever, you should be able to easily spot them as **bolded text**.\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
associated experiment ordinal
case explanatory variable placebo
categorical independent positive association
cohort level randomized experiment
continuous negative association response variable
data nominal summary statistic
data frame numerical tidy data
dependent observational study variable
discrete observational unit
\n\n`````\n:::\n:::\n\n\n\\clearpage\n\n## Exercises {chp1-exercises}\n\nAnswers to odd-numbered exercises can be found in [Appendix -@sec-exercise-solutions-01].\n\n::: {.exercises data-latex=\"\"}\n1. **Marvel Cinematic Universe films.** The data frame below contains information on Marvel Cinematic Universe films through the Infinity saga (a movie storyline spanning from Ironman in 2008 to Endgame in 2019).\n Box office totals are given in millions of US Dollars.\n How many observations and how many variables does this data frame have?[^_01-ex-data-hello-1]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Length
Gross
Title Hrs Mins Release Date Opening Wknd US US World
1 Iron Man 2 6 5/2/2008 98.62 319.03 585.8
2 The Incredible Hulk 1 52 6/12/2008 55.41 134.81 264.77
3 Iron Man 2 2 4 5/7/2010 128.12 312.43 623.93
4 Thor 1 55 5/6/2011 65.72 181.03 449.33
5 Captain America: The First Avenger 2 4 7/22/2011 65.06 176.65 370.57
... ... ... ... ... ... ... ...
23 Spiderman: Far from Home 2 9 7/2/2019 92.58 390.53 1131.93
\n \n `````\n :::\n :::\n\n2. **Cherry Blossom Run.** The data frame below contains information on runners in the 2017 Cherry Blossom Run, which is an annual road race that takes place in Washington, DC. Most runners participate in a 10-mile run while a smaller fraction take part in a 5k run or walk.\n How many observations and how many variables does this data frame have?[^_01-ex-data-hello-2]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Time
Bib Name Sex Age City / Country Net Clock Pace Event
1 6 Hiwot G. F 21 Ethiopia 3217 3217 321 10 Mile
2 22 Buze D. F 22 Ethiopia 3232 3232 323 10 Mile
3 16 Gladys K. F 31 Kenya 3276 3276 327 10 Mile
4 4 Mamitu D. F 33 Ethiopia 3285 3285 328 10 Mile
5 20 Karolina N. F 35 Poland 3288 3288 328 10 Mile
... ... ... ... ... ... ... ... ... ...
19961 25153 Andres E. M 33 Woodbridge, VA 5287 5334 1700 5K
\n \n `````\n :::\n :::\n\n3. **Air pollution and birth outcomes, study components.** Researchers collected data to examine the relationship between air pollutants and preterm births in Southern California.\n During the study air pollution levels were measured by air quality monitoring stations.\n Specifically, levels of carbon monoxide were recorded in parts per million, nitrogen dioxide and ozone in parts per hundred million, and coarse particulate matter (PM$_{10}$) in $\\mu g/m^3$.\n Length of gestation data were collected on 143,196 births between the years 1989 and 1993, and air pollution exposure during gestation was calculated for each birth.\n The analysis suggested that increased ambient PM$_{10}$ and, to a lesser degree, CO concentrations may be associated with the occurrence of preterm births.\n [@Ritz+Yu+Chapa+Fruin:2000]\n\n a. Identify the main research question of the study.\n\n b. Who are the subjects in this study, and how many are included?\n\n c. What are the variables in the study?\n Identify each variable as numerical or categorical.\n If numerical, state whether the variable is discrete or continuous.\n If categorical, state whether the variable is ordinal.\n\n4. **Cheaters, study components.** Researchers studying the relationship between honesty, age and self-control conducted an experiment on 160 children between the ages of 5 and 15.\n Participants reported their age, sex, and whether they were an only child or not.\n The researchers asked each child to toss a fair coin in private and to record the outcome (white or black) on a paper sheet and said they would only reward children who report white.\n [@Bucciol:2011]\n\n a. Identify the main research question of the study.\n\n b. Who are the subjects in this study, and how many are included?\n\n c. The study's findings can be summarized as follows: *\"Half the students were explicitly told not to cheat, and the others were not given any explicit instructions. In the no instruction group probability of cheating was found to be uniform across groups based on child's characteristics. In the group that was explicitly told to not cheat, girls were less likely to cheat, and while rate of cheating didn't vary by age for boys, it decreased with age for girls.\"* How many variables were recorded for each subject in the study in order to conclude these findings?\n State the variables and their types.\n\n5. **Gamification and statistics, study components.** Gamification is the application of game-design elements and game principles in non-game contexts.\n In educational settings, gamification is often implemented as educational activities to solve problems by using characteristics of game elements.\n Researchers investigating the effects of gamification on learning statistics conducted a study where they split college students in a statistics class into four groups: (1) no reading exercises and no gamification, (2) reading exercises but no gamification, (3) gamification but no reading exercises, and (4) gamification and reading exercises.\n Students in all groups also attended lectures.\n Students in the class were from two majors: Electrical and Computer Engineering (n = 279) and Business Administration (n = 86).\n After their assigned learning experience, each student took a final evaluation comprised of 30 multiple choice question and their score was measured as the number of questions they answered correctly.\n The researchers considered students' gender, level of studies (first through fourth year) and academic major.\n Other variables considered were expertise in the English language and use of personal computers and games, both of which were measured on a scale of 1 (beginner) to 5 (proficient).\n The study found that gamification had a positive effect on student learning compared to traditional teaching methods involving lectures and reading exercises.\n They also found that the effect was larger for females and Engineering students.\n [@Legaki:2020]\n\n a. Identify the main research question of the study.\n\n b. Who were the subjects in this study, and how many were included?\n\n c. What are the variables in the study?\n Identify each variable as numerical or categorical.\n If numerical, state whether the variable is discrete or continuous.\n If categorical, state whether the variable is ordinal.\n\n6. **Stealers, study components.** In a study of the relationship between socio-economic class and unethical behavior, 129 University of California undergraduates at Berkeley were asked to identify themselves as having low or high social class by comparing themselves to others with the most (least) money, most (least) education, and most (least) respected jobs.\n They were also presented with a jar of individually wrapped candies and informed that the candies were for children in a nearby laboratory, but that they could take some if they wanted.\n After completing some unrelated tasks, participants reported the number of candies they had taken.\n [@Piff:2012]\n\n a. Identify the main research question of the study.\n\n b. Who were the subjects in this study, and how many were included?\n\n c. The study found that students who were identified as upper-class took more candy than others.\n How many variables were recorded for each subject in the study in order to conclude these findings?\n State the variables and their types.\n\n \\clearpage\n\n7. \"Figure **Migraine and acupuncture.** A migraine is a particularly painful type of headache, which patients sometimes wish to treat with acupuncture.\n To determine whether acupuncture relieves migraine pain, researchers conducted a randomized controlled study where 89 individuals who identified as female diagnosed with migraine headaches were randomly assigned to one of two groups: treatment or control.\n Forty-three (43) patients in the treatment group received acupuncture that is specifically designed to treat migraines.\n Forty-six (46) patients in the control group received placebo acupuncture (needle insertion at non-acupoint locations).\n Twenty-four (24) hours after patients received acupuncture, they were asked if they were pain free.\n Results are summarized in the contingency table below.\n Also provided is a figure from the original paper displaying the appropriate area (M) versus the inappropriate area (S) used in the treatment of migraine attacks.\n [^_01-ex-data-hello-3] [@Allais:2011]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Pain free?
Group No Yes
Control 44 2
Treatment 33 10
\n \n `````\n :::\n :::\n\n a. What percent of patients in the treatment group were pain free 24 hours after receiving acupuncture?\n\n b. What percent were pain free in the control group?\n\n c. In which group did a higher percent of patients become pain free 24 hours after receiving acupuncture?\n\n d. Your findings so far might suggest that acupuncture is an effective treatment for migraines for all people who suffer from migraines.\n However, this is not the only possible conclusion.\n What is one other possible explanation for the observed difference between the percentages of patients that are pain free 24 hours after receiving acupuncture in the two groups?\n\n e. What are the explanatory and response variables in this study?\n\n8. **Sinusitis and antibiotics.** Researchers studying the effect of antibiotic treatment for acute sinusitis compared to symptomatic treatments randomly assigned 166 adults diagnosed with acute sinusitis to one of two groups: treatment or control.\n Study participants received either a 10-day course of amoxicillin (an antibiotic) or a placebo similar in appearance and taste.\n The placebo consisted of symptomatic treatments such as acetaminophen, nasal decongestants, etc.\n At the end of the 10-day period, patients were asked if they experienced improvement in symptoms.\n The distribution of responses is summarized below.[^_01-ex-data-hello-4]\n [@Garbutt:2012]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Improvement
Group No Yes
Control 16 65
Treatment 19 66
\n \n `````\n :::\n :::\n\n a. What percent of patients in the treatment group experienced improvement in symptoms?\n\n b. What percent experienced improvement in symptoms in the control group?\n\n c. In which group did a higher percentage of patients experience improvement in symptoms?\n\n d. Your findings so far might suggest a real difference in the effectiveness of antibiotic and placebo treatments for improving symptoms of sinusitis.\n However, this is not the only possible conclusion.\n What is one other possible explanation for the observed difference between the percentages patients who experienced improvement in symptoms?\n\n e. What are the explanatory and response variables in this study?\n\n9. **Daycare fines, study components.** Researchers tested the deterrence hypothesis which predicts that the introduction of a penalty will reduce the occurrence of the behavior subject to the fine, with the condition that the fine leaves everything else unchanged by instituting a fine for late pickup at daycare centers.\n For this study, they worked with 10 volunteer daycare centers that did not originally impose a fine to parents for picking up their kids late.\n They randomly selected 6 of these daycare centers and instituted a monetary fine (of a considerable amount) for picking up children late and then removed it.\n In the remaining 4 daycare centers no fine was introduced.\n The study period was divided into four: before the fine (weeks 1--4), the first 4 weeks with the fine (weeks 5-8), the last 8 weeks with fine (weeks 9--16), and the after fine period (weeks 17-20).\n Throughout the study, the number of kids who were picked up late was recorded each week for each daycare.\n The study found that the number of late-coming parents increased discernibly when the fine was introduced, and no reduction occurred after the fine was removed.[^_01-ex-data-hello-5]\n [@Gneezy:2000]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
center week group late_pickups study_period
1 1 test 8 before fine
1 2 test 8 before fine
1 3 test 7 before fine
1 4 test 6 before fine
1 5 test 8 first 4 weeks with fine
... ... ... ... ...
10 20 control 13 after fine
\n \n `````\n :::\n :::\n\n a. Is this an observational study or an experiment?\n Explain your reasoning.\n\n b. What are the cases in this study and how many are included?\n\n c. What is the response variable in the study and what type of variable is it?\n\n d. What are the explanatory variables in the study and what types of variables are they?\n\n \\vspace{5mm}\n\n10. **Efficacy of COVID-19 vaccine on adolescents, study components.** Results of a Phase 3 trial announced in March 2021 show that the Pfizer-BioNTech COVID-19 vaccine demonstrated 100% efficacy and robust antibody responses on 12 to 15 years old adolescents with or without prior evidence of SARS-CoV-2 infection.\n In this trial 2,260 adolescents were randomly assigned to two groups: one group got the vaccine (n = 1,131) and the other got a placebo (n = 1,129).\n While 18 cases of COVID-19 were observed in the placebo group, none were observed in the vaccine group.[^_01-ex-data-hello-6]\n [@Pfizer:2021]\n\n a. Is this an observational study or an experiment?\n Explain your reasoning.\n\n b. What are the cases in this study and how many are included?\n\n c. What is the response variable in the study and what type of variable is it?\n\n d. What are the explanatory variables in the study and what types of variables are they?\n\n \\clearpage\n\n11. **Palmer penguins.** Data were collected on 344 penguins living on three islands (Torgersen, Biscoe, and Dream) in the Palmer Archipelago, Antarctica.\n In addition to which island each penguin lives on, the data contains information on the species of the penguin (*Adelie*, *Chinstrap*, or *Gentoo*), its bill length, bill depth, and flipper length (measured in millimeters), its body mass (measured in grams), and the sex of the penguin (female or male).[^_01-ex-data-hello-7]\n Bill length and depth are measured as shown in the image.\n [^_01-ex-data-hello-8] [@palmerpenguins]\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](exercises/images/culmen_depth.png){fig-alt='Bill length and depth marked on an illustration of a penguin head.' width=40%}\n :::\n :::\n\n a. How many cases were included in the data?\n b. How many numerical variables are included in the data? Indicate what they are, and if they are continuous or discrete.\n c. How many categorical variables are included in the data, and what are they? List the corresponding levels (categories) for each.\n\n \\vspace{5mm}\n\n12. **Smoking habits of UK residents.** A survey was conducted to study the smoking habits of 1,691 UK residents.\n Below is a data frame displaying a portion of the data collected in this survey.\n A blank cell indicates that data for that variable was not available for a given respondent.[^_01-ex-data-hello-9]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
amount
sex age marital_status gross_income smoke weekend weekday
1 Female 61 Married 2,600 to 5,200 No
2 Female 61 Divorced 10,400 to 15,600 Yes 5 4
3 Female 69 Widowed 5,200 to 10,400 No
4 Female 50 Married 5,200 to 10,400 No
5 Male 31 Single 10,400 to 15,600 Yes 10 20
... ... ... ... ... ...
1691 Male 49 Divorced Above 36,400 Yes 15 10
\n \n `````\n :::\n :::\n\n a. What does each row of the data frame represent?\n\n b. How many participants were included in the survey?\n\n c. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n \\clearpage\n\n13. **US Airports.** The visualization below shows the geographical distribution of airports in the contiguous United States and Washington, DC. This visualization was constructed based on a dataset where each observation is an airport.[^_01-ex-data-hello-10]\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-33-1.png){width=90%}\n :::\n :::\n\n a. List the variables you believe were necessary to create this visualization.\n\n b. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n \\vspace{5mm}\n\n14. **UN Votes.** The visualization below shows voting patterns in the United States, Canada, and Mexico in the United Nations General Assembly on a variety of issues.\n Specifically, for a given year between 1946 and 2019, it displays the percentage of roll calls in which the country voted yes for each issue.\n This visualization was constructed based on a dataset where each observation is a country/year pair.[^_01-ex-data-hello-11]\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-34-1.png){width=90%}\n :::\n :::\n\n a. List the variables used in creating this visualization.\n\n b. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n15. **UK baby names.** The visualization below shows the number of baby girls born in the United Kingdom (comprised of England & Wales, Northern Ireland, and Scotland) who were given the name \"Fiona\" over the years.[^_01-ex-data-hello-12]\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-35-1.png){width=90%}\n :::\n :::\n\n a. List the variables you believe were necessary to create this visualization.\n\n b. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n \\vspace{5mm}\n\n16. **Shows on Netflix.** The visualization below shows the distribution of ratings of TV shows on Netflix (a streaming entertainment service) based on the decade they were released in and the country they were produced in.\n In the dataset, each observation is a TV show.[^_01-ex-data-hello-13]\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-36-1.png){width=90%}\n :::\n :::\n\n a. List the variables you believe were necessary to create this visualization.\n\n b. Indicate whether each variable in the study is numerical or categorical.\n If numerical, identify as continuous or discrete.\n If categorical, indicate if the variable is ordinal.\n\n \\clearpage\n\n17. **Stanford Open Policing.** The Stanford Open Policing project gathers, analyzes, and releases records from traffic stops by law enforcement agencies across the United States.\n Their goal is to help researchers, journalists, and policy makers investigate and improve interactions between police and the public.\n The following is an excerpt from a summary table created based off the data collected as part of this project.\n [@pierson2020large]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
Driver
Car
County State Race / Ethnicity Arrest rate Stops / year Search rate
Apache County AZ Black 0.016 266 0.077
Apache County AZ Hispanic 0.018 1008 0.053
Apache County AZ White 0.006 6322 0.017
Cochise County AZ Black 0.015 1169 0.047
Cochise County AZ Hispanic 0.01 9453 0.037
Cochise County AZ White 0.008 10826 0.024
... ... ... ... ... ...
Wood County WI Black 0.098 16 0.244
Wood County WI Hispanic 0.029 27 0.036
Wood County WI White 0.029 1157 0.033
\n \n `````\n :::\n :::\n\n a. What variables were collected on each individual traffic stop in order to create the summary table above?\n\n b. State whether each variable is numerical or categorical.\n If numerical, state whether it is continuous or discrete.\n If categorical, state whether it is ordinal or not.\n\n c. Suppose we wanted to evaluate whether vehicle search rates are different for drivers of different races.\n In this analysis, which variable would be the response variable and which variable would be the explanatory variable?\n\n \\vspace{5mm}\n\n18. **Space launches.** The following summary table shows the number of space launches in the US by the type of launching agency and the outcome of the launch (success or failure).[^_01-ex-data-hello-14]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
1957 - 1999
2000-2018
Failure Success Failure Success
Private 13 295 10 562
State 281 3751 33 711
Startup 0 0 5 65
\n \n `````\n :::\n :::\n\n a. What variables were collected on each launch in order to create to the summary table above?\n\n b. State whether each variable is numerical or categorical.\n If numerical, state whether it is continuous or discrete.\n If categorical, state whether it is ordinal or not.\n\n c. Suppose we wanted to study how the success rate of launches vary between launching agencies and over time.\n In this analysis, which variable would be the response variable and which variable would be the explanatory variable?\n\n \\clearpage\n\n19. **Pet names.** The city of Seattle, WA has an open data portal that includes pets registered in the city.\n For each registered pet, we have information on the pet's name and species.\n The following visualization plots the proportion of dogs with a given name versus the proportion of cats with the same name.\n The 20 most common cat and dog names are displayed.\n The diagonal line on the plot is the $x = y$ line; if a name appeared on this line, the name's popularity would be exactly the same for dogs and cats.[^_01-ex-data-hello-15]\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](01-data-hello_files/figure-html/unnamed-chunk-39-1.png){width=90%}\n :::\n :::\n\n a. Are these data collected as part of an experiment or an observational study?\n\n b. What is the most common dog name?\n What is the most common cat name?\n\n c. What names are more common for cats than dogs?\n\n d. Is the relationship between the two variables positive or negative?\n What does this mean in context of the data?\n\n \\vspace{5mm}\n\n20. **Stressed out in an elevator.** In a study evaluating the relationship between stress and muscle cramps, half the subjects are randomly assigned to be exposed to increased stress by being placed into an elevator that falls rapidly and stops abruptly and the other half are left at no or baseline stress.\n\n a. What type of study is this?\n\n b. Can this study be used to conclude a causal relationship between increased stress and muscle cramps?\n\n[^_01-ex-data-hello-1]: The [`mcu_films`](http://openintrostat.github.io/openintro/reference/mcu_films.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-2]: The [`run17`](http://openintrostat.github.io/openintro/reference/run17.html) data used in this exercise can be found in the [**cherryblossom**](http://openintrostat.github.io/cherryblossom) R package.\n\n[^_01-ex-data-hello-3]: The [`migraine`](http://openintrostat.github.io/openintro/reference/migraine.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-4]: The [`sinusitis`](http://openintrostat.github.io/openintro/reference/sinusitis.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-5]: The [`daycare_fines`](http://openintrostat.github.io/openintro/reference/daycare_fines.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-6]: The [`biontech_adolescents`](http://openintrostat.github.io/openintro/reference/biontech_adolescents.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-7]: The [`penguins`](https://allisonhorst.github.io/palmerpenguins/reference/penguins.html) data used in this exercise can be found in the [**palmerpenguins**](https://allisonhorst.github.io/palmerpenguins/) R package.\n\n[^_01-ex-data-hello-8]: Artwork by [Allison Horst](https://twitter.com/allison_horst).\n\n[^_01-ex-data-hello-9]: The [`smoking`](http://openintrostat.github.io/openintro/reference/smoking.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_01-ex-data-hello-10]: The [`usairports`](http://openintrostat.github.io/airports/reference/usairports.html) data used in this exercise can be found in the [**airports**](http://openintrostat.github.io/airports/) R package.\n\n[^_01-ex-data-hello-11]: The data used in this exercise can be found in the [**unvotes**](https://cran.r-project.org/web/packages/unvotes/index.html) R package.\n\n[^_01-ex-data-hello-12]: The [`ukbabynames`](https://mine-cetinkaya-rundel.github.io/ukbabynames/reference/ukbabynames.html) data used in this exercise can be found in the [**ukbabynames**](https://mine-cetinkaya-rundel.github.io/ukbabynames/) R package.\n\n[^_01-ex-data-hello-13]: The [`netflix_titles`](https://github.com/rfordatascience/tidytuesday/blob/master/data/2021/2021-04-20/readme.md) data used in this exercise can be found in the [**tidytuesdayR**](https://cran.r-project.org/web/packages/tidytuesdayR/index.html) R package.\n\n[^_01-ex-data-hello-14]: The data used in this exercise comes from the [JSR Launch Vehicle Database, 2019 Feb 10 Edition](https://www.openintro.org/go?id=textbook-space-launches-data&referrer=ims0_html).\n\n[^_01-ex-data-hello-15]: The [`seattlepets`](http://openintrostat.github.io/openintro/reference/seattlepets.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n\n:::\n", "supporting": [ "01-data-hello_files" ], diff --git a/_freeze/11-foundations-randomization/execute-results/html.json b/_freeze/11-foundations-randomization/execute-results/html.json index ba877ef8..830eca9c 100644 --- a/_freeze/11-foundations-randomization/execute-results/html.json +++ b/_freeze/11-foundations-randomization/execute-results/html.json @@ -1,7 +1,8 @@ { - "hash": "5b5610b02848b52c2a44ee65f19d3f4c", + "hash": "2fa89c2b893c4bd92de15405b28fea3f", "result": { - "markdown": "\n\n\n# Hypothesis testing with randomization {#sec-foundations-randomization}\n\n::: {.chapterintro data-latex=\"\"}\nStatistical inference is primarily concerned with understanding and quantifying the uncertainty of parameter estimates.\nWhile the equations and details change depending on the setting, the foundations for inference are the same throughout all of statistics.\n\nWe start with two case studies designed to motivate the process of making decisions about research claims.\nWe formalize the process through the introduction of the **hypothesis testing framework**\\index{hypothesis test}, which allows us to formally evaluate claims about the population.\n:::\n\n\n\n\n\nThroughout the book so far, you have worked with data in a variety of contexts.\nYou have learned how to summarize and visualize the data as well as how to model multiple variables at the same time.\nSometimes the dataset at hand represents the entire research question.\nBut more often than not, the data have been collected to answer a research question about a larger group of which the data are a (hopefully) representative subset.\n\nYou may agree that there is almost always variability in data -- one dataset will not be identical to a second dataset even if they are both collected from the same population using the same methods.\nHowever, quantifying the variability in the data is neither obvious nor easy to do, i.e., answering the question \"*how* different is one dataset from another?\" is not trivial.\n\nFirst, a note on notation.\nWe generally use $p$ to denote a population proportion and $\\hat{p}$ to a sample proportion.\nSimilarly, we generally use $\\mu$ to denote a population mean and $\\bar{x}$ to denote a sample mean.\n\n::: {.workedexample data-latex=\"\"}\nSuppose your professor splits the students in your class into two groups: students who sit on the left side of the classroom and students who sit on the right side of the classroom.\nIf $\\hat{p}_{L}$ represents the proportion of students who prefer to read books on screen who sit on the left side of the classroom and $\\hat{p}_{R}$ represents the proportion of students who prefer to read books on screen who sit on the right side of the classroom, would you be surprised if $\\hat{p}_{L}$ did not *exactly* equal $\\hat{p}_{R}$?\n\n------------------------------------------------------------------------\n\nWhile the proportions $\\hat{p}_{L}$ and $\\hat{p}_{R}$ would probably be close to each other, it would be unusual for them to be exactly the same.\nWe would probably observe a small difference due to *chance*.\n:::\n\n::: {.guidedpractice data-latex=\"\"}\nIf we do not think the side of the room a person sits on in class is related to whether they prefer to read books on screen, what assumption are we making about the relationship between these two variables?[^11-foundations-randomization-1]\n:::\n\n[^11-foundations-randomization-1]: We would be assuming that these two variables are **independent**\\index{independent}.\n\n\n\n\n\nStudying randomness of this form is a key focus of statistics.\nThroughout this chapter, and those that follow, we provide three different approaches for quantifying the variability inherent in data: randomization, bootstrapping, and mathematical models.\nUsing the methods provided in this chapter, we will be able to draw conclusions beyond the dataset at hand to research questions about larger populations that the samples come from.\n\nThe first type of variability we will explore comes from experiments where the explanatory variable (or treatment) is randomly assigned to the observational units.\nAs you learned in Chapter \\@ref(data-hello), a randomized experiment can be used to assess whether one variable (the explanatory variable) causes changes in a second variable (the response variable).\nEvery dataset has some variability in it, so to decide whether the variability in the data is due to (1) the causal mechanism (the randomized explanatory variable in the experiment) or instead (2) natural variability inherent to the data, we set up a sham randomized experiment as a comparison.\nThat is, we assume that each observational unit would have gotten the exact same response value regardless of the treatment level.\nBy reassigning the treatments many many times, we can compare the actual experiment to the sham experiment.\nIf the actual experiment has more extreme results than any of the sham experiments, we are led to believe that it is the explanatory variable which is causing the result and not just variability inherent to the data.\nUsing a few different case studies, let's look more carefully at this idea of a **randomization test**\\index{randomization test}.\n\n\n\n\n\n## Sex discrimination case study {#caseStudySexDiscrimination}\n\nWe consider a study investigating sex discrimination in the 1970s, which is set in the context of personnel decisions within a bank.\nThe research question we hope to answer is, \"Are individuals who identify as female discriminated against in promotion decisions made by their managers who identify as male?\" [@Rosen:1974]\n\n::: {.data data-latex=\"\"}\nThe [`sex_discrimination`](http://openintrostat.github.io/openintro/reference/sex_discrimination.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n:::\n\nThis study considered sex roles, and only allowed for options of \"male\" and \"female\".\nWe should note that the identities being considered are not gender identities and that the study allowed only for a binary classification of sex.\n\n### Observed data\n\nThe participants in this study were 48 bank supervisors who identified as male, attending a management institute at the University of North Carolina in 1972.\nThey were asked to assume the role of the personnel director of a bank and were given a personnel file to judge whether the person should be promoted to a branch manager position.\nThe files given to the participants were identical, except that half of them indicated the candidate identified as male and the other half indicated the candidate identified as female.\nThese files were randomly assigned to the bank managers.\n\n::: {.guidedpractice data-latex=\"\"}\nIs this an observational study or an experiment?\nHow does the type of study impact what can be inferred from the results?[^11-foundations-randomization-2]\n:::\n\n[^11-foundations-randomization-2]: The study is an experiment, as subjects were randomly assigned a \"male\" file or a \"female\" file (remember, all the files were actually identical in content).\n Since this is an experiment, the results can be used to evaluate a causal relationship between the sex of a candidate and the promotion decision.\n\n\n::: {.cell}\n\n:::\n\n\nFor each supervisor both the sex associated with the assigned file and the promotion decision were recorded.\nUsing the results of the study summarized in Table \\@ref(tab:sex-discrimination-obs), we would like to evaluate if individuals who identify as female are unfairly discriminated against in promotion decisions.\nIn this study, a smaller proportion of female identifying applications were promoted than males (0.583 versus 0.875), but it is unclear whether the difference provides *convincing evidence* that individuals who identify as female are unfairly discriminated against.\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Summary results for the sex discrimination study.
decision
sex promoted not promoted Total
male 21 3 24
female 14 10 24
Total 35 13 48
\n\n`````\n:::\n:::\n\n\nThe data are visualized in Figure \\@ref(fig:sex-rand-obs) as a set of cards.\nNote that each card denotes a personnel file (an observation from our dataset) and the colors indicate the decision: red for promoted and white for not promoted.\nAdditionally, the observations are broken up into groups of male and female identifying groups.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![The sex discrimination study can be thought of as 48 red and white cards.](images/sex-rand-01-obs.png){fig-alt='48 cards are laid out; 24 indicating male files, 24 indicated female files. Of the 24 male files 3 of the cards are colored white, and 21 of the cards are colored red. Of the female files, 10 of the cards are colored white, and 14 of the cards are colored red.' width=40%}\n:::\n:::\n\n\n::: {.workedexample data-latex=\"\"}\nStatisticians are sometimes called upon to evaluate the strength of evidence.\nWhen looking at the rates of promotion in this study, why might we be tempted to immediately conclude that individuals identifying as female are being discriminated against?\n\n------------------------------------------------------------------------\n\nThe large difference in promotion rates (58.3% for female personnel versus 87.5% for male personnel) suggest there might be discrimination against women in promotion decisions.\nHowever, we cannot yet be sure if the observed difference represents discrimination or is just due to random chance when there is no discrimination occurring.\nSince we wouldn't expect the sample proportions to be *exactly* equal, even if the truth was that the promotion decisions were independent of sex, we can't rule out random chance as a possible explanation when simply comparing the sample proportions.\n:::\n\nThe previous example is a reminder that the observed outcomes in the sample may not perfectly reflect the true relationships between variables in the underlying population.\nTable \\@ref(tab:sex-discrimination-obs) shows there were 7 fewer promotions for female identifying personnel than for the male personnel, a difference in promotion rates of 29.2% $\\left( \\frac{21}{24} - \\frac{14}{24} = 0.292 \\right).$ This observed difference is what we call a **point estimate**\\index{point estimate} of the true difference.\nThe point estimate of the difference in promotion rate is large, but the sample size for the study is small, making it unclear if this observed difference represents discrimination or whether it is simply due to chance when there is no discrimination occurring.\nChance can be thought of as the claim due to natural variability; discrimination can be thought of as the claim the researchers set out to demonstrate.\nWe label these two competing claims, $H_0$ and $H_A:$\n\n\n\n\n\n\\vspace{-2mm}\n\n- $H_0:$ **Null hypothesis**\\index{null hypothesis}. The variables `sex` and `decision` are independent. They have no relationship, and the observed difference between the proportion of males and females who were promoted, 29.2%, was due to the natural variability inherent in the population.\n- $H_A:$ **Alternative hypothesis**\\index{alternative hypothesis}. The variables `sex` and `decision` are *not* independent. The difference in promotion rates of 29.2% was not due to natural variability, and equally qualified female personnel are less likely to be promoted than male personnel.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Hypothesis testing.**\n\nThese hypotheses are part of what is called a **hypothesis test**\\index{hypothesis test}.\nA hypothesis test is a statistical technique used to evaluate competing claims using data.\nOften times, the null hypothesis takes a stance of *no difference* or *no effect*.\nThis hypothesis assumes that any differences seen are due to the variability inherent in the population and could have occurred by random chance.\n\nIf the null hypothesis and the data notably disagree, then we will reject the null hypothesis in favor of the alternative hypothesis.\n\nThere are many nuances to hypothesis testing, so do not worry if you aren't a master of hypothesis testing at the end of this section.\nWe'll discuss these ideas and details many times in this chapter as well as in the chapters that follow.\n:::\n\n\n\n\n\nWhat would it mean if the null hypothesis, which says the variables `sex` and `decision` are unrelated, was true?\nIt would mean each banker would decide whether to promote the candidate without regard to the sex indicated on the personnel file.\nThat is, the difference in the promotion percentages would be due to the natural variability in how the files were randomly allocated to different bankers, and this randomization just happened to give rise to a relatively large difference of 29.2%.\n\nConsider the alternative hypothesis: bankers were influenced by which sex was listed on the personnel file.\nIf this was true, and especially if this influence was substantial, we would expect to see some difference in the promotion rates of male and female candidates.\nIf this sex bias was against female candidates, we would expect a smaller fraction of promotion recommendations for female personnel relative to the male personnel.\n\nWe will choose between the two competing claims by assessing if the data conflict so much with $H_0$ that the null hypothesis cannot be deemed reasonable.\nIf data and the null claim seem to be at odds with one another, and the data seem to support $H_A,$ then we will reject the notion of independence and conclude that the data provide evidence of discrimination.\n\n\\vspace{-2mm}\n\n### Variability of the statistic\n\nTable \\@ref(tab:sex-discrimination-obs) shows that 35 bank supervisors recommended promotion and 13 did not.\nNow, suppose the bankers' decisions were independent of the sex of the candidate.\nThen, if we conducted the experiment again with a different random assignment of sex to the files, differences in promotion rates would be based only on random fluctuation in promotion decisions.\nWe can actually perform this **randomization**, which simulates what would have happened if the bankers' decisions had been independent of `sex` but we had distributed the file sexes differently.[^11-foundations-randomization-3]\n\n[^11-foundations-randomization-3]: The test procedure we employ in this section is sometimes referred to as a **randomization test**.\n If the explanatory variable had not been randomly assigned, as in an observational study, the procedure would be referred to as a **permutation test**.\n Permutation tests are used for observational studies, where the explanatory variable was not randomly assigned.\\index{permutation test}.\n\n\n\n\n\nIn the **simulation**\\index{simulation}, we thoroughly shuffle the 48 personnel files, 35 labelled `promoted` and 13 labelled `not promoted`, together and we deal files into two new stacks.\nNote that by keeping 35 promoted and 13 not promoted, we are assuming that 35 of the bank managers would have promoted the individual whose content is contained in the file **independent** of the sex indicated on their file.\nWe will deal 24 files into the first stack, which will represent the 24 \"female\" files.\nThe second stack will also have 24 files, and it will represent the 24 \"male\" files.\nFigure \\@ref(fig:sex-rand-shuffle-1) highlights both the shuffle and the reallocation to the sham sex groups.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![The sex discrimination data is shuffled and reallocated to new groups of male and female files.](images/sex-rand-02-shuffle-1.png){fig-alt='The 48 red and white cards which denote the original data are shuffled and reassigned, 24 to each group indicating 24 male files and 24 female files.' width=80%}\n:::\n:::\n\n\nThen, as we did with the original data, we tabulate the results and determine the fraction of personnel files designated as \"male\" and \"female\" who were promoted.\n\n\n\n\n\nSince the randomization of files in this simulation is independent of the promotion decisions, any difference in promotion rates is due to chance.\nTable \\@ref(tab:sex-discrimination-rand-1) show the results of one such simulation.\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Simulation results, where the difference in promotion rates between male and female is purely due to random chance.
decision
sex promoted not promoted Total
male 18 6 24
female 17 7 24
Total 35 13 48
\n\n`````\n:::\n:::\n\n\n::: {.guidedpractice data-latex=\"\"}\nWhat is the difference in promotion rates between the two simulated groups in Table \\@ref(tab:sex-discrimination-rand-1) ?\nHow does this compare to the observed difference 29.2% from the actual study?[^11-foundations-randomization-4]\n:::\n\n[^11-foundations-randomization-4]: $18/24 - 17/24=0.042$ or about 4.2% in favor of the male personnel.\n This difference due to chance is much smaller than the difference observed in the actual groups.\n\nFigure \\@ref(fig:sex-rand-shuffle-1-sort) shows that the difference in promotion rates is much larger in the original data than it is in the simulated groups (0.292 \\> 0.042).\nThe quantity of interest throughout this case study has been the difference in promotion rates.\nWe call the summary value the **statistic** of interest (or often the **test statistic**).\nWhen we encounter different data structures, the statistic is likely to change (e.g., we might calculate an average instead of a proportion), but we will always want to understand how the statistic varies from sample to sample.\n\n\n\n\n::: {.cell}\n::: {.cell-output-display}\n![We summarize the randomized data to produce one estimate of the difference in proportions given no sex discrimination. Note that the sort step is only used to make it easier to visually calculate the simulated sample proportions.](images/sex-rand-03-shuffle-1-sort.png){fig-alt='The 48 red and white cards are show in three panels. The first panel represents the original data and original allocation of the male and female files (in the original data there are 3 white cards in the male group and 10 white cards in the female group). The second panel represents the shuffled red and white cards that are randomly assigned as male and female files. The third panel has the cards sorted according to the random assignment of female or male. In the third panel there are 6 white cards in the male group and 7 white cards in the female group.' width=100%}\n:::\n:::\n\n\n### Observed statistic vs. null statistics\n\nWe computed one possible difference under the null hypothesis in Guided Practice, which represents one difference due to chance when the null hypothesis is assumed to be true.\nWhile in this first simulation, we physically dealt out files, it is much more efficient to perform this simulation using a computer.\nRepeating the simulation on a computer, we get another difference due to chance under the same assumption: -0.042.\nAnd another: 0.208.\nAnd so on until we repeat the simulation enough times that we have a good idea of the shape of the *distribution of differences* under the null hypothesis.\nFigure \\@ref(fig:sex-rand-dot-plot) shows a plot of the differences found from 100 simulations, where each dot represents a simulated difference between the proportions of male and female files recommended for promotion.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![(ref:sex-rand-dot-plot-cap)](11-foundations-randomization_files/figure-html/sex-rand-dot-plot-1.png){width=100%}\n:::\n:::\n\n\n(ref:sex-rand-dot-plot-cap) A stacked dot plot of differences from 100 simulations produced under the null hypothesis, $H_0,$ where the simulated sex and decision are independent. Two of the 100 simulations had a difference of at least 29.2%, the difference observed in the study, and are shown as solid blue dots.\n\nNote that the distribution of these simulated differences in proportions is centered around 0.\nUnder the null hypothesis our simulations made no distinction between male and female personnel files.\nThus, a center of 0 makes sense: we should expect differences from chance alone to fall around zero with some random fluctuation for each simulation.\n\n::: {.workedexample data-latex=\"\"}\nHow often would you observe a difference of at least 29.2% (0.292) according to Figure \\@ref(fig:sex-rand-dot-plot)?\nOften, sometimes, rarely, or never?\n\n------------------------------------------------------------------------\n\nIt appears that a difference of at least 29.2% under the null hypothesis would only happen about 2% of the time according to Figure \\@ref(fig:sex-rand-dot-plot).\nSuch a low probability indicates that observing such a large difference from chance alone is rare.\n:::\n\nThe difference of 29.2% is a rare event if there really is no impact from listing sex in the candidates' files, which provides us with two possible interpretations of the study results:\n\n- If $H_0,$ the **Null hypothesis** is true: Sex has no effect on promotion decision, and we observed a difference that is so large that it would only happen rarely.\n\n- If $H_A,$ the **Alternative hypothesis** is true: Sex has an effect on promotion decision, and what we observed was actually due to equally qualified female candidates being discriminated against in promotion decisions, which explains the large difference of 29.2%.\n\nWhen we conduct formal studies, we reject a null position (the idea that the data are a result of chance only) if the data strongly conflict with that null position.[^11-foundations-randomization-5]\nIn our analysis, we determined that there was only a $\\approx$ 2% probability of obtaining a sample where $\\geq$ 29.2% more male candidates than female candidates get promoted under the null hypothesis, so we conclude that the data provide strong evidence of sex discrimination against female candidates by the male supervisors.\nIn this case, we reject the null hypothesis in favor of the alternative.\n\n[^11-foundations-randomization-5]: This reasoning does not generally extend to anecdotal observations.\n Each of us observes incredibly rare events every day, events we could not possibly hope to predict.\n However, in the non-rigorous setting of anecdotal evidence, almost anything may appear to be a rare event, so the idea of looking for rare events in day-to-day activities is treacherous.\n For example, we might look at the lottery: there was only a 1 in 176 million chance that the Mega Millions numbers for the largest jackpot in history (October 23, 2018) would be (5, 28, 62, 65, 70) with a Mega ball of (5), but nonetheless those numbers came up!\n However, no matter what numbers had turned up, they would have had the same incredibly rare odds.\n That is, *any set of numbers we could have observed would ultimately be incredibly rare*.\n This type of situation is typical of our daily lives: each possible event in itself seems incredibly rare, but if we consider every alternative, those outcomes are also incredibly rare.\n We should be cautious not to misinterpret such anecdotal evidence.\n\n**Statistical inference** is the practice of making decisions and conclusions from data in the context of uncertainty.\nErrors do occur, just like rare events, and the dataset at hand might lead us to the wrong conclusion.\nWhile a given dataset may not always lead us to a correct conclusion, statistical inference gives us tools to control and evaluate how often these errors occur.\nBefore getting into the nuances of hypothesis testing, let's work through another case study.\n\n\n\n\n\n## Opportunity cost case study {#caseStudyOpportunityCost}\n\nHow rational and consistent is the behavior of the typical American college student?\nIn this section, we'll explore whether college student consumers always consider the following: money not spent now can be spent later.\n\nIn particular, we are interested in whether reminding students about this well-known fact about money causes them to be a little thriftier.\nA skeptic might think that such a reminder would have no impact.\nWe can summarize the two different perspectives using the null and alternative hypothesis framework.\n\n- $H_0:$ **Null hypothesis**. Reminding students that they can save money for later purchases will not have any impact on students' spending decisions.\n- $H_A:$ **Alternative hypothesis**. Reminding students that they can save money for later purchases will reduce the chance they will continue with a purchase.\n\nIn this section, we'll explore an experiment conducted by researchers that investigates this very question for students at a university in the southwestern United States.\n[@Frederick:2009]\n\n### Observed data\n\nOne-hundred and fifty students were recruited for the study, and each was given the following statement:\n\n> *Imagine that you have been saving some extra money on the side to make some purchases, and on your most recent visit to the video store you come across a special sale on a new video. This video is one with your favorite actor or actress, and your favorite type of movie (such as a comedy, drama, thriller, etc.). This particular video that you are considering is one you have been thinking about buying for a long time. It is available for a special sale price of \\$14.99. What would you do in this situation? Please circle one of the options below.*[^11-foundations-randomization-6]\n\n[^11-foundations-randomization-6]: This context might feel strange if physical video stores predate you.\n If you're curious about what those were like, look up \"Blockbuster\".\n\nHalf of the 150 students were randomized into a control group and were given the following two options:\n\n> (A) Buy this entertaining video.\n\n> (B) Not buy this entertaining video.\n\nThe remaining 75 students were placed in the treatment group, and they saw a slightly modified option (B):\n\n> (A) Buy this entertaining video.\n\n> (B) Not buy this entertaining video. Keep the \\$14.99 for other purchases.\n\nWould the extra statement reminding students of an obvious fact impact the purchasing decision?\nTable \\@ref(tab:opportunity-cost-obs) summarizes the study results.\n\n::: {.data data-latex=\"\"}\nThe [`opportunity_cost`](http://openintrostat.github.io/openintro/reference/opportunity_cost.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n:::\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Summary results of the opportunity cost study.
decision
group buy video not buy video Total
control 56 19 75
treatment 41 34 75
Total 97 53 150
\n\n`````\n:::\n:::\n\n\nIt might be a little easier to review the results using a visualization.\nFigure \\@ref(fig:opportunity-cost-obs-bar) shows that a higher proportion of students in the treatment group chose not to buy the video compared to those in the control group.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![Stacked bar plot of results of the opportunity cost study.](11-foundations-randomization_files/figure-html/opportunity-cost-obs-bar-1.png){width=100%}\n:::\n:::\n\n\nAnother useful way to review the results from Table \\@ref(tab:opportunity-cost-obs) is using row proportions, specifically considering the proportion of participants in each group who said they would buy or not buy the video.\nThese summaries are given in Table \\@ref(tab:opportunity-cost-obs-row-prop).\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n\n
The opportunity cost data are summarized using row proportions. Row proportions are particularly useful here since we can view the proportion of *buy* and *not buy* decisions in each group.
decision
group buy video not buy video Total
control 0.747 0.253 1
treatment 0.547 0.453 1
\n\n`````\n:::\n:::\n\n\nWe will define a **success**\\index{success} in this study as a student who chooses not to buy the video.[^11-foundations-randomization-7]\nThen, the value of interest is the change in video purchase rates that results by reminding students that not spending money now means they can spend the money later.\n\n[^11-foundations-randomization-7]: Success is often defined in a study as the outcome of interest, and a \"success\" may or may not actually be a positive outcome.\n For example, researchers working on a study on COVID prevalence might define a \"success\" in the statistical sense as a patient who has COVID-19.\n A more complete discussion of the term **success** will be given in Chapter \\@ref(inference-one-prop).\n\n\n\n\n\nWe can construct a point estimate for this difference as ($T$ for treatment and $C$ for control):\n\n$$\\hat{p}_{T} - \\hat{p}_{C} = \\frac{34}{75} - \\frac{19}{75} = 0.453 - 0.253 = 0.200$$\n\nThe proportion of students who chose not to buy the video was 20 percentage points higher in the treatment group than the control group.\nIs this 20% difference between the two groups so prominent that it is unlikely to have occurred from chance alone, if there is no difference between the spending habits of the two groups?\n\n### Variability of the statistic\n\nThe primary goal in this data analysis is to understand what sort of differences we might see if the null hypothesis were true, i.e., the treatment had no effect on students.\nBecause this is an experiment, we'll use the same procedure we applied in Section \\@ref(caseStudySexDiscrimination): randomization.\n\nLet's think about the data in the context of the hypotheses.\nIf the null hypothesis $(H_0)$ was true and the treatment had no impact on student decisions, then the observed difference between the two groups of 20% could be attributed entirely to random chance.\nIf, on the other hand, the alternative hypothesis $(H_A)$ is true, then the difference indicates that reminding students about saving for later purchases actually impacts their buying decisions.\n\n### Observed statistic vs. null statistics\n\nJust like with the sex discrimination study, we can perform a statistical analysis.\nUsing the same randomization technique from the last section, let's see what happens when we simulate the experiment under the scenario where there is no effect from the treatment.\n\nWhile we would in reality do this simulation on a computer, it might be useful to think about how we would go about carrying out the simulation without a computer.\nWe start with 150 index cards and label each card to indicate the distribution of our response variable: `decision`.\nThat is, 53 cards will be labeled \"not buy video\" to represent the 53 students who opted not to buy, and 97 will be labeled \"buy video\" for the other 97 students.\nThen we shuffle these cards thoroughly and divide them into two stacks of size 75, representing the simulated treatment and control groups.\nBecause we have shuffled the cards from both groups together, assuming no difference in their purchasing behavior, any observed difference between the proportions of \"not buy video\" cards (what we earlier defined as *success*) can be attributed entirely to chance.\n\n::: {.workedexample data-latex=\"\"}\nIf we are randomly assigning the cards into the simulated treatment and control groups, how many \"not buy video\" cards would we expect to end up in each simulated group?\nWhat would be the expected difference between the proportions of \"not buy video\" cards in each group?\n\n------------------------------------------------------------------------\n\nSince the simulated groups are of equal size, we would expect $53 / 2 = 26.5,$ i.e., 26 or 27, \"not buy video\" cards in each simulated group, yielding a simulated point estimate of the difference in proportions of 0% .\nHowever, due to random chance, we might also expect to sometimes observe a number a little above or below 26 and 27.\n:::\n\nThe results of a single randomization is shown in Table \\@ref(tab:opportunity-cost-obs-simulated).\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Summary of student choices against their simulated groups. The group assignment had no connection to the student decisions, so any difference between the two groups is due to chance.
decision
group buy video not buy video Total
control 46 29 75
treatment 51 24 75
Total 97 53 150
\n\n`````\n:::\n:::\n\n\nFrom this table, we can compute a difference that occurred from the first shuffle of the data (i.e., from chance alone):\n\n$$\\hat{p}_{T, shfl1} - \\hat{p}_{C, shfl1} = \\frac{24}{75} - \\frac{29}{75} = 0.32 - 0.387 = - 0.067$$\n\nJust one simulation will not be enough to get a sense of what sorts of differences would happen from chance alone.\n\n\n::: {.cell}\n\n:::\n\n\nWe'll simulate another set of simulated groups and compute the new difference: 0.04.\n\nAnd again: 0.12.\n\nAnd again: -0.013.\n\nWe'll do this 1,000 times.\n\nThe results are summarized in a dot plot in Figure \\@ref(fig:opportunity-cost-rand-dot-plot), where each point represents the difference from one randomization.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![(ref:opportunity-cost-rand-dot-plot-cap)](11-foundations-randomization_files/figure-html/opportunity-cost-rand-dot-plot-1.png){width=90%}\n:::\n:::\n\n\n(ref:opportunity-cost-rand-dot-plot-cap) A stacked dot plot of 1,000 simulated (null) differences produced under the null hypothesis, $H_0.$ Six of the 1,000 simulations had a difference of at least 20% , which was the difference observed in the study.\n\nSince there are so many points and it is difficult to discern one point from the other, it is more convenient to summarize the results in a histogram such as the one in Figure \\@ref(fig:opportunity-cost-rand-hist), where the height of each histogram bar represents the number of simulations resulting in an outcome of that magnitude.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![A histogram of 1,000 chance differences produced under the null hypothesis. Histograms like this one are a convenient representation of data or results when there are a large number of simulations.](11-foundations-randomization_files/figure-html/opportunity-cost-rand-hist-1.png){width=90%}\n:::\n:::\n\n\nUnder the null hypothesis (no treatment effect), we would observe a difference of at least +20% about 0.6% of the time.\nThat is really rare!\nInstead, we will conclude the data provide strong evidence there is a treatment effect: reminding students before a purchase that they could instead spend the money later on something else lowers the chance that they will continue with the purchase.\nNotice that we are able to make a causal statement for this study since the study is an experiment, although we do not know why the reminder induces a lower purchase rate.\n\n## Hypothesis testing {#HypothesisTesting}\n\nIn the last two sections, we utilized a **hypothesis test**\\index{hypothesis test}, which is a formal technique for evaluating two competing possibilities.\nIn each scenario, we described a **null hypothesis**\\index{null hypothesis}, which represented either a skeptical perspective or a perspective of no difference.\nWe also laid out an **alternative hypothesis**\\index{alternative hypothesis}, which represented a new perspective such as the possibility of a relationship between two variables or a treatment effect in an experiment.\nThe alternative hypothesis is usually the reason the scientists set out to do the research in the first place.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Null and alternative hypotheses.**\n\nThe **null hypothesis** $(H_0)$ often represents either a skeptical perspective or a claim of \"no difference\" to be tested.\n\nThe **alternative hypothesis** $(H_A)$ represents an alternative claim under consideration and is often represented by a range of possible values for the value of interest.\n:::\n\nIf a person makes a somewhat unbelievable claim, we are initially skeptical.\nHowever, if there is sufficient evidence that supports the claim, we set aside our skepticism.\nThe hallmarks of hypothesis testing are also found in the US court system.\n\n### The US court system\n\nIn the US course system, jurors evaluate the evidence to see whether it convincingly shows a defendant is guilty.\nDefendants are considered to be innocent until proven otherwise.\n\n::: {.workedexample data-latex=\"\"}\nThe US court considers two possible claims about a defendant: they are either innocent or guilty.\n\nIf we set these claims up in a hypothesis framework, which would be the null hypothesis and which the alternative?\n\n------------------------------------------------------------------------\n\nThe jury considers whether the evidence is so convincing (strong) that there is no reasonable doubt regarding the person's guilt.\nThat is, the skeptical perspective (null hypothesis) is that the person is innocent until evidence is presented that convinces the jury that the person is guilty (alternative hypothesis).\n:::\n\nJurors examine the evidence to see whether it convincingly shows a defendant is guilty.\nNotice that if a jury finds a defendant *not guilty*, this does not necessarily mean the jury is confident in the person's innocence.\nThey are simply not convinced of the alternative, that the person is guilty.\nThis is also the case with hypothesis testing: *even if we fail to reject the null hypothesis, we do not accept the null hypothesis as truth*.\n\nFailing to find evidence in favor of the alternative hypothesis is not equivalent to finding evidence that the null hypothesis is true.\nWe will see this idea in greater detail in Section \\@ref(decerr).\n\n### p-value and statistical discernibility\n\nIn Section \\@ref(caseStudySexDiscrimination) we encountered a study from the 1970's that explored whether there was strong evidence that female candidates were less likely to be promoted than male candidates.\nThe research question -- are female candidates discriminated against in promotion decisions?\n-- was framed in the context of hypotheses:\n\n- $H_0:$ Sex has no effect on promotion decisions.\n\n- $H_A:$ Female candidates are discriminated against in promotion decisions.\n\nThe null hypothesis $(H_0)$ was a perspective of no difference in promotion.\nThe data on sex discrimination provided a point estimate of a 29.2% difference in recommended promotion rates between male and female candidates.\nWe determined that such a difference from chance alone, assuming the null hypothesis was true, would be rare: it would only happen about 2 in 100 times.\nWhen results like these are inconsistent with $H_0,$ we reject $H_0$ in favor of $H_A.$ Here, we concluded there was discrimination against female candidates.\n\nThe 2-in-100 chance is what we call a **p-value**, which is a probability quantifying the strength of the evidence against the null hypothesis, given the observed data.\n\n::: {.important data-latex=\"\"}\n**p-value.**\n\nThe **p-value**\\index{hypothesis testing!p-value} is the probability of observing data at least as favorable to the alternative hypothesis as our current dataset, if the null hypothesis were true.\nWe typically use a summary statistic of the data, such as a difference in proportions, to help compute the p-value and evaluate the hypotheses.\nThis summary value that is used to compute the p-value is often called the **test statistic**\\index{test statistic}.\n:::\n\n\n\n\n\n::: {.workedexample data-latex=\"\"}\nIn the sex discrimination study, the difference in discrimination rates was our test statistic.\nWhat was the test statistic in the opportunity cost study covered in Section \\@ref(caseStudyOpportunityCost)?\n\n------------------------------------------------------------------------\n\nThe test statistic in the opportunity cost study was the difference in the proportion of students who decided against the video purchase in the treatment and control groups.\nIn each of these examples, the **point estimate** of the difference in proportions was used as the test statistic.\n:::\n\nWhen the p-value is small, i.e., less than a previously set threshold, we say the results are **statistically discernible**\\index{statistically significant}\\index{statistically discernible}.\nThis means the data provide such strong evidence against $H_0$ that we reject the null hypothesis in favor of the alternative hypothesis.[^11-foundations-randomization-8]\nThe threshold is called the **discernibility level**\\index{hypothesis testing!discernibility level}\\index{significance level}\\index{discernibility level} and often represented by $\\alpha$ (the Greek letter *alpha*).\n[^11-foundations-randomization-9] The value of $\\alpha$ represents how rare an event needs to be in order for the null hypothesis to be rejected\n. Historically, many fields have set $\\alpha = 0.05,$ meaning that the results need to occur less than 5% of the time, if the null hypothesis is to be rejected\n. The value of $\\alpha$ can vary depending on the the field or the application\n.\n\n[^11-foundations-randomization-8]: Many texts use the phrase \"statistically significant\" instead of \"statistically discernible\".\n We have chosen to use \"discernible\" to indicate that a precise statistical event has happened, as opposed to a notable effect which may or may not fit the statistical definition of discernible or significant.\n\n[^11-foundations-randomization-9]: Here, too, we have chosen \"discernibility level\" instead of \"significance level\" which you will see in some texts.\n\n\n\n\n\nNote that you may have heard the phrase \"statistically significant\" as a way to describe \"statistically discernible.\" Although in everyday language \"significant\" would indicate that a difference is large or meaningful, that is not necessarily the case here.\nThe term \"statistically discernible\" indicates that the p-value from a study fell below the chosen discernibility level.\nFor example, in the sex discrimination study, the p-value was found to be approximately 0.02.\nUsing a discernibility level of $\\alpha = 0.05,$ we would say that the data provided statistically discernible evidence against the null hypothesis.\nHowever, this conclusion gives us no information regarding the size of the difference in promotion rates!\n\n::: {.important data-latex=\"\"}\n**Statistical discernibility.**\n\nWe say that the data provide **statistically discernible**\\index{hypothesis testing!statistically discernible.} evidence against the null hypothesis if the p-value is less than some predetermined threshold (e.g., 0.01, 0.05, 0.1).\n:::\n\n::: {.workedexample data-latex=\"\"}\nIn the opportunity cost study in Section \\@ref(caseStudyOpportunityCost), we analyzed an experiment where study participants had a 20% drop in likelihood of continuing with a video purchase if they were reminded that the money, if not spent on the video, could be used for other purchases in the future.\nWe determined that such a large difference would only occur 6-in-1,000 times if the reminder actually had no influence on student decision-making.\nWhat is the p-value in this study?\nWould you classify the result as \"statistically discernible\"?\n\n------------------------------------------------------------------------\n\nThe p-value was 0.006.\nSince the p-value is less than 0.05, the data provide statistically discernible evidence that US college students were actually influenced by the reminder.\n:::\n\n::: {.important data-latex=\"\"}\n**What's so special about 0.05?**\n\nWe often use a threshold of 0.05 to determine whether a result is statistically discernible.\nBut why 0.05?\nMaybe we should use a bigger number, or maybe a smaller number.\nIf you're a little puzzled, that probably means you're reading with a critical eye -- good job!\nWe've made a video to help clarify *why 0.05*:\n\n\n\nSometimes it's also a good idea to deviate from the standard.\nWe'll discuss when to choose a threshold different than 0.05 in Section \\@ref(decerr).\n:::\n\n\\clearpage\n\n## Chapter review {#chp11-review}\n\n### Summary\n\nFigure \\@ref(fig:fullrand) provides a visual summary of the randomization testing procedure.\n\n\\index{randomization test}\n\n\n\n\n::: {.cell}\n::: {.cell-output-display}\n![An example of one simulation of the full randomization procedure from a hypothetical dataset as visualized in the first panel. We repeat the steps hundreds or thousands of times.](images/fullrand.png){fig-alt='48 red and white cards are show in three panels. The first panel represents original data and original allocation of Group 1 and Group 2 (in the original data there are 7 white cards in Group 1 and 10 white cards in Group 2). The second panel represents the shuffled red and white cards that are randomly assigned as Group 1 and Group 2. The third panel has the cards sorted according to the random assignment of Group 1 and Group 2. In the third panel there are 8 white cards in the Group 1 and 9 white cards in Group 2.' width=100%}\n:::\n:::\n\n\nWe can summarize the randomization test procedure as follows:\n\n- **Frame the research question in terms of hypotheses.** Hypothesis tests are appropriate for research questions that can be summarized in two competing hypotheses. The null hypothesis $(H_0)$ usually represents a skeptical perspective or a perspective of no relationship between the variables. The alternative hypothesis $(H_A)$ usually represents a new view or the existance of a relationship between the variables.\n- **Collect data with an observational study or experiment.** If a research question can be formed into two hypotheses, we can collect data to run a hypothesis test. If the research question focuses on associations between variables but does not concern causation, we would use an observational study. If the research question seeks a causal connection between two or more variables, then an experiment should be used.\n- **Model the randomness that would occur if the null hypothesis was true.** In the examples above, the variability has been modeled as if the treatment (e.g., sexual identity, opportunity) allocation was independent of the outcome of the study. The computer generated null distribution is the result of many different randomizations and quantifies the variability that would be expected if the null hypothesis was true.\n- **Analyze the data.** Choose an analysis technique appropriate for the data and identify the p-value. So far, we have only seen one analysis technique: randomization. Throughout the rest of this textbook, we'll encounter several new methods suitable for many other contexts.\n- **Form a conclusion.** Using the p-value from the analysis, determine whether the data provide evidence against the null hypothesis. Also, be sure to write the conclusion in plain language so casual readers can understand the results.\n\nTable \\@ref(tab:chp11-summary) is another look at the randomization test summary.\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Summary of randomization as an inferential statistical method.
Question Answer
What does it do? Shuffles the explanatory variable to mimic the natural variability found in a randomized experiment
What is the random process described? Randomized experiment
What other random processes can be approximated? Can also be used to describe random sampling in an observational model
What is it best for? Hypothesis testing (can also be used for confidence intervals, but not covered in this text).
What physical object represents the simulation process? Shuffling cards
\n\n`````\n:::\n:::\n\n\n### Terms\n\nWe introduced the following terms in the chapter.\nIf you're not sure what some of these terms mean, we recommend you go back in the text and review their definitions.\nWe are purposefully presenting them in alphabetical order, instead of in order of appearance, so they will be a little more challenging to locate.\nHowever, you should be able to easily spot them as **bolded text**.\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
alternative hypothesis p-value statistic
confidence interval permutation test statistical inference
discernibility level point estimate statistically discernible
hypothesis test randomization test statistically significant
independent significance level success
null hypothesis simulation test statistic
\n\n`````\n:::\n:::\n\n\n\\clearpage\n\n## Exercises {#chp11-exercises}\n\nAnswers to odd-numbered exercises can be found in [Appendix -@sec-exercise-solutions-11].\n\n::: {.exercises data-latex=\"\"}\n1. **Identify the parameter, I**\nFor each of the following situations, state whether the parameter of interest is a mean or a proportion. It may be helpful to examine whether individual responses are numerical or categorical.\n\n a. In a survey, one hundred college students are asked how many hours per week they spend on the Internet.\n\n b. In a survey, one hundred college students are asked: \"What percentage of the time you spend on the Internet is part of your course work?\"\n\n c. In a survey, one hundred college students are asked whether they cited information from Wikipedia in their papers.\n\n d. In a survey, one hundred college students are asked what percentage of their total weekly spending is on alcoholic beverages.\n\n e. In a sample of one hundred recent college graduates, it is found that 85 percent expect to get a job within one year of their graduation date.\n\n1. **Identify the parameter, II.**\nFor each of the following situations, state whether the parameter of interest is a mean or a proportion.\n\n a. A poll shows that 64% of Americans personally worry a great deal about federal spending and the budget deficit.\n\n b. A survey reports that local TV news has shown a 17% increase in revenue within a two year period while newspaper revenues decreased by 6.4% during this time period.\n\n c. In a survey, high school and college students are asked whether they use geolocation services on their smart phones.\n\n d. In a survey, smart phone users are asked whether they use a web-based taxi service.\n\n e. In a survey, smart phone users are asked how many times they used a web-based taxi service over the last year.\n\n1. **Hypotheses.**\nFor each of the research statements below, note whether it represents a null hypothesis claim or an alternative hypothesis claim.\n\n a. The number of hours that grade-school children spend doing homework predicts their future success on standardized tests.\n \n b. King cheetahs on average run the same speed as standard spotted cheetahs.\n \n c. For a particular student, the probability of correctly answering a 5-option multiple choice test is larger than 0.2 (i.e., better than guessing).\n \n d. The mean length of African elephant tusks has changed over the last 100 years.\n \n e. The risk of facial clefts is equal for babies born to mothers who take folic acid supplements compared with those from mothers who do not.\n \n f. Caffeine intake during pregnancy affects mean birth weight.\n \n g. The probability of getting in a car accident is the same if using a cell phone than if not using a cell phone.\n \n \\clearpage\n\n1. **True null hypothesis.**\nUnbeknownst to you, let's say that the null hypothesis is actually true in the population. You plan to run a study anyway.\n\n a. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.05, how likely is it that you will mistakenly reject the null hypothesis?\n \n b. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.01, how likely is it that you will mistakenly reject the null hypothesis?\n \n c. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.10, how likely is it that you will mistakenly reject the null hypothesis?\n\n1. **Identify hypotheses, I.**\nWrite the null and alternative hypotheses in words and then symbols for each of the following situations.\n\n a. New York is known as \"the city that never sleeps\". A random sample of 25 New Yorkers were asked how much sleep they get per night. Do these data provide convincing evidence that New Yorkers on average sleep less than 8 hours a night?\n\n b. Employers at a firm are worried about the effect of March Madness, a basketball championship held each spring in the US, on employee productivity. They estimate that on a regular business day employees spend on average 15 minutes of company time checking personal email, making personal phone calls, etc. They also collect data on how much company time employees spend on such non- business activities during March Madness. They want to determine if these data provide convincing evidence that employee productivity decreases during March Madness.\n\n1. **Identify hypotheses, II.**\nWrite the null and alternative hypotheses in words and using symbols for each of the following situations.\n\n a. Since 2008, chain restaurants in California have been required to display calorie counts of each menu item. Prior to menus displaying calorie counts, the average calorie intake of diners at a restaurant was 1100 calories. After calorie counts started to be displayed on menus, a nutritionist collected data on the number of calories consumed at this restaurant from a random sample of diners. Do these data provide convincing evidence of a difference in the average calorie intake of a diners at this restaurant?\n\n b. Based on the performance of those who took the GRE exam between July 1, 2004 and June 30, 2007, the average Verbal Reasoning score was calculated to be 462. In 2021 the average verbal score was slightly higher. Do these data provide convincing evidence that the average GRE Verbal Reasoning score has changed since 2021?\n \n \\clearpage\n\n1. **Side effects of Avandia.** \nRosiglitazone is the active ingredient in the controversial type 2 diabetes medicine Avandia and has been linked to an increased risk of serious cardiovascular problems such as stroke, heart failure, and death. A common alternative treatment is Pioglitazone, the active ingredient in a diabetes medicine called Actos. In a nationwide retrospective observational study of 227,571 Medicare beneficiaries aged 65 years or older, it was found that 2,593 of the 67,593 patients using Rosiglitazone and 5,386 of the 159,978 using Pioglitazone had serious cardiovascular problems. These data are summarized in the contingency table below.^[The [`avandia`](http://openintrostat.github.io/openintro/reference/avandia.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.] [@Graham:2010]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
treatment No Yes Total
Pioglitazone 154,592 5,386 159,978
Rosiglitazone 65,000 2,593 67,593
Total 219,592 7,979 227,571
\n \n `````\n :::\n :::\n\n a. Determine if each of the following statements is true or false. If false, explain why. *Be careful:* The reasoning may be wrong even if the statement's conclusion is correct. In such cases, the statement should be considered false.\n \n i. Since more patients on Pioglitazone had cardiovascular problems (5,386 vs. 2,593), we can conclude that the rate of cardiovascular problems for those on a Pioglitazone treatment is higher.\n \n ii. The data suggest that diabetic patients who are taking Rosiglitazone are more likely to have cardiovascular problems since the rate of incidence was (2,593 / 67,593 = 0.038) 3.8\\% for patients on this treatment, while it was only (5,386 / 159,978 = 0.034) 3.4\\% for patients on Pioglitazone. \n \n iii. The fact that the rate of incidence is higher for the Rosiglitazone group proves that Rosiglitazone causes serious cardiovascular problems. \n \n iv. Based on the information provided so far, we cannot tell if the difference between the rates of incidences is due to a relationship between the two variables or due to chance.\n \n b. What proportion of all patients had cardiovascular problems?\n\n c. If the type of treatment and having cardiovascular problems were independent, about how many patients in the Rosiglitazone group would we expect to have had cardiovascular problems?\n \n ::: {.content-hidden unless-format=\"pdf\"}\n *See next page for part d.*\n :::\n \n \\clearpage\n\n d. We can investigate the relationship between outcome and treatment in this study using a randomization technique. While in reality we would carry out the simulations required for randomization using statistical software, suppose we actually simulate using index cards. In order to simulate from the independence model, which states that the outcomes were independent of the treatment, we write whether each patient had a cardiovascular problem on cards, shuffled all the cards together, then deal them into two groups of size 67,593 and 159,978. We repeat this simulation 100 times and each time record the difference between the proportions of cards that say \"Yes\" in the Rosiglitazone and Pioglitazone groups. Use the histogram of these differences in proportions to answer the following questions.\n \n i. What are the claims being tested? \n \n ii. Compared to the number calculated in part (b), which would provide more support for the alternative hypothesis, *higher* or *lower* proportion of patients with cardiovascular problems in the Rosiglitazone group? \n \n iii. What do the simulation results suggest about the relationship between taking Rosiglitazone and having cardiovascular problems in diabetic patients?\n \n ::: {.cell}\n ::: {.cell-output-display}\n ![](11-foundations-randomization_files/figure-html/unnamed-chunk-35-1.png){width=90%}\n :::\n :::\n \n \\clearpage\n\n1. **Heart transplants.** \nThe Stanford University Heart Transplant Study was conducted to determine whether an experimental heart transplant program increased lifespan. Each patient entering the program was designated an official heart transplant candidate, meaning that they were gravely ill and would most likely benefit from a new heart. Some patients got a transplant and some did not. The variable `transplant` indicates which group the patients were in; patients in the treatment group got a transplant and those in the control group did not. Of the 34 patients in the control group, 30 died. Of the 69 people in the treatment group, 45 died. Another variable called `survived` was used to indicate whether the patient was alive at the end of the study.^[The [`heart_transplant`](http://openintrostat.github.io/openintro/reference/heart_transplant.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.] [@Turnbull+Brown+Hu:1974]\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](11-foundations-randomization_files/figure-html/unnamed-chunk-36-1.png){width=90%}\n :::\n :::\n\n a. Does the stacked bar plot indicate that survival is independent of whether the patient got a transplant? Explain your reasoning.\n\n b. What do the box plots above suggest about the efficacy (effectiveness) of the heart transplant treatment.\n\n c. What proportion of patients in the treatment group and what proportion of patients in the control group died?\n \n ::: {.content-hidden unless-format=\"pdf\"}\n *See next page for part d.*\n :::\n \n \\clearpage\n\n d. One approach for investigating whether the treatment is effective is to use a randomization technique.\n \n i. What are the claims being tested?\n \n ii. The paragraph below describes the set up for such approach, if we were to do it without using statistical software. Fill in the blanks with a number or phrase, whichever is appropriate.\n \n > We write *alive* on $\\rule{2cm}{0.5pt}$ cards representing patients who were alive at the end of the study, and *deceased* on $\\rule{2cm}{0.5pt}$ cards representing patients who were not. Then, we shuffle these cards and split them into two groups: one group of size $\\rule{2cm}{0.5pt}$ representing treatment, and another group of size $\\rule{2cm}{0.5pt}$ representing control. We calculate the difference between the proportion of \\textit{deceased} cards in the treatment and control groups (treatment - control) and record this value. We repeat this 100 times to build a distribution centered at $\\rule{2cm}{0.5pt}$. Lastly, we calculate the fraction of simulations where the simulated differences in proportions are $\\rule{2cm}{0.5pt}$. If this fraction is low, we conclude that it is unlikely to have observed such an outcome by chance and that the null hypothesis should be rejected in favor of the alternative.\n\n iii. What do the simulation results shown below suggest about the effectiveness of the transplant program?\n \n ::: {.cell}\n ::: {.cell-output-display}\n ![](11-foundations-randomization_files/figure-html/unnamed-chunk-37-1.png){width=90%}\n :::\n :::\n\n\n:::\n", + "engine": "knitr", + "markdown": "\n\n\n# Hypothesis testing with randomization {#sec-foundations-randomization}\n\n::: {.chapterintro data-latex=\"\"}\nStatistical inference is primarily concerned with understanding and quantifying the uncertainty of parameter estimates.\nWhile the equations and details change depending on the setting, the foundations for inference are the same throughout all of statistics.\n\nWe start with two case studies designed to motivate the process of making decisions about research claims.\nWe formalize the process through the introduction of the **hypothesis testing framework**\\index{hypothesis test}, which allows us to formally evaluate claims about the population.\n:::\n\n\n\n\n\nThroughout the book so far, you have worked with data in a variety of contexts.\nYou have learned how to summarize and visualize the data as well as how to model multiple variables at the same time.\nSometimes the dataset at hand represents the entire research question.\nBut more often than not, the data have been collected to answer a research question about a larger group of which the data are a (hopefully) representative subset.\n\nYou may agree that there is almost always variability in data -- one dataset will not be identical to a second dataset even if they are both collected from the same population using the same methods.\nHowever, quantifying the variability in the data is neither obvious nor easy to do, i.e., answering the question \"*how* different is one dataset from another?\" is not trivial.\n\nFirst, a note on notation.\nWe generally use $p$ to denote a population proportion and $\\hat{p}$ to a sample proportion.\nSimilarly, we generally use $\\mu$ to denote a population mean and $\\bar{x}$ to denote a sample mean.\n\n::: {.workedexample data-latex=\"\"}\nSuppose your professor splits the students in your class into two groups: students who sit on the left side of the classroom and students who sit on the right side of the classroom.\nIf $\\hat{p}_{L}$ represents the proportion of students who prefer to read books on screen who sit on the left side of the classroom and $\\hat{p}_{R}$ represents the proportion of students who prefer to read books on screen who sit on the right side of the classroom, would you be surprised if $\\hat{p}_{L}$ did not *exactly* equal $\\hat{p}_{R}$?\n\n------------------------------------------------------------------------\n\nWhile the proportions $\\hat{p}_{L}$ and $\\hat{p}_{R}$ would probably be close to each other, it would be unusual for them to be exactly the same.\nWe would probably observe a small difference due to *chance*.\n:::\n\n::: {.guidedpractice data-latex=\"\"}\nIf we do not think the side of the room a person sits on in class is related to whether they prefer to read books on screen, what assumption are we making about the relationship between these two variables?[^1]\n:::\n\n[^1]: We would be assuming that these two variables are **independent**\\index{independent}.\n\n\n\n\n\nStudying randomness of this form is a key focus of statistics.\nThroughout this chapter, and those that follow, we provide three different approaches for quantifying the variability inherent in data: randomization, bootstrapping, and mathematical models.\nUsing the methods provided in this chapter, we will be able to draw conclusions beyond the dataset at hand to research questions about larger populations that the samples come from.\n\nThe first type of variability we will explore comes from experiments where the explanatory variable (or treatment) is randomly assigned to the observational units.\nAs you learned in [Chapter -@sec-data-hello], a randomized experiment can be used to assess whether one variable (the explanatory variable) causes changes in a second variable (the response variable).\nEvery dataset has some variability in it, so to decide whether the variability in the data is due to (1) the causal mechanism (the randomized explanatory variable in the experiment) or instead (2) natural variability inherent to the data, we set up a sham randomized experiment as a comparison.\nThat is, we assume that each observational unit would have gotten the exact same response value regardless of the treatment level.\nBy reassigning the treatments many many times, we can compare the actual experiment to the sham experiment.\nIf the actual experiment has more extreme results than any of the sham experiments, we are led to believe that it is the explanatory variable which is causing the result and not just variability inherent to the data.\nUsing a few different case studies, let's look more carefully at this idea of a **randomization test**\\index{randomization test}.\n\n\n\n\n\n## Sex discrimination case study {#sec-caseStudySexDiscrimination}\n\nWe consider a study investigating sex discrimination in the 1970s, which is set in the context of personnel decisions within a bank.\nThe research question we hope to answer is, \"Are individuals who identify as female discriminated against in promotion decisions made by their managers who identify as male?\" [@Rosen:1974]\n\n::: {.data data-latex=\"\"}\nThe [`sex_discrimination`](http://openintrostat.github.io/openintro/reference/sex_discrimination.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n:::\n\nThis study considered sex roles, and only allowed for options of \"male\" and \"female\".\nWe should note that the identities being considered are not gender identities and that the study allowed only for a binary classification of sex.\n\n### Observed data\n\nThe participants in this study were 48 bank supervisors who identified as male, attending a management institute at the University of North Carolina in 1972.\nThey were asked to assume the role of the personnel director of a bank and were given a personnel file to judge whether the person should be promoted to a branch manager position.\nThe files given to the participants were identical, except that half of them indicated the candidate identified as male and the other half indicated the candidate identified as female.\nThese files were randomly assigned to the bank managers.\n\n::: {.guidedpractice data-latex=\"\"}\nIs this an observational study or an experiment?\nHow does the type of study impact what can be inferred from the results?[^2]\n:::\n\n[^2]: The study is an experiment, as subjects were randomly assigned a \"male\" file or a \"female\" file (remember, all the files were actually identical in content).\n Since this is an experiment, the results can be used to evaluate a causal relationship between the sex of a candidate and the promotion decision.\n\n\n::: {.cell}\n\n:::\n\n\nFor each supervisor both the sex associated with the assigned file and the promotion decision were recorded.\nUsing the results of the study summarized in @tbl-sex-discrimination-obs, we would like to evaluate if individuals who identify as female are unfairly discriminated against in promotion decisions.\nIn this study, a smaller proportion of female identifying applications were promoted than males (0.583 versus 0.875), but it is unclear whether the difference provides *convincing evidence* that individuals who identify as female are unfairly discriminated against.\n\n\n::: {#tbl-sex-discrimination-obs .cell tbl-cap='Summary results for the sex discrimination study.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
decision
sex promoted not promoted Total
male 21 3 24
female 14 10 24
Total 35 13 48
\n\n`````\n:::\n:::\n\n\nThe data are visualized in @fig-sex-rand-obs as a set of cards.\nNote that each card denotes a personnel file (an observation from our dataset) and the colors indicate the decision: red for promoted and white for not promoted.\nAdditionally, the observations are broken up into groups of male and female identifying groups.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![The sex discrimination study can be thought of as 48 red and white cards.](images/sex-rand-01-obs.png){#fig-sex-rand-obs fig-alt='48 cards are laid out; 24 indicating male files, 24 indicated female files.\nOf the 24 male files 3 of the cards are colored white, and 21 of the cards\nare colored red. Of the female files, 10 of the cards are colored white,\nand 14 of the cards are colored red.\n' width=40%}\n:::\n:::\n\n\n::: {.workedexample data-latex=\"\"}\nStatisticians are sometimes called upon to evaluate the strength of evidence.\nWhen looking at the rates of promotion in this study, why might we be tempted to immediately conclude that individuals identifying as female are being discriminated against?\n\n------------------------------------------------------------------------\n\nThe large difference in promotion rates (58.3% for female personnel versus 87.5% for male personnel) suggest there might be discrimination against women in promotion decisions.\nHowever, we cannot yet be sure if the observed difference represents discrimination or is just due to random chance when there is no discrimination occurring.\nSince we wouldn't expect the sample proportions to be *exactly* equal, even if the truth was that the promotion decisions were independent of sex, we can't rule out random chance as a possible explanation when simply comparing the sample proportions.\n:::\n\nThe previous example is a reminder that the observed outcomes in the sample may not perfectly reflect the true relationships between variables in the underlying population.\n@tbl-sex-discrimination-obs shows there were 7 fewer promotions for female identifying personnel than for the male personnel, a difference in promotion rates of 29.2% $\\left( \\frac{21}{24} - \\frac{14}{24} = 0.292 \\right).$ This observed difference is what we call a **point estimate**\\index{point estimate} of the true difference.\nThe point estimate of the difference in promotion rate is large, but the sample size for the study is small, making it unclear if this observed difference represents discrimination or whether it is simply due to chance when there is no discrimination occurring.\nChance can be thought of as the claim due to natural variability; discrimination can be thought of as the claim the researchers set out to demonstrate.\nWe label these two competing claims, $H_0$ and $H_A:$\n\n\n\n\n\n\\vspace{-2mm}\n\n- $H_0:$ **Null hypothesis**\\index{null hypothesis}. The variables `sex` and `decision` are independent. They have no relationship, and the observed difference between the proportion of males and females who were promoted, 29.2%, was due to the natural variability inherent in the population.\n- $H_A:$ **Alternative hypothesis**\\index{alternative hypothesis}. The variables `sex` and `decision` are *not* independent. The difference in promotion rates of 29.2% was not due to natural variability, and equally qualified female personnel are less likely to be promoted than male personnel.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Hypothesis testing.**\n\nThese hypotheses are part of what is called a **hypothesis test**\\index{hypothesis test}.\nA hypothesis test is a statistical technique used to evaluate competing claims using data.\nOften times, the null hypothesis takes a stance of *no difference* or *no effect*.\nThis hypothesis assumes that any differences seen are due to the variability inherent in the population and could have occurred by random chance.\n\nIf the null hypothesis and the data notably disagree, then we will reject the null hypothesis in favor of the alternative hypothesis.\n\nThere are many nuances to hypothesis testing, so do not worry if you aren't a master of hypothesis testing at the end of this section.\nWe'll discuss these ideas and details many times in this chapter as well as in the chapters that follow.\n:::\n\n\n\n\n\nWhat would it mean if the null hypothesis, which says the variables `sex` and `decision` are unrelated, was true?\nIt would mean each banker would decide whether to promote the candidate without regard to the sex indicated on the personnel file.\nThat is, the difference in the promotion percentages would be due to the natural variability in how the files were randomly allocated to different bankers, and this randomization just happened to give rise to a relatively large difference of 29.2%.\n\nConsider the alternative hypothesis: bankers were influenced by which sex was listed on the personnel file.\nIf this was true, and especially if this influence was substantial, we would expect to see some difference in the promotion rates of male and female candidates.\nIf this sex bias was against female candidates, we would expect a smaller fraction of promotion recommendations for female personnel relative to the male personnel.\n\nWe will choose between the two competing claims by assessing if the data conflict so much with $H_0$ that the null hypothesis cannot be deemed reasonable.\nIf data and the null claim seem to be at odds with one another, and the data seem to support $H_A,$ then we will reject the notion of independence and conclude that the data provide evidence of discrimination.\n\n\\vspace{-2mm}\n\n### Variability of the statistic\n\n@tbl-sex-discrimination-obs shows that 35 bank supervisors recommended promotion and 13 did not.\nNow, suppose the bankers' decisions were independent of the sex of the candidate.\nThen, if we conducted the experiment again with a different random assignment of sex to the files, differences in promotion rates would be based only on random fluctuation in promotion decisions.\nWe can actually perform this **randomization**, which simulates what would have happened if the bankers' decisions had been independent of `sex` but we had distributed the file sexes differently.[^3]\n\n[^3]: The test procedure we employ in this section is sometimes referred to as a **randomization test**.\n If the explanatory variable had not been randomly assigned, as in an observational study, the procedure would be referred to as a **permutation test**.\n Permutation tests are used for observational studies, where the explanatory variable was not randomly assigned.\\index{permutation test}.\n\n\n\n\n\nIn the **simulation**\\index{simulation}, we thoroughly shuffle the 48 personnel files, 35 labelled `promoted` and 13 labelled `not promoted`, together and we deal files into two new stacks.\nNote that by keeping 35 promoted and 13 not promoted, we are assuming that 35 of the bank managers would have promoted the individual whose content is contained in the file **independent** of the sex indicated on their file.\nWe will deal 24 files into the first stack, which will represent the 24 \"female\" files.\nThe second stack will also have 24 files, and it will represent the 24 \"male\" files.\n@fig-sex-rand-shuffle-1 highlights both the shuffle and the reallocation to the sham sex groups.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![The sex discrimination data is shuffled and reallocated to new groups of\nmale and female files.\n](images/sex-rand-02-shuffle-1.png){#fig-sex-rand-shuffle-1 fig-alt='The 48 red and white cards which denote the original data are shuffled and\nreassigned, 24 to each group indicating 24 male files and 24 female files.\n' width=80%}\n:::\n:::\n\n\nThen, as we did with the original data, we tabulate the results and determine the fraction of personnel files designated as \"male\" and \"female\" who were promoted.\n\n\n\n\n\nSince the randomization of files in this simulation is independent of the promotion decisions, any difference in promotion rates is due to chance.\n@tbl-sex-discrimination-rand-1 show the results of one such simulation.\n\n\n::: {#tbl-sex-discrimination-rand-1 .cell tbl-cap='Simulation results, where the difference in promotion rates between male\nand female is purely due to random chance.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
decision
sex promoted not promoted Total
male 18 6 24
female 17 7 24
Total 35 13 48
\n\n`````\n:::\n:::\n\n\n::: {.guidedpractice data-latex=\"\"}\nWhat is the difference in promotion rates between the two simulated groups in @tbl-sex-discrimination-rand-1 ?\nHow does this compare to the observed difference 29.2% from the actual study?[^4]\n:::\n\n[^4]: $18/24 - 17/24=0.042$ or about 4.2% in favor of the male personnel.\n This difference due to chance is much smaller than the difference observed in the actual groups.\n\n@fig-sex-rand-shuffle-1-sort shows that the difference in promotion rates is much larger in the original data than it is in the simulated groups (0.292 \\> 0.042).\nThe quantity of interest throughout this case study has been the difference in promotion rates.\nWe call the summary value the **statistic** of interest (or often the **test statistic**).\nWhen we encounter different data structures, the statistic is likely to change (e.g., we might calculate an average instead of a proportion), but we will always want to understand how the statistic varies from sample to sample.\n\n\n\n\n::: {.cell}\n::: {.cell-output-display}\n![We summarize the randomized data to produce one estimate of the difference\nin proportions given no sex discrimination. Note that the sort step is only used\nto make it easier to visually calculate the simulated sample proportions.\n](images/sex-rand-03-shuffle-1-sort.png){#fig-sex-rand-shuffle-1-sort fig-alt='The 48 red and white cards are show in three panels. The first panel represents\nthe original data and original allocation of the male and female files (in the original\ndata there are 3 white cards in the male group and 10 white cards in the female\ngroup). The second panel represents the shuffled red and white cards that are randomly\nassigned as male and female files. The third panel has the cards sorted according\nto the random assignment of female or male. In the third panel there are 6 white\ncards in the male group and 7 white cards in the female group.' width=100%}\n:::\n:::\n\n\n### Observed statistic vs. null statistics\n\nWe computed one possible difference under the null hypothesis in Guided Practice, which represents one difference due to chance when the null hypothesis is assumed to be true.\nWhile in this first simulation, we physically dealt out files, it is much more efficient to perform this simulation using a computer.\nRepeating the simulation on a computer, we get another difference due to chance under the same assumption: -0.042.\nAnd another: 0.208.\nAnd so on until we repeat the simulation enough times that we have a good idea of the shape of the *distribution of differences* under the null hypothesis.\n@fig-sex-rand-dot-plot shows a plot of the differences found from 100 simulations, where each dot represents a simulated difference between the proportions of male and female files recommended for promotion.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![A stacked dot plot of differences from 100 simulations produced under\nthe null hypothesis, $H_0,$ where the simulated sex and decision are\nindependent. Two of the 100 simulations had a difference of at least\n29.2%, the difference observed in the study, and are shown as solid\nblue dots.\n](11-foundations-randomization_files/figure-html/fig-sex-rand-dot-plot-1.png){#fig-sex-rand-dot-plot width=100%}\n:::\n:::\n\n\nNote that the distribution of these simulated differences in proportions is centered around 0.\nUnder the null hypothesis our simulations made no distinction between male and female personnel files.\nThus, a center of 0 makes sense: we should expect differences from chance alone to fall around zero with some random fluctuation for each simulation.\n\n::: {.workedexample data-latex=\"\"}\nHow often would you observe a difference of at least 29.2% (0.292) according to @fig-sex-rand-dot-plot?\nOften, sometimes, rarely, or never?\n\n------------------------------------------------------------------------\n\nIt appears that a difference of at least 29.2% under the null hypothesis would only happen about 2% of the time according to @fig-sex-rand-dot-plot.\nSuch a low probability indicates that observing such a large difference from chance alone is rare.\n:::\n\nThe difference of 29.2% is a rare event if there really is no impact from listing sex in the candidates' files, which provides us with two possible interpretations of the study results:\n\n- If $H_0,$ the **Null hypothesis** is true: Sex has no effect on promotion decision, and we observed a difference that is so large that it would only happen rarely.\n\n- If $H_A,$ the **Alternative hypothesis** is true: Sex has an effect on promotion decision, and what we observed was actually due to equally qualified female candidates being discriminated against in promotion decisions, which explains the large difference of 29.2%.\n\nWhen we conduct formal studies, we reject a null position (the idea that the data are a result of chance only) if the data strongly conflict with that null position.[^5]\nIn our analysis, we determined that there was only a $\\approx$ 2% probability of obtaining a sample where $\\geq$ 29.2% more male candidates than female candidates get promoted under the null hypothesis, so we conclude that the data provide strong evidence of sex discrimination against female candidates by the male supervisors.\nIn this case, we reject the null hypothesis in favor of the alternative.\n\n[^5]: This reasoning does not generally extend to anecdotal observations.\n Each of us observes incredibly rare events every day, events we could not possibly hope to predict.\n However, in the non-rigorous setting of anecdotal evidence, almost anything may appear to be a rare event, so the idea of looking for rare events in day-to-day activities is treacherous.\n For example, we might look at the lottery: there was only a 1 in 176 million chance that the Mega Millions numbers for the largest jackpot in history (October 23, 2018) would be (5, 28, 62, 65, 70) with a Mega ball of (5), but nonetheless those numbers came up!\n However, no matter what numbers had turned up, they would have had the same incredibly rare odds.\n That is, *any set of numbers we could have observed would ultimately be incredibly rare*.\n This type of situation is typical of our daily lives: each possible event in itself seems incredibly rare, but if we consider every alternative, those outcomes are also incredibly rare.\n We should be cautious not to misinterpret such anecdotal evidence.\n\n**Statistical inference** is the practice of making decisions and conclusions from data in the context of uncertainty.\nErrors do occur, just like rare events, and the dataset at hand might lead us to the wrong conclusion.\nWhile a given dataset may not always lead us to a correct conclusion, statistical inference gives us tools to control and evaluate how often these errors occur.\nBefore getting into the nuances of hypothesis testing, let's work through another case study.\n\n\n\n\n\n## Opportunity cost case study {#sec-caseStudyOpportunityCost}\n\nHow rational and consistent is the behavior of the typical American college student?\nIn this section, we'll explore whether college student consumers always consider the following: money not spent now can be spent later.\n\nIn particular, we are interested in whether reminding students about this well-known fact about money causes them to be a little thriftier.\nA skeptic might think that such a reminder would have no impact.\nWe can summarize the two different perspectives using the null and alternative hypothesis framework.\n\n- $H_0:$ **Null hypothesis**. Reminding students that they can save money for later purchases will not have any impact on students' spending decisions.\n- $H_A:$ **Alternative hypothesis**. Reminding students that they can save money for later purchases will reduce the chance they will continue with a purchase.\n\nIn this section, we'll explore an experiment conducted by researchers that investigates this very question for students at a university in the southwestern United States.\n[@Frederick:2009]\n\n### Observed data\n\nOne-hundred and fifty students were recruited for the study, and each was given the following statement:\n\n> *Imagine that you have been saving some extra money on the side to make some purchases, and on your most recent visit to the video store you come across a special sale on a new video. This video is one with your favorite actor or actress, and your favorite type of movie (such as a comedy, drama, thriller, etc.). This particular video that you are considering is one you have been thinking about buying for a long time. It is available for a special sale price of \\$14.99. What would you do in this situation? Please circle one of the options below.*[^6]\n\n[^6]: This context might feel strange if physical video stores predate you.\n If you're curious about what those were like, look up \"Blockbuster\".\n\nHalf of the 150 students were randomized into a control group and were given the following two options:\n\n> (A) Buy this entertaining video.\n\n> (B) Not buy this entertaining video.\n\nThe remaining 75 students were placed in the treatment group, and they saw a slightly modified option (B):\n\n> (A) Buy this entertaining video.\n\n> (B) Not buy this entertaining video. Keep the \\$14.99 for other purchases.\n\nWould the extra statement reminding students of an obvious fact impact the purchasing decision?\n@tbl-opportunity-cost-obs summarizes the study results.\n\n::: {.data data-latex=\"\"}\nThe [`opportunity_cost`](http://openintrostat.github.io/openintro/reference/opportunity_cost.html) data can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n:::\n\n\n::: {#tbl-opportunity-cost-obs .cell tbl-cap='Summary results of the opportunity cost study.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
decision
group buy video not buy video Total
control 56 19 75
treatment 41 34 75
Total 97 53 150
\n\n`````\n:::\n:::\n\n\nIt might be a little easier to review the results using a visualization.\n@fig-opportunity-cost-obs-bar shows that a higher proportion of students in the treatment group chose not to buy the video compared to those in the control group.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![Stacked bar plot of results of the opportunity cost study.](11-foundations-randomization_files/figure-html/fig-opportunity-cost-obs-bar-1.png){#fig-opportunity-cost-obs-bar width=100%}\n:::\n:::\n\n\nAnother useful way to review the results from @tbl-opportunity-cost-obs is using row proportions, specifically considering the proportion of participants in each group who said they would buy or not buy the video.\nThese summaries are given in @tbl-opportunity-cost-obs-row-prop.\n\n\n::: {#tbl-opportunity-cost-obs-row-prop .cell tbl-cap='The opportunity cost data are summarized using row proportions. Row\nproportions are particularly useful here since we can view the proportion\nof *buy* and *not buy* decisions in each group.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n\n
decision
group buy video not buy video Total
control 0.747 0.253 1
treatment 0.547 0.453 1
\n\n`````\n:::\n:::\n\n\nWe will define a **success**\\index{success} in this study as a student who chooses not to buy the video.[^7]\nThen, the value of interest is the change in video purchase rates that results by reminding students that not spending money now means they can spend the money later.\n\n[^7]: Success is often defined in a study as the outcome of interest, and a \"success\" may or may not actually be a positive outcome.\n For example, researchers working on a study on COVID prevalence might define a \"success\" in the statistical sense as a patient who has COVID-19.\n A more complete discussion of the term **success** will be given in [Chapter -@sec-inference-one-prop].\n\n\n\n\n\nWe can construct a point estimate for this difference as ($T$ for treatment and $C$ for control):\n\n$$\\hat{p}_{T} - \\hat{p}_{C} = \\frac{34}{75} - \\frac{19}{75} = 0.453 - 0.253 = 0.200$$\n\nThe proportion of students who chose not to buy the video was 20 percentage points higher in the treatment group than the control group.\nIs this 20% difference between the two groups so prominent that it is unlikely to have occurred from chance alone, if there is no difference between the spending habits of the two groups?\n\n### Variability of the statistic\n\nThe primary goal in this data analysis is to understand what sort of differences we might see if the null hypothesis were true, i.e., the treatment had no effect on students.\nBecause this is an experiment, we'll use the same procedure we applied in @sec-caseStudySexDiscrimination: randomization.\n\nLet's think about the data in the context of the hypotheses.\nIf the null hypothesis $(H_0)$ was true and the treatment had no impact on student decisions, then the observed difference between the two groups of 20% could be attributed entirely to random chance.\nIf, on the other hand, the alternative hypothesis $(H_A)$ is true, then the difference indicates that reminding students about saving for later purchases actually impacts their buying decisions.\n\n### Observed statistic vs. null statistics\n\nJust like with the sex discrimination study, we can perform a statistical analysis.\nUsing the same randomization technique from the last section, let's see what happens when we simulate the experiment under the scenario where there is no effect from the treatment.\n\nWhile we would in reality do this simulation on a computer, it might be useful to think about how we would go about carrying out the simulation without a computer.\nWe start with 150 index cards and label each card to indicate the distribution of our response variable: `decision`.\nThat is, 53 cards will be labeled \"not buy video\" to represent the 53 students who opted not to buy, and 97 will be labeled \"buy video\" for the other 97 students.\nThen we shuffle these cards thoroughly and divide them into two stacks of size 75, representing the simulated treatment and control groups.\nBecause we have shuffled the cards from both groups together, assuming no difference in their purchasing behavior, any observed difference between the proportions of \"not buy video\" cards (what we earlier defined as *success*) can be attributed entirely to chance.\n\n::: {.workedexample data-latex=\"\"}\nIf we are randomly assigning the cards into the simulated treatment and control groups, how many \"not buy video\" cards would we expect to end up in each simulated group?\nWhat would be the expected difference between the proportions of \"not buy video\" cards in each group?\n\n------------------------------------------------------------------------\n\nSince the simulated groups are of equal size, we would expect $53 / 2 = 26.5,$ i.e., 26 or 27, \"not buy video\" cards in each simulated group, yielding a simulated point estimate of the difference in proportions of 0% .\nHowever, due to random chance, we might also expect to sometimes observe a number a little above or below 26 and 27.\n:::\n\nThe results of a single randomization is shown in @tbl-opportunity-cost-obs-simulated.\n\n\n::: {#tbl-opportunity-cost-obs-simulated .cell tbl-cap='Summary of student choices against their simulated groups. The group\nassignment had no connection to the student decisions, so any difference\nbetween the two groups is due to chance.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n\n\n\n\n\n \n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
decision
group buy video not buy video Total
control 46 29 75
treatment 51 24 75
Total 97 53 150
\n\n`````\n:::\n:::\n\n\nFrom this table, we can compute a difference that occurred from the first shuffle of the data (i.e., from chance alone):\n\n$$\\hat{p}_{T, shfl1} - \\hat{p}_{C, shfl1} = \\frac{24}{75} - \\frac{29}{75} = 0.32 - 0.387 = - 0.067$$\n\nJust one simulation will not be enough to get a sense of what sorts of differences would happen from chance alone.\n\n\n::: {.cell}\n\n:::\n\n\nWe'll simulate another set of simulated groups and compute the new difference: 0.04.\n\nAnd again: 0.12.\n\nAnd again: -0.013.\n\nWe'll do this 1,000 times.\n\nThe results are summarized in a dot plot in @fig-opportunity-cost-rand-dot-plot, where each point represents the difference from one randomization.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![A stacked dot plot of 1,000 simulated (null) differences produced under\nthe null hypothesis, $H_0.$ Six of the 1,000 simulations had a difference\nof at least 20%, which was the difference observed in the study.](11-foundations-randomization_files/figure-html/fig-opportunity-cost-rand-dot-plot-1.png){#fig-opportunity-cost-rand-dot-plot width=90%}\n:::\n:::\n\n\nSince there are so many points and it is difficult to discern one point from the other, it is more convenient to summarize the results in a histogram such as the one in @fig-opportunity-cost-rand-hist, where the height of each histogram bar represents the number of simulations resulting in an outcome of that magnitude.\n\n\n::: {.cell}\n::: {.cell-output-display}\n![A histogram of 1,000 chance differences produced under the null hypothesis.\nHistograms like this one are a convenient representation of data or results\nwhen there are a large number of simulations.](11-foundations-randomization_files/figure-html/fig-opportunity-cost-rand-hist-1.png){#fig-opportunity-cost-rand-hist width=90%}\n:::\n:::\n\n\nUnder the null hypothesis (no treatment effect), we would observe a difference of at least +20% about 0.6% of the time.\nThat is really rare!\nInstead, we will conclude the data provide strong evidence there is a treatment effect: reminding students before a purchase that they could instead spend the money later on something else lowers the chance that they will continue with the purchase.\nNotice that we are able to make a causal statement for this study since the study is an experiment, although we do not know why the reminder induces a lower purchase rate.\n\n## Hypothesis testing {#HypothesisTesting}\n\nIn the last two sections, we utilized a **hypothesis test**\\index{hypothesis test}, which is a formal technique for evaluating two competing possibilities.\nIn each scenario, we described a **null hypothesis**\\index{null hypothesis}, which represented either a skeptical perspective or a perspective of no difference.\nWe also laid out an **alternative hypothesis**\\index{alternative hypothesis}, which represented a new perspective such as the possibility of a relationship between two variables or a treatment effect in an experiment.\nThe alternative hypothesis is usually the reason the scientists set out to do the research in the first place.\n\n\n\n\n\n::: {.important data-latex=\"\"}\n**Null and alternative hypotheses.**\n\nThe **null hypothesis** $(H_0)$ often represents either a skeptical perspective or a claim of \"no difference\" to be tested.\n\nThe **alternative hypothesis** $(H_A)$ represents an alternative claim under consideration and is often represented by a range of possible values for the value of interest.\n:::\n\nIf a person makes a somewhat unbelievable claim, we are initially skeptical.\nHowever, if there is sufficient evidence that supports the claim, we set aside our skepticism.\nThe hallmarks of hypothesis testing are also found in the US court system.\n\n### The US court system\n\nIn the US course system, jurors evaluate the evidence to see whether it convincingly shows a defendant is guilty.\nDefendants are considered to be innocent until proven otherwise.\n\n::: {.workedexample data-latex=\"\"}\nThe US court considers two possible claims about a defendant: they are either innocent or guilty.\n\nIf we set these claims up in a hypothesis framework, which would be the null hypothesis and which the alternative?\n\n------------------------------------------------------------------------\n\nThe jury considers whether the evidence is so convincing (strong) that there is no reasonable doubt regarding the person's guilt.\nThat is, the skeptical perspective (null hypothesis) is that the person is innocent until evidence is presented that convinces the jury that the person is guilty (alternative hypothesis).\n:::\n\nJurors examine the evidence to see whether it convincingly shows a defendant is guilty.\nNotice that if a jury finds a defendant *not guilty*, this does not necessarily mean the jury is confident in the person's innocence.\nThey are simply not convinced of the alternative, that the person is guilty.\nThis is also the case with hypothesis testing: *even if we fail to reject the null hypothesis, we do not accept the null hypothesis as truth*.\n\nFailing to find evidence in favor of the alternative hypothesis is not equivalent to finding evidence that the null hypothesis is true.\nWe will see this idea in greater detail in [Chapter -@sec-decerr].\n\n### p-value and statistical discernibility\n\nIn @caseStudySexDiscrimination we encountered a study from the 1970's that explored whether there was strong evidence that female candidates were less likely to be promoted than male candidates.\nThe research question -- are female candidates discriminated against in promotion decisions?\n-- was framed in the context of hypotheses:\n\n- $H_0:$ Sex has no effect on promotion decisions.\n\n- $H_A:$ Female candidates are discriminated against in promotion decisions.\n\nThe null hypothesis $(H_0)$ was a perspective of no difference in promotion.\nThe data on sex discrimination provided a point estimate of a 29.2% difference in recommended promotion rates between male and female candidates.\nWe determined that such a difference from chance alone, assuming the null hypothesis was true, would be rare: it would only happen about 2 in 100 times.\nWhen results like these are inconsistent with $H_0,$ we reject $H_0$ in favor of $H_A.$ Here, we concluded there was discrimination against female candidates.\n\nThe 2-in-100 chance is what we call a **p-value**, which is a probability quantifying the strength of the evidence against the null hypothesis, given the observed data.\n\n::: {.important data-latex=\"\"}\n**p-value.**\n\nThe **p-value**\\index{hypothesis testing!p-value} is the probability of observing data at least as favorable to the alternative hypothesis as our current dataset, if the null hypothesis were true.\nWe typically use a summary statistic of the data, such as a difference in proportions, to help compute the p-value and evaluate the hypotheses.\nThis summary value that is used to compute the p-value is often called the **test statistic**\\index{test statistic}.\n:::\n\n\n\n\n\n::: {.workedexample data-latex=\"\"}\nIn the sex discrimination study, the difference in discrimination rates was our test statistic.\nWhat was the test statistic in the opportunity cost study covered in @sec-caseStudyOpportunityCost)?\n\n------------------------------------------------------------------------\n\nThe test statistic in the opportunity cost study was the difference in the proportion of students who decided against the video purchase in the treatment and control groups.\nIn each of these examples, the **point estimate** of the difference in proportions was used as the test statistic.\n:::\n\nWhen the p-value is small, i.e., less than a previously set threshold, we say the results are **statistically discernible**\\index{statistically significant}\\index{statistically discernible}.\nThis means the data provide such strong evidence against $H_0$ that we reject the null hypothesis in favor of the alternative hypothesis.[^8]\nThe threshold is called the **discernibility level**\\index{hypothesis testing!discernibility level}\\index{significance level}\\index{discernibility level} and often represented by $\\alpha$ (the Greek letter *alpha*).\n[^9] The value of $\\alpha$ represents how rare an event needs to be in order for the null hypothesis to be rejected\n. Historically, many fields have set $\\alpha = 0.05,$ meaning that the results need to occur less than 5% of the time, if the null hypothesis is to be rejected\n. The value of $\\alpha$ can vary depending on the the field or the application\n.\n\n[^8]: Many texts use the phrase \"statistically significant\" instead of \"statistically discernible\".\n We have chosen to use \"discernible\" to indicate that a precise statistical event has happened, as opposed to a notable effect which may or may not fit the statistical definition of discernible or significant.\n\n[^9]: Here, too, we have chosen \"discernibility level\" instead of \"significance level\" which you will see in some texts.\n\n\n\n\n\nNote that you may have heard the phrase \"statistically significant\" as a way to describe \"statistically discernible.\" Although in everyday language \"significant\" would indicate that a difference is large or meaningful, that is not necessarily the case here.\nThe term \"statistically discernible\" indicates that the p-value from a study fell below the chosen discernibility level.\nFor example, in the sex discrimination study, the p-value was found to be approximately 0.02.\nUsing a discernibility level of $\\alpha = 0.05,$ we would say that the data provided statistically discernible evidence against the null hypothesis.\nHowever, this conclusion gives us no information regarding the size of the difference in promotion rates!\n\n::: {.important data-latex=\"\"}\n**Statistical discernibility.**\n\nWe say that the data provide **statistically discernible**\\index{hypothesis testing!statistically discernible.} evidence against the null hypothesis if the p-value is less than some predetermined threshold (e.g., 0.01, 0.05, 0.1).\n:::\n\n::: {.workedexample data-latex=\"\"}\nIn the opportunity cost study in @sec-caseStudyOpportunityCost, we analyzed an experiment where study participants had a 20% drop in likelihood of continuing with a video purchase if they were reminded that the money, if not spent on the video, could be used for other purchases in the future.\nWe determined that such a large difference would only occur 6-in-1,000 times if the reminder actually had no influence on student decision-making.\nWhat is the p-value in this study?\nWould you classify the result as \"statistically discernible\"?\n\n------------------------------------------------------------------------\n\nThe p-value was 0.006.\nSince the p-value is less than 0.05, the data provide statistically discernible evidence that US college students were actually influenced by the reminder.\n:::\n\n::: {.important data-latex=\"\"}\n**What's so special about 0.05?**\n\nWe often use a threshold of 0.05 to determine whether a result is statistically discernible.\nBut why 0.05?\nMaybe we should use a bigger number, or maybe a smaller number.\nIf you're a little puzzled, that probably means you're reading with a critical eye -- good job!\nWe've made a video to help clarify *why 0.05*:\n\n\n\nSometimes it's also a good idea to deviate from the standard.\nWe'll discuss when to choose a threshold different than 0.05 in [Chapter -@sec-decerr].\n:::\n\n\\clearpage\n\n## Chapter review {#chp11-review}\n\n### Summary\n\n@fig-fullrand provides a visual summary of the randomization testing procedure.\n\n\\index{randomization test}\n\n\n\n\n::: {.cell}\n::: {.cell-output-display}\n![An example of one simulation of the full randomization procedure from a hypothetical\ndataset as visualized in the first panel. We repeat the steps hundreds or thousands\nof times.\n](images/fullrand.png){#fig-fullrand fig-alt='48 red and white cards are show in three panels. The first panel represents\noriginal data and original allocation of Group 1 and Group 2 (in the original data\nthere are 7 white cards in Group 1 and 10 white cards in Group 2). The second panel\nrepresents the shuffled red and white cards that are randomly assigned as Group\n1 and Group 2. The third panel has the cards sorted according to the random assignment\nof Group 1 and Group 2. In the third panel there are 8 white cards in the Group\n1 and 9 white cards in Group 2.' width=100%}\n:::\n:::\n\n\nWe can summarize the randomization test procedure as follows:\n\n- **Frame the research question in terms of hypotheses.** Hypothesis tests are appropriate for research questions that can be summarized in two competing hypotheses. The null hypothesis $(H_0)$ usually represents a skeptical perspective or a perspective of no relationship between the variables. The alternative hypothesis $(H_A)$ usually represents a new view or the existance of a relationship between the variables.\n- **Collect data with an observational study or experiment.** If a research question can be formed into two hypotheses, we can collect data to run a hypothesis test. If the research question focuses on associations between variables but does not concern causation, we would use an observational study. If the research question seeks a causal connection between two or more variables, then an experiment should be used.\n- **Model the randomness that would occur if the null hypothesis was true.** In the examples above, the variability has been modeled as if the treatment (e.g., sexual identity, opportunity) allocation was independent of the outcome of the study. The computer generated null distribution is the result of many different randomizations and quantifies the variability that would be expected if the null hypothesis was true.\n- **Analyze the data.** Choose an analysis technique appropriate for the data and identify the p-value. So far, we have only seen one analysis technique: randomization. Throughout the rest of this textbook, we'll encounter several new methods suitable for many other contexts.\n- **Form a conclusion.** Using the p-value from the analysis, determine whether the data provide evidence against the null hypothesis. Also, be sure to write the conclusion in plain language so casual readers can understand the results.\n\n@tbl-chp11-summary is another look at the randomization test summary.\n\n\n::: {#tbl-chp11-summary .cell tbl-cap='Summary of randomization as an inferential statistical method.'}\n::: {.cell-output-display}\n`````{=html}\n\n \n \n \n \n \n \n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
Question Answer
What does it do? Shuffles the explanatory variable to mimic the natural variability found in a randomized experiment
What is the random process described? Randomized experiment
What other random processes can be approximated? Can also be used to describe random sampling in an observational model
What is it best for? Hypothesis testing (can also be used for confidence intervals, but not covered in this text).
What physical object represents the simulation process? Shuffling cards
\n\n`````\n:::\n:::\n\n\n### Terms\n\nWe introduced the following terms in the chapter.\nIf you're not sure what some of these terms mean, we recommend you go back in the text and review their definitions.\nWe are purposefully presenting them in alphabetical order, instead of in order of appearance, so they will be a little more challenging to locate.\nHowever, you should be able to easily spot them as **bolded text**.\n\n\n::: {.cell}\n::: {.cell-output-display}\n`````{=html}\n\n\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n
alternative hypothesis p-value statistic
confidence interval permutation test statistical inference
discernibility level point estimate statistically discernible
hypothesis test randomization test statistically significant
independent significance level success
null hypothesis simulation test statistic
\n\n`````\n:::\n:::\n\n\n\\clearpage\n\n## Exercises {#chp11-exercises}\n\nAnswers to odd-numbered exercises can be found in [Appendix -@sec-exercise-solutions-11].\n\n::: {.exercises data-latex=\"\"}\n1. **Identify the parameter, I** For each of the following situations, state whether the parameter of interest is a mean or a proportion.\n It may be helpful to examine whether individual responses are numerical or categorical.\n\n a. In a survey, one hundred college students are asked how many hours per week they spend on the Internet.\n\n b. In a survey, one hundred college students are asked: \"What percentage of the time you spend on the Internet is part of your course work?\"\n\n c. In a survey, one hundred college students are asked whether they cited information from Wikipedia in their papers.\n\n d. In a survey, one hundred college students are asked what percentage of their total weekly spending is on alcoholic beverages.\n\n e. In a sample of one hundred recent college graduates, it is found that 85 percent expect to get a job within one year of their graduation date.\n\n2. **Identify the parameter, II.** For each of the following situations, state whether the parameter of interest is a mean or a proportion.\n\n a. A poll shows that 64% of Americans personally worry a great deal about federal spending and the budget deficit.\n\n b. A survey reports that local TV news has shown a 17% increase in revenue within a two year period while newspaper revenues decreased by 6.4% during this time period.\n\n c. In a survey, high school and college students are asked whether they use geolocation services on their smart phones.\n\n d. In a survey, smart phone users are asked whether they use a web-based taxi service.\n\n e. In a survey, smart phone users are asked how many times they used a web-based taxi service over the last year.\n\n3. **Hypotheses.** For each of the research statements below, note whether it represents a null hypothesis claim or an alternative hypothesis claim.\n\n a. The number of hours that grade-school children spend doing homework predicts their future success on standardized tests.\n\n b. King cheetahs on average run the same speed as standard spotted cheetahs.\n\n c. For a particular student, the probability of correctly answering a 5-option multiple choice test is larger than 0.2 (i.e., better than guessing).\n\n d. The mean length of African elephant tusks has changed over the last 100 years.\n\n e. The risk of facial clefts is equal for babies born to mothers who take folic acid supplements compared with those from mothers who do not.\n\n f. Caffeine intake during pregnancy affects mean birth weight.\n\n g. The probability of getting in a car accident is the same if using a cell phone than if not using a cell phone.\n\n \\clearpage\n\n4. **True null hypothesis.** Unbeknownst to you, let's say that the null hypothesis is actually true in the population.\n You plan to run a study anyway.\n\n a. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.05, how likely is it that you will mistakenly reject the null hypothesis?\n\n b. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.01, how likely is it that you will mistakenly reject the null hypothesis?\n\n c. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.10, how likely is it that you will mistakenly reject the null hypothesis?\n\n5. **Identify hypotheses, I.** Write the null and alternative hypotheses in words and then symbols for each of the following situations.\n\n a. New York is known as \"the city that never sleeps\".\n A random sample of 25 New Yorkers were asked how much sleep they get per night.\n Do these data provide convincing evidence that New Yorkers on average sleep less than 8 hours a night?\n\n b. Employers at a firm are worried about the effect of March Madness, a basketball championship held each spring in the US, on employee productivity.\n They estimate that on a regular business day employees spend on average 15 minutes of company time checking personal email, making personal phone calls, etc.\n They also collect data on how much company time employees spend on such non- business activities during March Madness.\n They want to determine if these data provide convincing evidence that employee productivity decreases during March Madness.\n\n6. **Identify hypotheses, II.** Write the null and alternative hypotheses in words and using symbols for each of the following situations.\n\n a. Since 2008, chain restaurants in California have been required to display calorie counts of each menu item.\n Prior to menus displaying calorie counts, the average calorie intake of diners at a restaurant was 1100 calories.\n After calorie counts started to be displayed on menus, a nutritionist collected data on the number of calories consumed at this restaurant from a random sample of diners.\n Do these data provide convincing evidence of a difference in the average calorie intake of a diners at this restaurant?\n\n b. Based on the performance of those who took the GRE exam between July 1, 2004 and June 30, 2007, the average Verbal Reasoning score was calculated to be 462.\n In 2021 the average verbal score was slightly higher.\n Do these data provide convincing evidence that the average GRE Verbal Reasoning score has changed since 2021?\n\n \\clearpage\n\n7. **Side effects of Avandia.** Rosiglitazone is the active ingredient in the controversial type 2 diabetes medicine Avandia and has been linked to an increased risk of serious cardiovascular problems such as stroke, heart failure, and death.\n A common alternative treatment is Pioglitazone, the active ingredient in a diabetes medicine called Actos.\n In a nationwide retrospective observational study of 227,571 Medicare beneficiaries aged 65 years or older, it was found that 2,593 of the 67,593 patients using Rosiglitazone and 5,386 of the 159,978 using Pioglitazone had serious cardiovascular problems.\n These data are summarized in the contingency table below.[^_11-ex-foundations-randomization-1]\n [@Graham:2010]\n\n ::: {.cell}\n ::: {.cell-output-display}\n `````{=html}\n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n
treatment No Yes Total
Pioglitazone 154,592 5,386 159,978
Rosiglitazone 65,000 2,593 67,593
Total 219,592 7,979 227,571
\n \n `````\n :::\n :::\n\n a. Determine if each of the following statements is true or false.\n If false, explain why.\n *Be careful:* The reasoning may be wrong even if the statement's conclusion is correct.\n In such cases, the statement should be considered false.\n\n i. Since more patients on Pioglitazone had cardiovascular problems (5,386 vs. 2,593), we can conclude that the rate of cardiovascular problems for those on a Pioglitazone treatment is higher.\n\n ii. The data suggest that diabetic patients who are taking Rosiglitazone are more likely to have cardiovascular problems since the rate of incidence was (2,593 / 67,593 = 0.038) 3.8% for patients on this treatment, while it was only (5,386 / 159,978 = 0.034) 3.4% for patients on Pioglitazone.\n\n iii. The fact that the rate of incidence is higher for the Rosiglitazone group proves that Rosiglitazone causes serious cardiovascular problems.\n\n iv. Based on the information provided so far, we cannot tell if the difference between the rates of incidences is due to a relationship between the two variables or due to chance.\n\n b. What proportion of all patients had cardiovascular problems?\n\n c. If the type of treatment and having cardiovascular problems were independent, about how many patients in the Rosiglitazone group would we expect to have had cardiovascular problems?\n\n ::: {.content-hidden unless-format=\"pdf\"} *See next page for part d.* :::\n\n \\clearpage\n\n d. We can investigate the relationship between outcome and treatment in this study using a randomization technique.\n While in reality we would carry out the simulations required for randomization using statistical software, suppose we actually simulate using index cards.\n In order to simulate from the independence model, which states that the outcomes were independent of the treatment, we write whether each patient had a cardiovascular problem on cards, shuffled all the cards together, then deal them into two groups of size 67,593 and 159,978.\n We repeat this simulation 100 times and each time record the difference between the proportions of cards that say \"Yes\" in the Rosiglitazone and Pioglitazone groups.\n Use the histogram of these differences in proportions to answer the following questions.\n\n i. What are the claims being tested?\n\n ii. Compared to the number calculated in part (b), which would provide more support for the alternative hypothesis, *higher* or *lower* proportion of patients with cardiovascular problems in the Rosiglitazone group?\n\n iii. What do the simulation results suggest about the relationship between taking Rosiglitazone and having cardiovascular problems in diabetic patients?\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](11-foundations-randomization_files/figure-html/unnamed-chunk-35-1.png){width=90%}\n :::\n :::\n\n \\clearpage\n\n8. **Heart transplants.** The Stanford University Heart Transplant Study was conducted to determine whether an experimental heart transplant program increased lifespan.\n Each patient entering the program was designated an official heart transplant candidate, meaning that they were gravely ill and would most likely benefit from a new heart.\n Some patients got a transplant and some did not.\n The variable `transplant` indicates which group the patients were in; patients in the treatment group got a transplant and those in the control group did not.\n Of the 34 patients in the control group, 30 died.\n Of the 69 people in the treatment group, 45 died.\n Another variable called `survived` was used to indicate whether the patient was alive at the end of the study.[^_11-ex-foundations-randomization-2]\n [@Turnbull+Brown+Hu:1974]\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](11-foundations-randomization_files/figure-html/unnamed-chunk-36-1.png){width=90%}\n :::\n :::\n\n a. Does the stacked bar plot indicate that survival is independent of whether the patient got a transplant?\n Explain your reasoning.\n\n b. What do the box plots above suggest about the efficacy (effectiveness) of the heart transplant treatment.\n\n c. What proportion of patients in the treatment group and what proportion of patients in the control group died?\n\n ::: {.content-hidden unless-format=\"pdf\"}\n *See next page for part d.*\n :::\n\n \\clearpage\n\n d. One approach for investigating whether the treatment is effective is to use a randomization technique.\n\n i. What are the claims being tested?\n\n ii. The paragraph below describes the set up for such approach, if we were to do it without using statistical software.\n Fill in the blanks with a number or phrase, whichever is appropriate.\n\n > We write *alive* on $\\rule{2cm}{0.5pt}$ cards representing patients who were alive at the end of the study, and *deceased* on $\\rule{2cm}{0.5pt}$ cards representing patients who were not.\n > Then, we shuffle these cards and split them into two groups: one group of size $\\rule{2cm}{0.5pt}$ representing treatment, and another group of size $\\rule{2cm}{0.5pt}$ representing control.\n > We calculate the difference between the proportion of \\textit{deceased} cards in the treatment and control groups (treatment - control) and record this value.\n > We repeat this 100 times to build a distribution centered at $\\rule{2cm}{0.5pt}$.\n > Lastly, we calculate the fraction of simulations where the simulated differences in proportions are $\\rule{2cm}{0.5pt}$.\n > If this fraction is low, we conclude that it is unlikely to have observed such an outcome by chance and that the null hypothesis should be rejected in favor of the alternative.\n\n iii. What do the simulation results shown below suggest about the effectiveness of the transplant program?\n\n ::: {.cell}\n ::: {.cell-output-display}\n ![](11-foundations-randomization_files/figure-html/unnamed-chunk-37-1.png){width=90%}\n :::\n :::\n\n[^_11-ex-foundations-randomization-1]: The [`avandia`](http://openintrostat.github.io/openintro/reference/avandia.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n[^_11-ex-foundations-randomization-2]: The [`heart_transplant`](http://openintrostat.github.io/openintro/reference/heart_transplant.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.\n\n\n:::\n", "supporting": [ "11-foundations-randomization_files" ], diff --git a/_freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-obs-bar-1.png b/_freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-obs-bar-1.png new file mode 100644 index 0000000000000000000000000000000000000000..3e5e2beead4eebf909e7f0d7ee50be08578e5169 GIT binary patch literal 82500 zcmeEvcR1JW-}hI`rJ^a4(IDB0qRgwIqEJ@K9vPLDmEDkrs3gg%5ZR<`$_zzFBqAew z@BO^ay3+ML_i^0EeLTnW$MeVUd;jk1`r$i1-}7^x@Aqq+=kKPX{9)SVOv@=03hmJ& z2TxKcbgLV!fzVXn(XnfWqNXl4^rmI|2@fy@WF3rERLvOq);?u$p2HVe{kS$ z3S~3p=)u30?E`xnOq`SrAB!|av0r06=>8Xz!Ql;GmlkL;tv=Ie`B5hP#8=u+YwQl1 z(4X;FJ=`m!VNuWY_IV=xneZaZ#Ttr}Y0|fE+`97DmcOnX-0=5Z3e5`#shxSftvBQtjc-5LGHAa9m-Fl4Hc%4Tz3lf-6iTG}qR>A-ZQLj4h^#J(I%!Voa#fax^qDsyU61XlrB?KKGedNa$tU z)a7fka&oRSgGFvs-xx8xugdv4sTPKLzr4=+g&#JzE|K}qpMDR=e@5fKnH&5}-bLN% z)RZT5F=tZDioUu91_sL9VKOu{oXupqBO|oSDe;;^L`+Oi`@H|Xdu#5Y^2Urix_Jvl+I}*Wo%Xi3tMO{_6DBvr%}o~m{j4IgotxH+ zlW$aeQmy9w`}cThTWjmgM2q*^#_Q;$kz4k>rgCdgGc$`z-a+oUbZqgvcgA(eCYp9w z1U=8O7IemaeSDN^_y2Gql zqe-4s-9L3XLfduBghuY=ay9R19bLZh#jEuqSSruzc+=T5;1k}=Z$mrniHhNUZ8`if zy^nlAq{~-XIUiqH{lw<`y|2Ekluq@1SkRS@XS>aNpQ&8@>jLo4|Kl3|o6GyppZ`u$8}iC)ye2bA9DTs}imVK(Lq}Oiz9+5x=OH zcB^b%`FI;+Yh#_NB42neyrrRmR}j{C$yNjS5H5mox< z!&czs*$?~hzICt8iCh{oNIXH&5!tdpoqD`fV@_F??QLgvnfR{lI%}gjzKEjOvH<1W z8fqA{ohkq^*KCt{;Okp$BS4|-KC*!OY8&pbN~GKMf7>Kt7Sj#-XnJd*A4wbhc<&#y z&t~dJfO%K?8j2g!pU+)=^WfHVHE|L>33(3%w6$vPP$Uj6lX^{=ll zD2WQPdKc*>;tJ+Qsub{=ASu_m!)(qYm2v{~8#buA+&><$$EN?A^W4m2?CDpsPpK(x z4yAOznWD7B{d@QH9&KT|bN1}nJtma~IkRJ86HQmk_qGR8v)bzv-{*){iw_nyIoVzo z#Iv{jI_)Me(dHX?&+yO7DAKbA9%#%zADiEwPByljn`{rU`*!JKds)_0SF}-iu;zCz zyn*ECC#6Q$`Pm0m(aIUd!ao7d?bAtTBu-IG@1*Sh=Pjfs4uw{1^A;ZpnV)IDEs*^P zi2eJ7zmSm^)9$DZOp7UzEDICmP2X0gJHa-e)#d#7dofSkubOA{zRu0fJ>9XK@?^tb z3m727?;+nA7hG4C!)TO6>zm7q8#Xdi{-P#`;^#vr#V06e_VXEY7Tn{vd6KguRiG1b zwx<_SB2WD5^CB%<3Wd(TuQdvBzT%;I@xyLR(^pk%DbgQ`qrk(B-{30jz8L!XO3ihI zdb3)*p?cN0>eojo7Xx3-c16c8YYcFiof;)`@(_cj@;OZ^%BLk_o{R3L+ly;GJR;5- z-~IX5OP-u`nJm=~zF4;Rtv&`_6%VmlP@mO!_OEA9GG3AU?9QMCf`WG)#{lQAQ;11p zy>d#t>Pcadk;a%VX=!N}>XP@i-aU|R+w0JiSj2j%^&a2pqTa+Jj6aG^UGhX2(o{WOcxHYtl!x2)mFSaiVmBQUW7oWAqtUlGQ(OKlX+x`3Z zX*cb08Z2NC^KNZxqh;A={qf1)_-Evp3wQGQFG)vzwo6QPghs2za%=N(adGkUYo%GW zVFXpKXu*z*}mCpnc#ID*9?vD7AK7FCt!>H_pBOY9{w+!|~_I$s^{j z(`V2U0z}No+AzZ%dbO;1(B9T+mE?quX;q)FexYX`omfxP)m5y!O_lKhyYO6A5i^bQ zV2R=3;rSuIob!#@5+BZ*PQC3*KKtP@>TS=f8m-0DbjKcUIDU4pxj>}BS_yYyYOGfb z)4t1;t0_^$q>}ynM2)s;_MUzQWd8i}zAb{Z;9@B2kFD3NQXds7l)Y@l)K$?()j)H@U+={z^8J#W)l8O|jjVp#G3*D5*u zUZ~TC_9F##kzMiOkyvM;e@auNbB(5*=73v7umkt3O7_f9DaNMJvWTTq;ZVFSI=bfFy=~pS5$`ea&ey~>Tu5n9y>pR_5!N+Imh0oesuHL*?I4H4bJP85rRNzm ztt$q;=S3TGyE(`$w9?I$FOABVp?yiD z+5!@wY`udfwbS*r#rND#+r5igw#j&=4wdjIiDm6VJ@&@c%KK?sE$4L7t5WYKAqDW%IHgvPJhk2G}7Z=S9I@4tEW)eU#vSF$9mR3zf;r# z8LPLWB2>vV%5>Q()|py;@9@1x#aY?J?FS|XTcX3mDW!e_{WbC0L9JZcm)d;Km}kAR z-7q!V@2b6Gg-YQEkwz!frBAv0fiq?c1YGV}z1b(NuKvZ`WjMffriHCqa#((LdR%~? zKQ3*Os_X6_ti!(cCNqSxw~L=Egaqd%yH4b>alhQ8SNf2zKefe6{pHzM&5YM!VeA`j zW2{lZ@#7eJ!X^}c8qPpP|F*cSu{tiL=V2e)<+0GKgv!O0z9-Dg%%HYjEDPKVILO7v zcc(xPO#$U@wlAaqY+2x?@dmpT)acx!_+c-WjCK0)x45U&D;ZadKZgj2(l85*=qI2( zSEV53>+9Q_x|M^219zhZ%T&vGw7NSkBMwib=NEAp>F}1COMUF1(C|o5A0Lpt+ykPZ zwqx%rRF~Pw#R58cfARrK*tFq^O?ZBJGtCaP>QbrF8vwGLq ztfGvTHNCxxdz4f97S}wB!XNMB(iQvaT#c4PXLuW~aiRrqFmBc*^8RRdjR+dIu1Q%g z$9#KXhG`lbz{8Ubo}%;b*R+TDCyZ$QU7;_u;ggjVWsB|Eaocv51}M^LIr3@wbb|h;nW%KSGKP^rb)0N z-Nv!`CMSU}XAP7ShHEh3hrL-f{e{2Y=a56gIOQ%gUn4a)=#3jJW`7K&4qw}@@+jw0 z5oYfqqxX*ljXyqV`lKTxQ-}hQ1Ju4u0Elt%Lk#(}S>|A2(?;8UEuKPJn4t#M+mAo? zWRr4fdUM(LQmj{j9xzX4UwSuzac;Wk`x>}<_ZqthQ>O&6%=x+LEXQ#=)+$ssz_}pX zIumtu^|#yf6Kl~gt!77S$^-Wb*&Afo_HN+Ucm#oJQuQjEEmzQFid1p53P$k{mK-V`c@xr zm^eAyKHk@mv1>~jD*HFUV^mC0RQ;=mgB`kFU?%&T+jszY&5Whw(6S0ycYH+Yn`-q@ zh)eixEL;bGb>+&HCbs>&8=`|U^7;p=)wGv}9m2Iwp<4w5hWj2HGcqukLGzr!s|vkX zHtmc_NZ9$|f_7CRCUup(7@z(7(HiX>y@FdpWul?E$;Rw!q11^2&`9AzP%rqz#Kd%3 zFFBK(?}_JjF1*F_6o z5NDnLVD7SxS;!eBo)yrX`+^TNgZZl}xe|N7iP98F1ap-tj6``<-Rmh|=Y~=LfNbf&YcCJX*gJpxb zPFsnuZ=fmg*u@|3kE&j%3@ZjC;MU;xN1-nE;T-R-5zu*0D^jl*KC2jUJYYj+bhGPB zk?YD$dt!#x^*y+EZxAB@JVEVw>4(43$wz5XKzfTdIAAFa4GoQsgupU zB*Y0&i<`{3DFO2*XKpm!H!v2BD5;cx1>;9d$a~uktHu_D6c-m?0z_E6%oFISt(d1D zl?uhVI4WoIgL!4({KGS57|EkaU9H7FRe?ECpz7g%T1-2ez*oiB~?uk%8VF70;%xpdwWpo{18a?2Ed(-%;+tcT_=q%J#apBWUw?@}PYtCIEaI81w-jvhQU%t?j;1%z*`v{XOc`t-!0|sPJ zjl#p*mUYOLUqocwS50g0k4O6VX;X*G#Ntz%Z{0Q3YGM3yGxwG z_RYndA%Q)rO_Jjtu>`+jX*<$TOuz<)sA9FV(ps{i!)-5)rj47xtO zxXmCSuZod!1g?lSe9Etx?#U{#@5^HEgIm%4hYJ|A1ASF4oCpVAi~`H=e1F%^&#rKz zQ6`XM@iJbm%v2DsPF^a-#=kuGJD7kT zWYbr__k&%l*oDUI*-&rEsrdP+_-l?$L_@-&!WRe>v+MKP_TlkvvFV^#6m}ySNH=+Qa2QbWF4iqu}<~rBz z8mIp9xsyKqp81P5R(<6M8-Hg3{<)8v4Y1%)5PIug(aWQ7lC~wLK01)MN?`t;afz4Y zRELs+#3;(H!YMv(ZZfIR1+H>J_~`*x-q6yG-p2c=goU5klWR#wIj z(yqNBsL#W8slI^looW>| zq8F%?FwND2Y6=7Ej3{~2(9_dvx=gnDD%_r{hxBFNaz|vl6N47pdIpA7oA&U|hMbYe zx$GA7c$6N0qTLCW=55urmc!XS5LRKwW4IRMmvIL+E*7 zttv0f#3JcrpM+(u6m95BA+ItP_JXE&Ok^a7wR6&af7|}qN+^|AKZEmDvd~!$KCTO%5K*|*t#mAR}cju#AS-> z!=>l)LHqRbZ&X%RMg@zanQS?5J#2nML|9lWlow~LG^MiG?IUe|+62$}rae8dYw6OZ zDc>BK^bwBgVV=K!jR38@bo~X7<#tx6VCGP0@5M~@qsF{Qrr*JI zhYrJ~Zc`nl@;2jHp2z2LT6|C>~f;t*K~60 zW9e1jAJs@UuE2`Z=HpZG!w3bKrFTyE=O|nZc5wOK7PdqUNY>EP{gr)H4;3-GUWp?R z=#Z)!?TuQQfnVd4hDKn_V?V!|ME#;qVmuMxW>nQg>Sn6p7LbyXda}=cpvm-$L9*l{ zDOZ;_hAdEh09ViHHDI2JJ|Xh+^PGckmc?;(e0+K!sdA{TG}>~D+mtl!WFeWM=+s?7 z!_o2CQ`3#}TE%a{N9A`Hs@Os5W5#rvI@7_he*KdA(5F#zbK^M?FOQpy-YRM#%FdKI zPxmDKugH?yb)E^y2KvIDIlxhN9u}}csF7T+={o>o=pxJfg*cx~5zMAcjm4uY^I8^g z!y66HpxW(&dUOGdgtdyZ1pK1VTNubRVu`qQLH#^+pqqecs_Kz(N7K6GPRy#HAM8?g zfC=n87ob}(F)WH)mDH6^Rm%b`Q$VL>{0O@hKqaY(7%UR_fV#@Q76g(MI`r^q^mf=7 zB42Kz7|w7-1XiMsH!TA|Aa%fvia-L$9yM{AP^p5EKWS+~w;`MiRt0I37}+DXeIR{v z6Gc+rT&8=u=F1XLSn%E%GlQ9#nJ9}d9mo4FUAlxp5OX=o!^Nczftsv41}*z7P2ZOI za4KYXMMarg3M(I5JA=I0D9=YVc4?f;O5at!1lp*{*)n~4jAD19b7neZ#r zD4?&ds)%wlo}Df;69#XK(k`|WNy;er(pl+ERHy~7OYed3)#KhvIE?II(}gZ&iLOn= zqi*f_DF{dkV~%A3=Gm7f+x(2qo_#0)OF>QRlA+&KA}bLBU-}jhOB1z5#h$$lSIVLL z5#T78GsyZRa2rr-2o~&8&fVSfe`c;IAJff)gcZ1T<+`s}9EA@*5*|^~SsksG^v3wj z^<9JZ;@_`Jiox*G?X*=53AC;}O7G<_erc#1l#QTtPzf=S4wF+QB_+@y?!^%C{qx7! z4m;7d2TEw?IULcz729=`%9q>p*6nV)xUMeoj@o|uY$l4ZC~C{sLeGsp=eNE0QIMR( zbjKYx@eN02Z{e8~}1vL{;30sYBGBT)XJKd-tX^*nS1Z^4TeLT2=M6b!X+`RpJTv zZ*R|BPOtTNx$pec35bkv;?~aawDB|5)5nB>t2k}qWlpL5S)h$?>@oiqIM+@`dm6UV z8!t1(6z-YzCXniBB7x;2sHzD(u2gDcw)u1dU&tW05)~7IaIV5ysN|ZbPd`3iR$pJw z?fh7MzOB6-DkqejMq1X_U>)cm8kPn0SC`SIV`?~#bessKDK%A7R$i~zi$!@S?i;?O z+nWxoLmzn^Yj8Tb$@**cj_Yb;0ZC&?y}N%Qwh?6I=>ZSbp*u%}nV>D5gWXYLUbyk* zLDY{d1IGh#8fm+}_~n&JPWRmAPmkOc-EaL~u&5q?#2a7C?IIpkQx}l$Y zlEKGVm~>M*CgC05<1IjLRoWJZzG`_MUUA1O&DM!e7 zx$R3vJ54ux>IKjj8F$7ltfcXl1p`*Y^2lX9ZMY^N%7?NFzEuEJ2H~f8U*qZ5=11-~ z>~r#1Coj5Xwy-Mz)nC=hujCZ(9?Rx@mXw6~>UfvkI&a(nx^M%-=W=euo=V*M#G&=x z;m;jiH0C$cssOI5{GA$|$B(yLyEO!c{q-pdqP6(mFvq2ef|t z!Zv4qwm;%P{pLrE%{f?>RMn{7H62}V{ma1g zo(o-iL#sv=2|4mpFu0og3Wn{x4Nk)!U|FjK4S+C<4(6{bWz&9n_IU1@hwB0fpf>rD>nvqYT!!u`4Cjs8Az89u#VBa&WG30 z4urv`r&jRQUYKb;*NR}Km9hoyGL+4IyLj13;#;0Pw|VW&gP|4Z<@&K;E1WrOJQ)e+VS-+a`LvitoIFG<%7SDw~xNhIwATFJHiPrse5_ExU+O?)o zIZD3XULc=QGlPe2Z%|3Pd|;JC^678Q~jAC;lX!*m{kPY8N0Zaf{O%k zFiwg_>uUb}3-%g6`R33a>t+fKXK_@q*|ZiL``59g$jBW{G1g`_wVO4piaDa^1RU*{ z*lcX}(7A5kvO15+;P&c!EE=oVpE$@%uc2tk;C|)Qr`%X~@6Vd&%~E79}0pKokA;?p^=(r6D=1MEo}<9XqQtG@E_DJFw9v?!7r9=lk95 zG3pm#iWUhPoj6ee()N$5EAq{L8`q{y1*x$#wY&E)t}JAXZRPSy^jW+*;QEOpcR{QU zdZL=A-0wfTwePvQgGUAWIrL|(h(lr`PoeVo^6K~*2WaqXq$Vu-0x$7N$@+D%+k|dz znwx(Ha!#LNF`s_**S$-Sy7l@_slc<|yrk0Xftv=x6%G@6AytopgSB?I^<1>NcyS)! znJ{huKUU-nKm*v~-vggYpg5UljeaJ4S2shy5JQ_9kr<*}Ve7VNGgZ&dry$31liZ zb`ABnfU&_(>V@a$ou`Y3-zptL{fAQ~gvy7Z#$wh&>ji(hE%$>&tbr&jkE(3gZF;a_ zzgdwN3mLu(=Rz->T_U}xR(Ji{r;(A72?+_-;t~>BcyF2=PZAO=pxcDE_%=3L+X2sM zBpDp-oPhmVni1{<7#?`5u3fpO=H_f4UEeeqk=~4#^6`l_Vp~u)t5;T4t$STupZ#L0 zNBx~kds=(&ZNWOw_*yo@vjztFjK}5VzEYRRcsqAE<$H5QUxoJiOLQlJiP|yd9=eQIz}O5_0HvY4_0TXEnBM(!D>wlrmVvIoTUUV z>SbaDTWW;E_+QfkdTvYBdd|PeR^|1;8l0_V?9g1!b$Jua+t9SijtT?3LybC_n438mqP2v7HH!U?kEQPvli?qASgY*nIgoifOCFmYdi4XSk zW6;MJey)O;YemnQ{{5R(NVU`xr|Ms%&#=02To;YTlM$@a@siTy$xha>jD?jI1ckjQ z*aC34C^(@;sBf(Wll`TFxmpJZ`83f6jeZXw+M@ri+_AX=xy|horDWr}+P{NS>U;k9@k6z)b_88c2TUs-vp4h7q*bRcO3Oez8D&Ep2FGibiZ1rot+Tk&h=rWj+Ln z+2viQ1yyr`kXCB-9pq|V@7+pKQ*dn03UEHP&MuUM+k#B`<4TmM$EZZtj5i5y?|Ia3 z+r{*9xN$1-GA)3sap{BJ-& zyMS>R*P%t(eEgf*mqP`M7}o$ltSvgGi^b~Q7D1VaWBy6yF5j}snM5s`AbIH@JMxAu z6#Q0DrV;u|)R`&Zj$48dFCtVMDk(j_!585{`U#%tVfiTl?D}!^5m*jLhRi15Bn>FG^$ZYR&wbbdmbGTQ zZEZhn9q&Y&ZisSG>24(B9;Yc**8#3WufOi2EF4omJx?g+H&v4PDTYr;%>wFJ(^9d= z+B3u0d`ZihH-NRJul5Qr+snD=Ju^yh2Csz`um9xtfxsSIYK5;vP%Xu z1q>m|%Z)+NIqtP|9)5ghRQF|f_u6EtzIeT`wwAL&cL9}RaYO_|zp}EVPJ7MDW#w?u z8P|P-j+eASjTIOO62|dl{`XM-^Haxg+1`RvSdl{6;f11ivruB70^IDk${~tFauL!t zdo8v55a03^WTNwE$!=yPPB3HW{8SCBoeESSOfKV4sJ}NWX5a(mirCXL4dZ@o6rcj@5bFP4grwzJ^_lcuB89iH0XOtEf-`q2TVkOd7 z3d|r-XzbwNP_I^>2eX7(e@_MEP+Zao7FQb(Q@P)&=R4^c|OWs+9Z9tH=6Jv$Dt zdnVO_R5POWV4fg=fXHETaxw}Pag18YgJe_D9MCcd5JCBd%%W}6uUYGQ$Z^{Q6m@92 zuw|8Ps9=WNVGIG@!+c=%<9Nug$t36k6kovMx_e=|If0_H0C_m}`a6Om@Pll5 z3Z^4!07N1;0ZS_H41DK=iGcZ^SBu&^rYlkp+_ypyO-z3=~Q~y655H#AYWgDqbrK zOH(cM`r${?n^zxEP>||)aurwaQF#CvQLkCexU9#5`h~OOjX8&R!lOcJ?5lw5F*&(& zB;rJS96>Nld#35z#|?!c`P>*p8CI3t`@2r%SKt$&2PD>fbAvPqK+~a2@w%FuCE?^t zZJ4DK_GYmA$3o#2V5XaIVVf5P02;5`bl2Axaa;wJ^S+Rqxe7b5_=PZKZyEAm_@3)7 z_?i^ZZkXDyYuJqfEoD$#lSvbmg84=tV~#vY420}s$rS`*LNFhS&bO#I#BgX+Iz;E@ zuML9GAB+#E)G=gaz%fa|%B+w(+ zfHavv_Qck{NtC)d6cCb7MY*|z1TSFj#&M2XZ|m;Qe0noT|3$wKC_}?ISkFlMgX2Mv z5GKJqM45QzI!CaOV?J1bURQY$hMH!5tH{#ruBXN-kkeCj;U`sD?+`NFIJni=$VjX5@# zBnksQl$P&Q!sfc|V)VqwCHaZEju#QZO!4k|(JIlOA*HO<&qahV9YS$x%x;oFyGX8It}<%X6R^*^WA(~q zaz#XMMJ-q!amUuv9&wtn8_DL4l6q7q{`=e6l9~yAvC;VVO~6k2?J&z zh3P=B6uddVw)>mRGZXKBmB!lIQ`i9s+hzJ|qpH=pN4QXYB_bl#U1ODSARxld0G>~{D{=pt3Hx9M3LZ+&+k__f@PJvL=%4$rPx(*V1_7^g7T|?)AD`mPMEGCu# zk;7Lz+%pcSyf$FTXwR36xEa10hNN(9KXya#I|3k4t!pXyhiuL>qRnTv-j{>0oT8g| z{a{?iFG-LYixA)UriP#MK~yezfaDto;5{BIux)(e)W zTDEWxJHA6T-{#V`gK?!Tcy+GH_}_yPZcj3Qcg!8P(TF#!Ur+J~k9T*Idnsz61B3)R zN|eG~XGIZ3>Vw)L`_K|*76N6Xg4>B14~TB#F4f7iW5)!fxKT({g^z?FYv0JIJov!h ze{wu$UZU_Ck!lcnh&@%_f!qs8+%m2+1KUG%S$Xrtw6KT>Vsuo}497P(52k?{KE z_=2WGt;H4F>rtajOm3d5DK04?in87@)R{cu8;68wf9F6PQykruaUIO4FVGH`w^MKS ziqg#MK)b@^89>S7h<5w((g=opGlcKss#NSJk{d=z4hBUmY7q@$GX>}oeqJF+rL1Wj zA>sZt!@L@)14wklN>g2y-n@SKq3P`(@oG(U;alMiBH&~EX-iZ8A->Ag2#g>3Fcb}> zzLRm~va9gTz$Q&9o*e>Ohw?E5<2F&lBL_cC!xZlelY~OzayxNwu4$2{l=s0 zsbUAvK8Z$p?ghxpMyV?a*yzT6GK)zDNb56zx$j?RY}9{e0eIB5XWV@QKMnB=sqJKtSlqC!_w6C=Su7;y>StLewJ2?%PKFT&%?mn{HdA9#Qr z$MPDqbOU7Bvg%Tg$jLble-P0hmo~3UegWYeuIo2MG1MLgVt{{T4K#c1=r6wf21$5R z@Ek8Isz}-DNL^vXAyLbG>-UO#L1GNXt?JwuYevfPjlmGuuB%)p4t#Nx!R`So^i>(= zeM9fI1t5pfn~O-2jHgH5cO-bvqQ4pP>eO(ctk}2ts%`bsvaUFU9?a+X+WC0CNDP=K zl*%*d)}1JSYqcx+e`5>fdpvQe%>d4K`njAi!Chd4>z9)?)$cN%fyGLQFzWj0M7;ut z8LlRrwHRN3qHI)NgqD)Q{7J9`u9QA!48pCL1PmGdLXQIj1G9dVmzU?DV!V9$l5Ao@ zNjMLK76Gh`>-(Q7BGZiB1SqHglL5rxhYOwfG6*yZ;rAHn7xcDyv?73=`N6|e-SKR2 zpg_4uMiwqVf~{JLiV2S1=MizjqDT7H1&Kto2VD6W;8mkudk-?&2w$C^oZ@+cIT{Z$ zL@Oc-0to@I$bR6qh@^q&`H<_E`uNk(>Z;654|84-xDg{??E*AS(3hAY%Ou$Z!% zbN78s=_}{4YIij}>+I}=(uTy(A?$^)&Dzb&%ZqBL;o~9o>HjreGv;vc`@c;mg zT94J(VKi8z%ICp&)E$hmT?T>pFG$XP#JJy}F6k$|9>Dez+C#;5VyNFfA&t~Yj>{}z zFgN_o5j}wGc@DI~aaOhpkdp{^0HcSQW7Xonxlt|FGpa3W`|%@AD=XbvTtJ}z@wvD! zqm2l(zST*9YE$859sex%_gcFV4}9;3Z0(g5{E@d>+XF9_A$Tr`NJDKEY%kC;q+uo+ zqL;hxZ`0)G5wTQTcehPni*IU4NPcT)n;=K>}>ak4bOyDyrLzb9CDxK(8f zLY2h#MT5w$@kb8}MQQ~wukY=x2EU%39#9F63C@NFR9I)cy4U8wN9oN8h_Oh`d|#Du zn0suSw#D0}BwBJQe$f+ImD|@V6nA_AjH(St?0<@}LY0)nn#Uzo;Xk#FY~08iqr9T= z5giPvYN9Uib8~aI?8oM-chF#k&^3~33g`OJnr4wpgfb?#s<$?=B`%{6f#okGE|I_H zurPM>ZQHhuapm>A?~n(PHg*L=!S_}5^!W=_!4E|(!wuSm6GF}vb289Qfi4CM(GH{G z*49A(i@_ak+{>E>BMjdm{hnIt%(#y6dGvh$OOT4J51%5}wqK?TUmQW6A^L1HC0cyaPsq z&OLYUFe_K-kI)0xS55*LR3kE;6#veJ57Pi&eiK~uWIJU5|Aub)(KRgCwVauXLHcGUI9c6y}0tW3AThXnkGs941L*Z3b2mE7SSXQO^$cn z;)y$jjYq&bXR22io+X+3muQqKS&HiQ)>X$rB8gcaZSBj0Y&6U%IR%CIN)<|^+b8qZ zc~J53+8tugkYytwXk?Hgf^1Kxr5}>RLkujYA7vd0JYulWG6~<1kXpYy2!-9SzisPM za^gncbX-mBnQ^q?_!FVWG@AhB5HX)SIfm_Nt}Z0*OiYB0oc*PzAp;frUEyx~JxvTr zVuo}HsN4aM%qlb?+GN2@fWD!8Xov`QFbyp`H#BfCuEY+TDWcn`argzb7qKbKurL1Dhv+%=$wThH+NK1t3juy6N6aAY?7{Jy^2q8k2!APN5WIpJhwH1~*aJ!Rr+S zFrmE(Zr4Dezr=S<-6KkUmN#Ii!m5o-aaLuL=&~!n09LVSt6=&R8CO^zh*rwh8G1Kq5|Y zMn*Ujdmrk5N?B0W#sVw;wxik{$MtgYyNaI_+OuCw@s#!+gUy~~=Ss^&IP=&FEQO88U=mvwt!TLhB1uA!4N68|`YDglvJy;Bat#039Fb*%KK~fXL!F4(@;0q1&uHI{o=bWsDKZK@$SQ zuA|jzL_Y-me=u7IA!5L2`+h0m;CSm+qLCGa~e)`&G?(6w8JvpgB{@4f-ca4wwt_F>> z`|$(|Q35=0pKpZ1st7B%1^t+G zaypiM`Q3XpPM#!&8(51a0JULe80(5Y_QoRG$E84)e-UqFd#Lu-d?cq!S$)Tbd zr8DAU43e19%)tK)b`1BA+uCAh`gIh(Nt19F**>!JZ~8MkQrs(gL8{K+eRT69OSf zlnc9WD}c&p2Ltnniv$XY<)8^*2h|OQ>?J5ZkTmw3KaYq&^6CeKP>6JZQ`nbb4{s15 zZfv=vj);ih%ova*2{A;e$ZjX_PqLvEz7e_}6452^-=7C|BkmbIdb}y#nFOm)utwB{ z-nel3Zu-f&o*!>*e2Z~SKqUtPXHN~2-nx3c^0|6Z?j>9E;;QfY71>Bg(j5z_u87Up?f3142P1RVgT8>8lGL2 zZo-m~gknHKfj2^j+spfbPp`=7HA05J`164|5)i|L%rQ&^C>QMp^wJz@|Bz{%q+?=I z%>QJ$GjP_L7UWRK23QNhj7>z5dkO)EGYLoN{PTFS??~JA3al&{&s7_Dv8NSfv%#oA z#K$TBDYo2kq>?kMemyp~g;`{1{R)N5(a24A{0p)Tc-P<(-I=%!p|5 zF$)gE_$?9=5^sGMK8wO7fEzvT9@<{YbJ~Yz;rG(+M}nbSHCkp@L$6I&sdzTd=u(3c}r5)k5OP0!+l8N_;l*5qhg7e&CGx*Ze&F zVgqd`O5>w_Hm3PcVTD6_?*WR7>tce_@)_S2QpEESMeMyH5lI!BKf^8kN`;S!TrQ*u z0?Th4fUjl^kU&}w0Eucr<)K4|NC+AA4`!XZLo%upl3Yh2o<-@IEL^{v^r#6V?UF?# z9!iX3OJht|P$q0?7(~lV$9J-iJ%ytMAep0!_JCura^D}$Nnjw>C#0;KHMbVtjS{XB zdc6X52!#`X?(in;Di{U`Y(Rm;bZo%JYFtAx;$Wp22Su5+P-qdcw#E)?u=RE{vqo$t z%=ZWVLtzvkvB7T~f8M-=V^m>3F`^)H!5C3c$ienDvQwSWk4SQ4PY=KZ1_fvXRLFZ@ zS0uy;5z|jQpt3@|MMsGHDZ`+ru0!csoK z^sh7UP6l58eFO(0kn4Yy&tKnlbAidf-sOnpfAcc6ZC{our{Tt-O9d6j{XQE5I-CjS zVKM)onSbPO zatkn@Ajli2o!I`}LiEeO<_Oojdm{_qkisROw`1Wa>04C`C)=P#Hw!NuB|@QuiK1^U zJpS94nX+fNbwy&5V9A^~dh{rWdszc}2LHmVH}59Y2ek&Q-svK=0Si$L4UHL8;0tK` zSYE)3fGFQEbI@NHmb>d|XG2t!-aODQHJ>JP=acKq!q;^RlbgL>0MNbND$PPP6Hg;( z1-CT-!S!SlS5QEx+%xcS5e4N;5?{E8Crq+(wp1^+GpsBDZ{HH&4fKwpJKNQOu3j-iOv2-!7tD(J85uQM+d+F3e#HcO$#5R z=xodwYXyx9pkMQqDal31d6Sq300MTB-xOH6@YKld!k*hn8tp8EZ1jhRtRyrGsrJ#t z{e>sFneNXsZZ|&_Kig=P1~p zA5;edM|SH!@XA5DbI-=53m*}6<$47><6bL+{0RtI_x|0KyQK4s*J2ALl;mG(? znl@J(ZD#k8R`^vm6GxqC2- z#_PzI!GoXwyj+=@=&QSjaD%iU{ehBMdhUhFbL7;&?$mBwj|y%EIu8cE)7H=!KzP}0 zQ##1*KcL2h+=Xj#Gu=9B$LRdCsaR}PTj`O9zKKn&aOCFzWk`+*(q57V(aTkBE-buG zdiR4V+EA#oJpBCfw)BoQ_>S0IsrK(0eB^Jhutqg-OMbo&y$i3TG%I*COX}i~8)(qS zZRr>OAZ=Q?^RW}|AUYbSkLI5ldp8LyM;%oIWCd66-?M+=HEs{Wb%p);k!XN+O)SPQ z?hAjTyf}slgk)9|>V+eu_f?`zZU!~~nw2PeH*JAR;6jxG=1W0U@X`F|&=?g&6A?DShaitYxr+tyhsI=Ez3@FKj+Hy7T-UE({~p#U(YRr8 z!l5}CcMfC<0e5HI=MZGC$hIRwr6P~~erc^XATEk<m;FU^b;83z@t_GUp6Rc#7QV-CmWICq{z_< zP$Gzxmp}jg_l=R>jjhTW`xxmw)@jplAun;*DVw84^3>XDrPE0(jwE5*0B|iyqhmjz zsUcL$0E9pwgR22vLfHU;75DQ0{caTGhE9uk!o8orfVd1SSrRQZzNxqaig_wnV-U{u zg1i*{Oy&0%rcm@EpC7Iyc?B#CNK3N0s)1zd-BBN$JoA|BA;#_j-R?!wOPQ;mj+Xd^ z9QnC&q-Uz%-6ae79?|3M*LeJ`5&5x!IR|_@D{lfb}i3xi0W6d07bx zyV@(U`!3Kuz>DRYI|s;FD-gk*5t~8A%V6QwOP72F#I)o>3oMRX;no_dMH@=a1407@ zBK6TcqBGJ_0q!~?rL!;so2jBsdVKp177-&m*m1Q62Q z%}*60G3T&w1*SQ0@AqLVl>^){NDI&q$;p9$+}KhBZxh#nvIdch*jIqn&Yx5U?`<*NMtVc6Gf_;v8$m;bPV}mdj5H79O&B@VTvi#Tj$=W%Yb%I;zXpWy zz*3TuUxBVgM@kb~4<3qlAer^lrwM%_v!nXNt6Jsr*a(jjcA;l4iNatbH1r2jow4`D zD8AttPNEBkpEcIsI1h<=2QTjo$>G0Ae%3$sW1`I8 zUS9~{i^r`Fiv$mYP<314JH$c=aGQ{Ez=CW}(!)RDPfvrHw70ht^9oQ$aJ%1w2O2ij zDwgUDloAeRI&%!U+E?S$2L@`?YwRB;Y44c5)pe;fyL_GR>=lMnV~2wydjvAyBsC5m zG|WjTTK6g}EDS+#Ai?ayRTK)lTo>C>Db)5~`B+=qF#r(4{JgP@fL{FTelGq!9Y3YdU zAd-~qsl>JY03HgD6VcTV*qH8$KY<_tL)jww5BD8VTO9joU_Ig3>l+_9vOe~gj3)9{<*RuQ)y`!eL6j#88r0FDH|Ei*WKmaO!9 zqtfcvo8qAQM~-ulb9mGh+e#)!y9>I55Gm{m@0c6*`H zJ~kVRPy@9!3QEt9b;3JmeM|BR@Z1`=rNRe+{AhqvZ?LgG@gf45IK^-T0ZGq(Rs&Q; zv;!sx4&?lVhm-J!V80H-oFcYMwk$mV*>VSn%8LYFcN;-NB2onQm#V~2o1xSb3#4-blYo0TJ`^$p|Lh~Fv08l`lD0!) zFEbtBGdcM#+=DCzL`Yxf8qVmUUV>Edu}BdUrZ#MZcxe~k3$F1X)+ZctWtW@a5->(y zTF;=fh2Z2T*0(nV=%D--+@i-9q36+o<&J4RK}c3e2%95B?cL_snt)6Qpv!=t4(RJ0 zrZsyA24vf`J8FVw82pYv1RQX=LqNbh-Up~t3|-fm?#?Kis`a-Z3?+5hw-_;FA`fFpL0_GNnur79H};spfu}F9qEk$k%7zZRdi9(0LjVLsgg?awvrf`Z&{8c6=LYBV+XD+EA^KkYvQh3kA&(j za>4Fo-n*-r1IEA+4xTSFh z7LT<)jF_`>QysCVF!gwNd1H=I!5DLfG)>OOK}S&I&4c**38Fn(N7^pK9tLvG7Obn~ zJ(tqp$3xv~u*jpeG#NOaiEX|+^qepaea*L$umo~pvPH-+Lhe;6Zgph$tWDkc*OEDy zkgC}Xm#|bTUbo*)^)Y6?P@C|bSW@8GrPE7RxbG)t|G}Rc@6hwUjf#hJbz4b8F5sWX zely7WPB|ILw_fc2NgduDsl7}+!+B4P&*+V^O) zyP4|)sOc59sS*HcYvCP`GuQGbAZ4vxVC2%=lh`iLUDZ8#8#ZG-00({Q0I}9^lqPrD zR3G9tjX1(B^*nWIJUL?OuqWe*Npa#zqJv~ejd^Ne?M8Gn@E4U`>%xwoR*JOzB1a&UD0XZwz91IaBXf(jh;4V-OTW@{bG<<_T-7XfU-G zE5aF?ep`AgNxjU^l+Wi!yJIpCwEr*0&OEN?^n3r!*!LwZLYb5(Su0U7C=!Y! zM2boaDs3oA_BKgnSCr6ZEvcj|*|#^9HM_LPT1i@d&)dv=hWY;U>+yMf#*BLRTJHPY z=Umryt`jOBKp~}ZFUJ}SUO~BT9*%y8`bx&M$79a6%`}oi+2yM~77QRB!4^X&>h@Gb z0g6=mmHFNGrU3lF=V@nVuGs%LK+r2f6nlviKzfdGbD_rg(W>!3AVkWzgFx{>r^}Xe zfD4LRhzH3aiEKYoXPIu@2FyD49NiPj)ZmCOkc%3AzX|sN!P`z2b%3zIUjL;Gw)0-WZMT;cjzMAO+-U6DfEf^C&R^Q-{+F(RYAt#M@Edr!Gr3~;#Z-qV2wEO zj6>In&SQa$Xy;o-0~hXvx9_qM#gD~{H2!Md#af6hn#VNu=xpE;hAlXA?AS+`^Cb62 zRCh)zZ`rVboSkPBe$x>Wuk1$AcP?HV9YheXJ~=VnWMv1!S0Xzi6B%eA!e#V;GVU;> zSX1;9QFK&q&(+R0v7*)xY#R~1NHmk7Z>34s)v?2>WG&j;d~V_MPLdPeK$SVmwIdB_!6QTR-%)WU~-dS#P$@VJQc| z9vNN#79LP^^i=G5W;qX3SwB3wsbl5^*fHi>7g_4>y?yn( z`lIfTocug3i#rV^>WDn|krVNpyWxy`B7BtDs@!w-JTrJ-Arls27~v#{90I=Qx$ZVC zN(q2b?MJ1^OTTff8W3y+Bmc(j=8>(t=(nLBrvC$ToFAqSCD2wsDQ&gKo%IrKSuMBiCtR(+l(0=`EtdUn|ciDfl4{eWI> z$ck8P>RXP5#(AG*&!1Y*W4x@atmz)z<6dWY{=6I+$R#|<+&Hyrt8RT5MINHc(IRJGqDU{{5v7l6$u% zJ`UTz`wz<0;fc-SMC&nhLl0fI%Ga+&?vJQ_w^A8;BU3Z8`>FU;zb1_h3=G_m;jwJl zvkW&IC#S=uTy zvH-e!&rC3hrmX9eo@IOP_miIeU8o!4yziMNY#({a`t~2sPaMn0*#79LH<@%_t$JV~ z!-^L#Ui9_Sh!`Iq6dKyi8b!t(kQEn;;ptXFWCu^MOS+63j@u~l^Yy)S`En24&P`ga zT5V)UXJuxV4OCTA+kSfY&_N@6*j~plWzl`v)Mt1&yimzv9TA#Gzx0%JKg-edG}H6)VM{_woMT9X z#hAo0CV(YWQAF4Cg7fe%%XnntJ43Vc_RL_{i-jX(C*w{cvEhOH9T6usVAF? zSH=#XmRaeC3(GfcYAs2i`nhn}(!9q}(-{4SrL!&(`eJf(b6pLF4f}!sXMB3sUVbvo z$GAvO|3V}6%(Sz}4BE=5?w|x|%xlKjL`1IoI zj8`e}x?R2cMo!+XGbQaTqO172O^xSr&Ya*jH_3>Jj`sdiGDR|Hx#VH{Ig0X_w+1<_0_4O$v+c$e z8w&E$3$|$d{FY1#j@pcl{Q7&h=KJB(KTD5ZJWYfI9XdP!c$NqUG{UveLRGJSSKHPcl;r;u=b#))C z>jAcTWKLC0O~3 zgv{F7k(+9>zu zf8L8MOLw>~EAi#8Zn}+HaIv+Wo5UqO&hG><=w7}4n%+EVn>7FOg8q_`gGTP2Pk_L) z5zbcHT4C72P?_P~Su{xn=4eNvCjZOqNJ-gFBB@z)t8(DLfpOjj@f*z_Z(F}%!>-8J zZES38Bz5Q3wsI(Q6QuCgZ&RoTQDGgLbKglTu7~org+g`Ww2C^krO&K1rwG?+sg~p( z536Qf3fa6_HdWNXEq!W{TX=`iBnZMh*kIc{aH~Sik-ECZOJ+MoAr+MOyUy!1yd4jw zAOCGd^D*x3?wxyCOfoj^oD(Cr_vW!Tfz!tLj?~lCoN}aWpet|TIH_#eriC2%=8>zZ^?&h?is81sV^(pVxqSrwUdI@m8(}LZdlo};z{Po((t=* z_U%VRH}aa|?ACCEMgFm82M_1mH?j;q!H)|G_V^r?6JRl(8s>Sxmfo854D| z<%%MQ5tr(M@V$`uE?jsp)NI;Qsxh@mN{LGxh7BERUv^X_aeA3}^j$xMg@j0_hWFAd z+GE_;-NQp+gvS9_qOie`A;&L1HZuETW^$oe!0lgLG`=Ytve{x+-p!jgAI!n0rMDG5 z*Jhd%l%SLS(^Gqx_yddv=@jyZo*E z{5NIK%1c^=m>VaUmj#^roM}{6b>nT(I%^lHNz;=H>uip#be-0=tZ{ANfH{p)pFvXm zO4cSxocP^*rOLFCy4Gpt%$cf6Xp{$9$r)5Uv^V!_OQ$(_=afsW`ls-VPgH&S@TWO(hQ@;n5mZKl={pQ7TJJ zE_?TGfSE3B?@v0Xwrbw|%3YfT^A&!6hYlW8@V`#rH>ywwD=7<@udXK&MEI`qEz<+sg^O9k>hR$+0}u6^e95{Q8_}r3Trb?pl!Woy6ka2Z3#oI$!@^col}40m zQdz}K-+_;drM~;!%a;#PC}&lZ>`y8N(b&3W%f307Ot0Q^)ysI*I(z$ft)2!yb}8=| zN;;_eW`V6m=XD^uLAN9oD8;3u$~7zLL6KHIY3r$w_*NrkLzU2qP8PN z1EjzA@Zks*6?=G?mYesyf10yr^Lg zE0tZlb}fk*x1u0PThkj9O;uTWY{o!e#hlWD#4`uRcLioryWa=XaMyxrtQ}+x?u*2r zZNRY>+)2Vp?gS=MwtIJH(~a~8Q$`aE%84ShB2SqzMcdJ;3WW>`gU}Hx{=IT?4^4Bw zStd)O9Tg}RsWK{9#)2G`OF(XEQ3xbrM za!J20cFAj8Kf$ZxrG2{_@WD~PH-MfLyY> z`g3pMsGDECd>QBGvtsh(8yurC^{JN0dvO4MUx_F3W`{3r*7R--1lBE82{G2T#;kkC zRoiy#C|j(nGi1mRUENumr;dLvUd=1> zy5OLHrQYHGsDExctxeJ(?ZLa2t7*J9PdYDF+rHQdEhe-a|Jy!&p6&^!RiLjBcVPp< zb(g+e=aeI8)T)d)4mFYXJ~T`&WY(`y21Tx8w28w)&v;z*O`mQcZi&v1Vfkc@2qi~7 z^c*s1keQdAsYJRm^*kF@Ss5Yn+2sd?$>pI|;}N=~WG_1y9&Sdms;M}w^MRJzU%h&T zdn!rKjduZcRnB&9!mPung6)q%?)IH4Li0mzZHvn8Qx@yKY*{!s3-jsPx3?$>Vx2P< z3Q}6-UYvNh|9t7>@r(QQGtP)1f<{FAalH?0-CwEOfQD4#^6-UGoFq)8D=V_`EmM`w za!$93jJ$HzZEwM+e6!dw0Uw`_DL#3t^4&Yp7vd)G*`7KjW5<>)TXxmu=Kh{TM@;b| zg2urc1#VD<38o3T?l0DSYao+e{7%z6@&wy)nBHcISe>8s23w_Ys8Cf2_!M?c^J_Q2 z3lbwrwq;Z@F5WAecKuvFJqV>4+B!`Un;-u#Po6A0^)2WhEx;49hMCIcZO^#xYnnG3<|E#o#5I(A?4MwbSQl6uP<%>(`eRQC&Mqa{U(oHzP{? zykW=$45NSl{dX@>jA=BsOSPnD=~?-_kBCBN>pYxJkE5p5v(roCckbow(AZ=5&ic3C zev7kP2wHJw*@u{&5zWVt{x9u@q2(Wv3Q-?!kZX}{RSXtF^GnPK&xPEbna|>FMpRd* zySI}GqrOeSj%ldR&zbz{!W=5rxN4rs?vvII$Kl#H6|n%9^jO=k#B4W%Jf>%qK7W4a z@U%V#%Q8=&-c+PCYNeA^C?={qeB%8;$o>%uRPCKhR{hEs_sz^xC^Bgyn_Y|GcS@}e3GO>1RdS_+7 zCK78ZR`ln$IQqqVHp>IZ^OS))+oSZ$=<>PSj?XTZmqvGO}C0(8hf`e+RN_L)? z&e}kUBd7BEb?YWWMbHq@pS@&i`jk@`Y?E%uQB-6Q=<7CY5Q7fkKmm8#cIZ$^?##(e zBKwM^sW`$zg>H8IHPAB1>n}f65Rm@AC&3@`baY3K?AU#%p;v!p<@0--ufV_K2R|$0 zh-EUZbJ~%Qcjfll7YgjuKRt8bAIi$gh84t&djWPJltvW?D~p$NAQ1(3xZ4GB)b;bV zsDpNjt$#Z#Em{jmndWFAUY4Y_V*k#(s;hDg_572AE`Tx zKzl{~S~|1n23$&TN708M_8Grgunr8PV-<-lff@y3L68n4!_nuL{i}KBfecXLjimXb z(IFw-U38McGyFMj60>zQ&dvkt=9p!3PzK}Ii(1Bat zE&zx6@cj8c<0DPg$iFugO*c1(AJ&joAT!U~xVS zeWadVh^gA>X{Y9SZ8`tHp>022wrv*asX(~Bobk3I@6q1>7NUhQS$(pqSd%>-7<%15 z$y;QGT;4ik*{v}#V%(v;-oc$)w<@Q9e=h7jUi!E-Ha5mp7qXeEzBQTG;w;NyKgp!q;;Z}Ie9N^N(;#n!Wc+n!5Q#nRUdaRuf?EZ4@i#~w0LI4N!Mw&BVJm*MbA32Ws+ad%-q}n!fm%U)hXn##+u%xcjiNW zwX9iz(>VzOqc$BD#&9V3!}-Qdf}l_YIT|x2@I|p{>?msl8=;}?i&fp+KCoD$9_;rz zTWZ^lG~vhF{QLh-YAt>+wJOSSOlNedoE|;8cmKwPcKtp#$2XnpM>5;lI@LVk8gIIT znX30tKk{>kUTbS>_GL~^PJFx_^3@J*i`pDNewy7RLk2Ayh&2gj;&jt_WOFI zv<0!X|5886g18Aea-)@1R1RE}WYB=Ual?jNSbUVlSuKf}oq`reVYvg9s%Doz2gXGn z&4R;g)+{&Z#3I@n3=P*62p<@sJnR~aSK4;+ZBZXUu7@$PQUqpS4!OJ)2Abty~Fkd zy3`+br)RfrRfLco+b&BaO95xild%S9)1dZ4gGB4PO+U+aXAMy=u>%+Xuj0{+zO_Q7ml|DW>)DXDnf5hIB0tXf~+k{Ki^G{o&v z3rMz1)>a4$Y!L0iU~lotnDnL>xE8#Ha)pA~xNe>P^jsb+eTF3AFKpuYro;~IjAk5} z`wh-_Hh6hK3;0k_-R&=ih~zPSRs7BZ7jGJCg66bg$SKQuNO`*p3x~oj zWwWj?_42Bx15uFUyLW4N-{ipL#+{d6c<|r>t(1kYjbZ87GWSlddPk8T`!uKUu-qi} zrQ^+A4$F6#*T$`#ws^(=rU3p}Wq%H#@p$CQ+G8&q&3cS7lfB# z!cgKr;r!ZZCf9sEX3+W1_Ni^We|=!@-unp5z5|6(iG_Of`j~-zl$2uGk;bWK{+mHVt0Z z*Rn(G++P+_dkcYCytbcR^7Kh@F~Q_J%;YZpcDfXj;2yhUFM8kz7l{_|!RyBmF+|Zf zFJ8=lR0-(R!22$6x#xITdu zfaqPEiLNGn`%hzO@~ZVPSg~_s#Bu|5;Oj?os&*Pq#lymwc8nbsj zvnhY`ys~o1*x`PD-ziEk7c!hMp@&D$mBcQ@6rbVs7|d8*R)@2f+Vv2l&dsT$$hf%> z(m^itSza~)c_>ve@_x!dgUFjb6W$uNYL=L0m6|?m)-{r{s>O*pG`kqQD#t$H3~L|4 zJa}NQ>>UrZ%ZIK1BA)M^58tm$Ysfy+JFDt?#Kly{BO#(UG|$R+L+w|$*>k-5>*+ma z;cf|RmUk*A-9G&0EsZFX=~*p@Cp%xW@A_Jd?4-1!^6H8H3&aKmEbjo&lVXI>#&Vz% zfB~IoY`p2}q2$LKFu0{4q@s@{7sKjmIY=|C7yP8~?4k*Q8h8lOO9J<{cEa49qlG~% zO@vln9Jo2AVP4CYiIK4aI^?+CKdzOMlG61ScV40P4cWA5`N3I8qt~r#e(SU4pJT?H zW1)bvynOZQHrY2_>Lh~nQ;F6Yf*uYR&QH%|ex8%V`3jxoj)4eqg5%Q#fSXm}?G450 z0~&(z{~pjH*Y&Now%^A;UKq`+dk9y}#iMcX@bEC4$r=~d_!>RiNUgrRHc<2NA4=H@oq?o#{2LLvg^ zQ-Aq?d*j9Xn!J>}t=M@QkOB3om1?KeC$4O3HNM3d`O*Go3UqSG8mO

e2`C)0g}r z+*q>mgQV3)ju_EjspX&D9bPqymr=KPaKa&^pd9c?akPJmz2Z+lA|*9g99BFyuL=&h zV8`F4Zg^NLkS0LOUAjx-O3iVfK{^~2_A^)^B{jYl$0F|#u=JXm8p~1bS2GVpTwpC+ zn=t>ABnS@yG@aA_dy&eTnoFSRv#LcM{B5w*wKR_*gOej_t*Uz z&t|>wI}gkeQ#hkKHQSe>F-Y(k5aGOh(No*m+F(~Br0sS)4tSXUG z5{;G-9bbBG1tY-^PN94Ehe(EsD`P;U$)RKV;%u&IJNJ?#=OH66O;zdU!e>ui?e4w)%P9zQwumh{AW15wR7}-UwtBJ zWv_|9E<%R_VQfWaEk4e2$ge*rl~62f;b|)sf4kvfmdk$g#O?JNcjd0K}&( z5+3tZY^i&HUmZ4mj@~by%)bl>`LUUQ{?9!ezfZU;UiPtLcOLcs`EU4h$|aUOdVc%L z*8lmNqKp5zF)1mX&HwkqFaKILBT@<@aQymNd6)kC45e&e{rAqKjxGI9mC8||>$m8a zsPe|t@X#fzMUMSu{+@JtwjR2NV?%$b@mAk`RB&YBkDGbZ?q?5%A6N81_m^)L|7~&4 z|Gb|6@7p|?;j{W~{=IuA_wCEGG7EqcOIPgh>y0no5e7Mk*)bB3>d)!9l_yCmvzp`pcI|{0W1>*mTy@y|5P_ z&PQYHaro=C=+~VmC3PyXeW%bym`!rIBGdWXRgrxh`2f2V^E1hEXX|zR^(T(4a`3SALKp+6KcjX(zX%}*;qk10 zgDS|zBH7os=g7;Qh;61jMRV~ zoIexw844IjYAzen=GP1OI3PW}nY_S%fJn8=Wyw={Dpz}qBS#~*K?(&5TMuOgr07j1 zKy|>WJ*z2<35LG17{qEF#IuM zB%o=Eu`$Wo#uyDx4-aZv)XEFX{?{)2_hsf^yPM}^XlQ60s%fJ^r+Kk}AD|wEBz!mlrbxt8F^V$>B7($l<(vg|LK0`&3X)y&ZsPT=hrx`R|Rb{(P`~`_QMbYdSiX zw_6~kaDyIQuwwFHCT~FFO-elrrmYY*{_4M;96x?~-`xJqnu&h;!jsf2Vv@Ut>?M0r z!_QS!-K?_^xzn`Q?bfe3iqy66yQ2mt6}sS9y2wB-WnPX|f_eXKm+g^vQJ_azg@uON zNB-+4^W!(!{*kcCwu)BZ#Kc7NWHLf5*te}&dZVkNqM&jl2?YfOr%&rTy!!X9#Gh7w zj!Wwl`kn^o+vQmI9+=hjOQJ;*noW~bL4ufU_|Fo4Gr?I&p4NDTPj?^oC?-YQjxhv%X_bg22&!6&9BS`dTGlVMl?@9!{7 zRFt1$W`-tnyVWY145Hfi*-j7HI2Wu4y-oW5_maf7=lC~d6>L3v)C~oBG~Z4Ry&Q-1 zf%z9NI;C6vRZaYKNxNqzLGR5w(=WXM6iPMn3LC^ft{Ue)YP|Iqe)>-F$G^VY=Ins< z0v3$;ZbE|jB<_3q(Emh@ew|FJ^GeB%6Sh%r9J24aLL2zer3@78|6ceQai1uzt&;Eq zSTn}H1Wio(#s40zTdc+XdA{9Tuod0P)`_p*l$Wcg|DTikPoD%|+bR~L`6N>3sY8R# zpx#K>R<$_kzo*GAbAo(yv}*bR%kAZ_>&n{1Mnvql|3$${N~0*CtRMgl)klP^*>R~a z{?F-sLWB28eufOlWRzsA=iv=Zq=@kT&uW%>JUywC&sTH-R_4pMSj+=AG@m5)ipsB# z`LAU{O}5pF!J+1ZH{GCYIj{}UP4q8fM}F$sT5dr>UcO&?R7}hf9&*`EA0XV|trLI! z$Uj$1_J{tV!fHO)gaLK7Ks)>vpRJzhYq!q1jxhRkEdKVgh`Cii%3V z9Y#7H6<5aM{saFU8dNF@J zwKcs3>+9moT~fDN4hou{lu?znDOh!z5)M`9Ht7baphho^2>V+Lg4<9ZS zNkf5)latf>wlYySetwBlOPsV6CJX@^Jnp0QVBdoWvn03YxVR+E_zVjfRKmcBVfUxb#>s`j{!dfn z6Vu-OHq|n!CU6?a11`4{T(n1z4xm6cDH*bHeEd$%>X>#+zDSz&p95^Fzxbgsot69a zsZPP1#2#2Ic>R#e9QeSu2P~1dA<;bgpCVFfs%cbUpd>FZPY63RMH?B~*J%U7on4=u zO?6DR7}HrW=jMssuK)ZzcmvnMhYkj9I!`AtDKd{koXm9vmE8 zHTMhjbpLI?WV5U^4F@~hG|G0$rTd=eh!u}PZntkgG)v_I#9j?}9<{CS5nN8^63t{n z{ac(u_>C>l0 zn_Eg<>OZMjJedmx_{^Z~d>DQR-uO!JG}<1x>rIOl0!*sVI0%o6AplSW!lXZcA+3p9 zuF(l%As`l@Ma=C=G;|I5mKX%?;c+5iy39Rj<@zsXB!+X+UA$3*k8@o?KNFE_ewpnr zS0}Y^kA|J7w5u4&i?O%X$Csp5-@bom!ix_H5rm0suorMRRP7(2z`RmKw1YnmgpZ<} zOR`XJm+-Snn-A}|(5+JH;HJ%+&%%Mi7CJt!=11rdq>F|W7c^-JM;r`wfy>Da4wUJ% z2%d&1=l23^TwB+X6`BgaI->ipS1Q$hTHhZq29m~ft4b2>(5yvV8PuShsOClD%!gBf zB1TD>7QX?&pN_})_;?fq_cG}6W9)~%e?1Q8uh6AS|mWdJ^#tk zrCO>dH;V_OZLI$$rc%)VxA=S|$u@}!0z0olsG4)<_U{v4c_~p{DevzhBbns&3!F_} zJi}64JUIc&mSi)G{QQu_$^PBq%xTk5($OEu*q6IqZ~lDp?<1qHpecZTB#eOJCn$F- zu*!M$YC8XoNsKVvu>N%2%+~9BO%7&j%NBPQQEhE4fW*8kul~b^-9sUD`}QDR-P4dU zG;6#BAQPmr`!R^lJ-Ds`xC#B+%=MtoJkSqE; zHQJE7N=rv>-3k!Wt7p%Zt5%7*ev~;}(w#eZ$V~cmZh7oChvl|uvmnDz{V;;TgN3-r zvHut+r&2Twvok#$7PX4Fys1kc64|E7L-h4m0%2QTZ5IEra_!FA*8e_;e$t2zzF{rI zA)!BA3|9b97Dff|4s*+Jv8S^eX2|i8{1ajoy;h^T5s0v*%e<7x<>LmsO7G{Zg0i}2OnB>v#OC9An(6W-ptQ)&&Q9neig}awb8>Q~v=)PyP#FkYWpIgA3;WZLhyg+nT zJE_J*@pywtA-p;B;7ETX{y4I#ipnc3MPqnubrC-fJ9cEvTY z35|~4cS-kH<*BW3la46F{jmNA^)!cI`kgT{?APe-SYxb!0SR zR@}lbWJ9Q)e#m36a$T_Si=%=`2Up?ZL-x0@W)Pz_P$QIXE!Bw|dX4D;PtSbA{3*1- zi>S|1?ASx+M%NxApfr;?h>(~MsjMO8hC2+0eE>2q*_es04e7vm5EfJlRvRfpW|l#{{1K3`L%t}bxsd?&4rGRa*B%nbQq#X+l+tN)sy0r z;YR{^)i4H+9zWKonfufAul8`|yE(a{lOF?c%mbnCKHSSR8 z`0)Pyoq1Ip)mit=b__mu!x&-0-O-vO;ggB|2Hzt3Z^k+w8PaH|d>SGRzLM0B(AF;e zI2i06MrTJ%J37s?pdvY0L7`-2WMrCJgGX`7mLYNE9Ey+equzc%wJmWQIdv4=RH-z% z9?#`FY#W2ofzi@Q)QI6BXU#gub?z*t0F(Eq_U%i4?TWLtzWy0nfIJ+2&K_3pgzDYO z_yJ+Wf;))6zdt95dbCNZW%lXQ6!#wpzowHX*K_t%zZ*l-M03xY5{sAuNqNa0lO{<1 zO+Q*(JsspKs)sbQrkEcr+`D?RCv43#yTpd{z|tANf6B&iDo#@(GpO+jQY1K9;>saR)X0_Iyx~o8 z4}8sNXc8KlR4Z*tUZh}~cmG_s^h@W|rQd0!clm*)p+q50M1G!>21IJpykRt>z|GI@ z9dCqJG%bV`u8BV+$h*qnkr!W}76g1M&H|v}+NZR0<}}&_8&+O~WhWK}J*9P;)3!z) zZsT3S2UUOhGE8;BL@kAzs0R;NGPmO+9b8eTjTV8O(cxY|z~q*8D`6JF0rN$#)2-3MzbpvjR#KI z2v<~6GS3SaTCcf7eCB%*fLVHZ!({^^kJoO#*gR8r>o3gTn{}wa*s&dAWi>4m%@fGM zj8g~BI+pit?ll~3LY<1!rk5pbUV7iN_2~h;72ad-th9wU6{Hn}G%K$9<41SttZ3tS ziQ)M1!2>a0x$@CjvH-4(qlRUmt#+5;6-J%nzgAU+hKCP#A>lwyNFvH^@Y=pLG7@b| zLQ@UJR8Wzgce$2l$z(fm{bYTTY0hIhGx1sAjqC)Ksf>>27Og7-~r zJ|@2?Yk!93%MEP{v-YiT-7no`QSp7N>Qk19miY;%LuM`Ml5l#zvQg*Xx`e(vG3XDK zF9BP=e+XZAYu(iwTPAP#`hASe&98eZMn1c-N2Sk~ofR&btQJw}QG~PpieewqWx{Q~ zrnbQOL}-SID{MUB#SQ}kn=8g&ih&|%8~)hXQ@HrE(&4{mdfNSc zuou2!$2!B__H0HXL)InNs-({cHYIXn?~Lq?hc*$G&rtl+T$wagSe*f-CU;9HriS8M zWM+S0+Anh4*s0rx2&*J9Lh?!-Ja{d3M*B^&?_$x2f$zMa6k$5Jw7II?C!v{^kufUT zt>yfgg?D+#eB=Sbj2>UtOU34CSKe{1D#+J`in(o#pSS1kVFYBvMnyE(*pv)@l*b+s zvugr33iFrKuVm%sx}UQPH_(CfzcQ|q{>Qu}8O5^C(zfWhEUFDH@5aE-_TA0*&$6;o zSW&`9k94>e)mAurKg9q0FB=EvbO(s~BO*r|mtIMxk@_D?n1#d{C2Q+*n zP?3#S6yBsLbI_1aZ?qPt+JQ*Zk$B3@NpqT3*sjtNcYS2N+>lU*w-~iUXotw-dE-8s zoL1F*yO1QkyDBlLsuE7Lx!;RFC|5B4V(j{BR9a$a93yNFj1_ibOf8epNJo4&iVZWJ0J~FqP`gv#1uyslovKW`JbN|`<2T69akSni~oFM$mNR$^afA5sunSG=a=w8ihV0mnc6km-b(8(@QlDGD2ZB@tcJS#z`!7ujMiXH1!uT2R(=-7 zHQfDz5u;_bm$x$-bxTGufj1`7nKNH*eP?o>;!fExR`)YLw%x$fw%Geb>*q&naev2e z{4J>1GJuT4Q~3gGb15sWm16MRKh>i5vK0fXlNNS}Pwo8eWNbsqHG_NyY^4IL=^>rr z9Fym!PZc4|KhvT^uG!yi7 zZ;v9E?jQ^?mE0fUb$-|U&?q#gVQJ?(5qg$|Ck)|a%lIHy#E8s z{&u^YD(Vree0M%qxj)x)itQ@O!#20(?(I0TbYEW1b*cxMR|*p`GXkFtd{&K$T3}OC z1BU3aLVvFy?AgB4yC>YW+`oPy+*&%@e1DL`Q4m^W#dUig&vcz@D9^D}) z@E*BCv20k^f7v7FLoJHpTWA5o{UL=H;@%Rk2O=ZwVeqGN(Kl zHh^g#46Qug@o#73EiHk56qhtrJfK|AJjPJlDyym@7c9b_$A#}tQn875=-Sn$*-#&V zXe{R@+pnU?;CS1#bSorcpJSsq#B24E3+VKdpQQvY{4!Dum7LM5YsZbv?%Nw+8ZG@n zty|k(%nu5zW)}`PrdU~|py#vLyl%v&i_*<1g#Vj)$;L;MY@;m5p!j72gYIyb@O&G`PXA}da zL#<1%JSSq8J}vj3!loq7>30{^ZcJ3lTb^+Y2h)MHzbS#KYlYq2MYTkt9hzX}3K3)$ zDIZK}`WD;NCWW%GVaTnIxlP}5Bl1bXVPGyjvn=FMw=5E#d-9H_8NAR(sNsZD3&(@i!l1}>06E`e4m$xHVf?Z2|?u68F_YAz^mC* zK4_H|*~7)RqJdN+ypH782{%iTvR%Kf5itKa5ETCcAg~INjrwO?dd%H)# zW%9cPalw(;qtb~)-*jZz0Zw8a(oS-xH-kFDqLKy(-67eFKmL*8Lyp@`c>d8{w;nf9 zl_7dNHj%wk7-o(=PQ()yl^i^bz+`6kY)eZqFO23uAr+U@INBfzWukdEdHr4>;Ot^B zvFjX*m^McRtXqVGjA%0kR*KiIVe?vgPpsiJsf#Q?3;?_0i?co>#R;zWF{cI?-u`S7 zdCDvpUmkc9UXGSq->kv{aUjl|wRL|(+{P_HPbOW{Z`I3ds_iQNOg`prK5&`=xacqj z4_&F_sAW$$T8`3rq*o%wb-WClF_COZ%=RK~pB^jhDDiA6hb(w=q1m!O@XhXtmiDey zy_;lBeqh8kU0Q^WC5@xxmYel~A$+#-!#m=L9Fd=wb_4U2--itb?3!qz_J(t%=jq?x zL78FHwf$ndF_p@Luf6917!HhD#atskX8+hvhekIzuNl;i*DaLK70XAz2b zQek_0i&3{h9Ag*<;50#4sSAg_k`l|q{3YMR7x{Y`PlUeI5|)wNY2{_k&Sg`WR77h1 z;Z)@3$arl4LOtXsSam9U#Lz|~^o3x90QaIU1XK}YNJTGEVE2po;=A)m0?RIxudKs< zS0siFVzzKDV_gBnmuVuJ)W-9dV}NK7!~SW;ye-`s_GzE+iOwmF3n>TUoqvihG%_ZB z(;_$@F$VehI4yEp&Vb9GS4K}FR+-!1@gcZS{!Iq?P*zJJHi>i*vhD6fH8B*5tDFCP z557Ysq&IzRT3de6{5zg?&ai)z$9Kxi3SSwkmA{wg6Id-?ct)V)%Ibyvx+Sr7Pv~?w zid$)>%CT6&qCe?fba)Q2rB4Xw@BG)h8?T!Gq4#MmkH4=&BWMS$7sx&@kFw{)53I&z z?ZDy&g(=S$9^$In>W^@r{{6Jk9DQ$?0#UYf9n?HMB(LAnwsV#BK6#()6Yot0s>GmL z(xU~jRE4k6jCIm4;Po-y_c-Q+*?Uz$;2BJ|l=~H981t%+%MF+{n9Pj*Q|Xh$aiKnV z=mT~va(Ur3k})jm>pj39GTPf>q$<%z*=z@5aW++t>lXVBYN}?qQ^6?W03F?28Al*f z9P|kW^^6}#U75to7QdU<7ac3AGEyr?+QcF@LQIH4%;{*EhH?5FrwmX*|C`$P-}&5Z z0=@wdsyVpZwe5{i*c5?wWH*$~$SluXUvrols(InVD`zZtxcA4tTWv6(LI9_I?P8-T z%qYBZ^=e|-z|~&TUlqe6n4_yWtJBKdQPF5yKH~Dbd9Df_HO{0ZDJr4I$vPSF+5d!a z_*Gpr=9+r{XU@YsGOzK9+z3a}D$+pG-x$JWR1{F1Y@?c)Z_Vr>s^k@@6{DE3#W0KEO_qd zOK4e!nbCV4i;QIAi%3#Qv^un}Z}=1*u#$PmKG|bm=VFVJSI1WBW@lB^ivEcD3rdZh zPrKC;{kr+Z3=Hg_}Xv=xHG?RVsIA?%)&sgp@@{vgn zt7-B}@A%Z=q83q^*TSXO#4hIdA;n%9hqyjHGs0c%6Ghk)4CZG9*F|gCJRbV-=oJEt zD7cDm4d#%!@{)A%<@e{tbVtITcbOfY5a}|E0z>{@9KN{2hIyiHjNbE+Njd75#)X$6 z6#Q#OK$=q~AWDlO(oUu8AG@7duP$K`Ke!k725drD-sX)X)tz+UZ;pGl0?Gc}qA4M# zHkBwApYiKt{fSPij`cobx}VAT7Vn!F`@ZGLlncqPiI^QzU|}=2PQ%!Cru|ZaLz{t> z7MV^Ol1p7iZ0c*JFmxB}O5cjRGh{NW->^uU-4^pVyB_UP+5gmuu6`p%OC2~Yrnw%D z-yCfB9Ah!XS-DJBO{%;6xfO3%459nI)0Dj<(?1`7;l3OKFG6$+j5xcHsLILz>dH$V z(yN%knF5i<@cX#QICi08yDV>zj$HZdUlI&!sWbt*mxEZx32a`LQVl@Cz@$n}Oq)kfFHad{0_g z6>rYAJOchhun$RjMm8$hATkKD(1>cr%xdi1YqZIyNoCrM4>byNEr$(dcO^U}p;MVR z-2H9g0UOpq;574T;LU<`)NM(mAU!%6QH_IW-`eim`-JPCfM<%R=AbZYod0-6T7w~5 zUwYZFz)6vP8x@AkzC{v{boS2y{rYY4ae_CV(ZP`Zq2@=76($|jY2mitWG?f`W?0*w zol6rALAOr@VyKXRZ&+r@?8~~{R_~) z$>^m$$jR-O5-Gr;I_Nij2x#)NKh6mu;`mm*?`{&=>@eA=&+Ck8^W`p&dbz1j(nxy_yC9##!1qh5j?r8-URDffBjP0Rkh^z4p$6ALd5|47}uc>sp(D(*Q~lY)z8q}@)e zcdy>w2RN%)kk<)n8p91ArU~Sv&$}L#YX>k|gaj-kKFn#wlj6pVF>RlYl~myhe0HvP zCMSH0qDAg9e;YEbZmy~^zx$FU=Six>4H`WzNJ|>Z9PBU!nc2cMxX&Pl5cNDg%#jWy z^Ia1SfnXco1~jUj@W&)*yeyNGy6#L8gE>ICz8ZUGGeViE{L<@Ke=` z((=8&9(K~G9{)Wv%g$9>y`Y&&L~}as6lCRCy`F_5h*TL83JF6XW!P^uK^IIjr0t zr5@xHODQ|J{}-Acw-bk*jnfL}3$Ops%}IT&7Q7G!xkai}Owfr6v*Ggino=}lpH5eK z)i<1ns%HZ!=vF;{xk*4WDe+B_(a|#UwIM5S9-kmAjRhifOT%&^>1L$v9L|w>2!2;WcrxDWo&;|hq$f1Y%Dy&e^h(KAgP%)pVWTDbYG(Dy5)wnaZ$x9|HbDlY1Ahq_PPz zqj(piQLog|D3k0Nd4us&giV!OI;6-~gsca9$Qq@y)RZ0P?il7i;k!Zv+dE%oreTqQ zo~?810S}e$-x3{2U`sW&o=v$Fjm?X&5D}wyYwKwYJW{@ekO74MpIHBXz0H`G-#@JO0(SLN8asP_}l+o+uFL-2=8hpS)7|l z9@V{8=RGO4+~vhVi@(&e{4N{l-0kkTXDPDj@kNfTPP*hjH;o3gVP4mPWs^eW(;>bqre4*c>R)qWFbI#fp5)`a0_Bx^cGH3@C;5#FI|W@{6xo zv>srxD2l(yHVGgfpM1t;b==6-d3q%E!JQhYA|rLE{0XSRB93g_RKHZ8}4ql(!o zNt<2xX*h9vWd}+ov4hi8N84opC;W)^(8kOuxN@bAvF=^F%Xe5mmPH|uy{?NFvXhw@ zV)%SN(ulsgBMN-{ssq+-S!jtGB7U*0IUq&{i(EO;XbPz$qLP^^<&!@ zCimYS5%FTkkIHJ_K@jsgN0-$G_PiMe{+ilv5GYkdK1ct!P6laPr%8N*o*bJ$Zl#|$ zFv-THp-E5ZKoP_0+vWq%8W4raIw*=sjqG0^20PO&+pFS4ewADQW{^fV@i?IL1&l?} z({@6u4hm7Ru{Kj0){hn0tF3Jn`4A$gvC7wbG<=C|3bm6YQ^v&BzgD9vv3k899TsK` zTJQa@F%>Q%bl?AhBKZFk%H?1Zfb=?Q5_`7-&??AgM&c;>D z_1nOYfytBR0lxd4NwpTI;W1LB8UR$)_s)zi#^JuA_R{!vjYur}o|bc^j3=NfSBRsT zr}umd<#daI6KlYqZ-Em=h&(cE_*3~=VknCAp6+*7=k+TSUKrZmWwYij;^9_fZQ7Gj z9nZHuILpDqug>(2S%Nri!uZn^8#4;OaQ{wp-*DSqZM$Ir1DEXzDc3FurFqjr;q?tVP*mScKxB_Ck~8)LFB3tZ_3#-Gp&&zY~o> zWfTtvM0pv(OABB%J*_4HR6r?n$D&MBo0Uv)JL@dM36E9z>~Yjl?Qb|C1)0Jq@v|eY z8+^XfheRzb1v6WnM_cyn*@Nfp@Q-3xc7$=scS3X%(@>Nv$TFB6VgBUa*hih^RaaeX zxUaP|yJ1{4+JH_4Ccaju3{+$@vvv!}{tQe0*ky6{pJAArB(oj&;|Pb5O@cf0&@uc0Ku2_gMjq@=3}Htc6LwJ>u;i^$tPB4%@9|XRl;bEhO(p0>%VI zjI6ctT0N|RDT6GDdPb$-=a z{r29^e*W2eKgaPrcgJzx_i-2B@AbJp*L4o>^L@Tg%#KZ9bZl(V&gq-{^lFu@q99Z4 zA(5^jI9R_v;Zx%lzGa413-|Y+)QGP|&d9+)w#@y~f?=C0etfss*}dJvzUlaSXfJ=>3AkR)g0y-nT{&rVIM{j3R9&!eQOY^EGS+!c(Yz#TirmxZ`K znG^QzpG~kKIV)i9i`11DEm}0azc(Ho2Js7!&&<74mREqXo(*n?qAJJ~!TW^Fy*NV| z8t3xtbgqjwg``&S10W1(48G-hGbN?`t)6#_WqzPb?Y?F{uBw)Hlv_vw=FTC~N$qf^ zgK%01UJe~PTEQ9LyqLz3&z3NU@#M*zif-GNA;2&IM||n*p%I`bG9#*#8Sfhhl z^Q8@;ipfBg$;F=mykx8!fXSUB)EzP%J-UI#HosH)LO+p9stCI!7ozo+4KoVwCp5fA9ux^9=yMs+AojYTTCg4I%e%P49IRh($}Qq-sUQ2PBOe6Bk`VLi8kXWpL%wKN&%6wI|o1kUEZU) zgG2bonSe`E265vW@LTw(=ee_q0*Ch2ZH z__PGIIq7H+FQV0xbbk`~Wy$wXQ`-p%ISUWk=Ykh4SRlmSLkxxGf^iaD8nu~nB27@S zuY)sW0DyqZ0Fphp_T;lKuzB}7cJA7B!|5@e2f!w?nE4Zt=`>|Z27!Hs`$ z;n?{}MAQ_$Uhh8rRn4Tq8E~YZFJ!G1l?G`o1`4ZPfa+WctF3r-3m6mh*REp@)*z;L zovISOlldpX9BH1rS|)F@E9=g0lz9GW?M;4(w{M@zjymMlYRGy1XRFtTOsLAS1Q)C@ zdqhex9--w(1GhW$5Xb_hUQ5HpFvBcvGpa;4riUz`luLPOZn`c@$%9%GJ)>9=bUaF% zIK5&^tu=$F0_Af-TYL1vM6-=c)u@n;aP#)erc}c1Dk@=u-$djs)jdr73*~OFEnK;Q z2-$jmhl+zSG5SxJf0g=v`s{lQTI9sW-Wcm=efHN@L~MmDr$CKMgPQN31-9xAI6@i_ zm8xK@OdsHSW**L{JX71`iKwNvTze1OFuAxEOm#7ujdoZZ0XI7IwGm9~$wtA}uX&k8 zP-xy{m|ggjTf}gSwwKK<27I{&7;k(%VEPzGaCVuNV^bChNR$kGU;oFOMjj?qKe6A@ zV|)1*lKE-KSSJOZ6aCKOX7rTv1`9gh#R91>O?UOXUCNp5*fYp!Z0(S(;lZOty zz9)9^!c(Mp7`1zwNF>_8dr5mTMxTtj9Oq6n6Y_F^AYVj7Tkqc|d@2W3GMv!kp=GDV zkQwff?L(N|B;!6ICRvb;2BeMZ)Ht5@-&@{meI`HIx+niQdS_A-nx!w9A9qo!d{`K6 zvf0I=Av4OhPjq2w=-~Dr5lF8Yl!d1nl{v(wU+Z%6$JcEvwElhMwyJ&87Yv>?>s`IR z>GfZHW}4}nTj$pd+6xE&BBq3+vpDBtTU$o@^<`TwcHZ1HXK$0CgZEng@yDwp&o+%e z_H3KsxEq+wDlgV!2_*&$Hi&GvNsK2AFazM%(tvTJ#{g~ZEP|^sw)QdUR>Ra~e?rP~ z967_Te~v5rR8js3-`_ClYHRkL08R$lg^vl@4;sfIgJWD0xmrgKdE_Y`^{#)r!TZz=@H7-HV|%<8}pe4?V*b zd`(7}jWw7{&kzke5<-mVGwOv6L(CX37e~Fx#xBbV`LQi8*!n4f?!K~Gg29)2af6!1 z-lt}RXJ-z!?si%0yw`#&wY00HOl90mS|nGp7qUX+j9mEZC)7)49}F(UmS4ahkl(*J zWei-A=tWp%pXN1auO$bMiYZ_w&gagx3ntFkUKwrFZZ--yB?NgPY#W(nJe)K_ zTfCv1JupuLLOIGB_bz%@fFE}}zw&try${Be>}w}5+3fwXtEz{}XBFzeGGXBBGYU!q z9PqXCh>OAS%Lue^H-*FkLbRmkiT5HrqEosBfoLpJvKB4}@jxI&UW(Z=@{-1_W=)!` zx%!GDd61JYaSYNtcM1GZJCJ7GFIq$PlPjl?jXVe`&p$}fO4Ue} z@>1alm_0;-Vv|93gwy^&{n-ueWT+>Cx($Z4!h{Bs&$q5R-THsOwnF4n6UL-aHT_Qp7i{$b&* z@RNHX8ol@5cQb8Sn1Q>9bL9e%9K(WbDA~^g*XKP5h~Y6M9-S{3z+!?cEt1EH3!r za1$l#sw=Ht$Kb}znv&1&>@gi!&>A(~GTm)t@L$L^o47kcnZ$7oBazEF=}Bo7Amj_N zPzN=-sxntMvWS>5m*rL&zrU{URf#=w=B>W^3IKU3#Sr3}qnRHUEaC$cFrZ9L48naqUpw-qM6diCni zVLv&Nl)sh~x?OMKD06k~2;4IF0>3VW*~|&<&!lRdkQv0f#L~-2l=cTNVCQErYo+I4 zZU`K+skFN#4yHekUM-=(uzH*tYaoIR{esfhl@*|%bmJmg|hO@ z-&g*04qu1WSbwAm^nh*>iyAe$`0zZuT&de?+2o+6ILUi`OhKr9E?^)$~eZo*-qS6(?o8foT0K4s{ zN0#P?{h1oKX6*KV4oP7N!yH>pXiYXiLuf(Ys-~wJG}p4=v{yWPQEvNSvRN7xV&C@((nv{K>xy-KD^(1KOi;0P^FPz00mx>^OZ?C7d5Y@MMd;H39;RM_v&1W8k zSzd_|{6aXkJ1Qyw%OnAPs@b`m6*c}ZE7~rh{J1ejO(q=8)Lp1_fAFl)eNE@3K?b6P z3sSlbvCAytfN2Bz7e-9QlL!Or_H8?FH!{p8!Xz4#5iMmW!kJsxbSz(^UD^d97p(o; zpRsga_{-*|j+HQK#uviBPcl}AM_&^4+)vBdlH8Qmr#bQKpTB=_@D5z)?SMsxYk3r8 zFL^fa410RbSd%CN4DjfEe^Z#{q`34A*%j}=$c>(H+Wrd8p;{ws-#?A%%v<%DwTi)EyGw{G6V12Qh2 z{N!kSb`)gNp?hR>E@x`I$8II-zSx8vyLK&mFuHHOHUnbATRquGW+k*wAa^|B`uTq; zS5+Y@ZUowzl9;%5{$KD=NF)zXD6~<3%(O#J@^ea+O$twuLBx?(yqOa|Y2Gr7l1}=d z&WXPO4gWw&Lb_+t7vf$(;}`@$Y)Q-zGyg?75kaj175H$AgJ(`EukF~Owd$kAYN^YG zAc|8Vjf04CjHnvGo8?J(z2fs_Slt5%0Rczm#NPnAe#&zR1B)96T9>fU3&2UHE&fa!P{>24I4>=O=^gfhqVENapL-f4MNB90-Rmt?N z1-irU8{}41o5vs%=HkFe44n9wre_^P(j3bJ)=6+AxdGB$*NMXNcr+wsl zfE2%Il-y{<%850%4ieoj=Vr*L`8*xs(AaIHLrh?;4S6VEOz-E_mC|n1Mv9^G&#`77(&N4fhmfcu(50G>v(~?YV;?#&Dses_ z5Ba>but6SxxbF$V(I3=pbHCSXC6porXWI^aXrmmVT;-n+_P2%kD=jjCc~yK;w@!HQ zn=;xl$6CM1kss*)o2Z2HxGy^^;4}%wx+D^{1(e>nNGl`}bR-p84px%izvRsQXB+>sjsH`l^ndh#R9e8X7SGCdzwmxLMErx&=c$_p zhEte4aa>pT8>51#A5B;tYb~z&vH82xWZY9Lfu$mny9Eu}4%_ zM#7yUg&WQ z@hlLjy7MFZwJw~05+S3F^%egHw@A0Af)`;K3|HMAD$j$-{G>+*+{WYkL`^c7heel=Ge8Xsd>9oIfQBujLzB$XTR*AE>D}C zHFcSik0sl)M%P~_b6C3}^m^x%9L*lP^guZA+=xxJna4mwr(3-ZPg`wi%-43QsQz({ za%AKc&$A!(CJt|KwoLwi=T2WQ6x7+?IOf^ZV{A^^orAjnTOI8G(X;%&?aMAz+{g&N zG0f)0k2fLaZEHE0)>fNgWolYyUwiB051%hT>Or$^^wMQMiGP)p{_|^W*MGKzP4NHUa7vDhUc|7(=;wGaV>o88Y+ehA z3*KuS86q=ED5`=I=R-gzgQVAFDWED2BJk|}x@W(!gz2%1s5;=!-|5z>xt2bF z72uWhN76_c3|mpDh#n7{2oN zsh-$Lxz4pFm*zPtjl5ZJAX#6sTp#_-PWlE=s&Id&5v4D50=XD6BmrzJdnlqUUm-Nl zrEJ=*Q=)IH)hP6Qr4D-7V;N|qhhzQ6e7UqSk-9^t?Uz?8EiDZMcQQa1uJWS_b$AcB z*=3)7O{7imqz|3xj)Wz%Ew(0-QRf3KcN-btxGMCo?Olpy&(iMduy+VU2ugu40%v}} zeNtW3+16`SNO7E|L%Ww!TA}~rM0q0p`F&?3`sYM9uY4XYd7gox*y6y;mBs29rmLmu z!4eVSEi^?S4xI)ao^fm^7&Pwv=;6aTLbL$vg8F027!a7<=ixd)hKCc?RY&LM%Y~-S^F(>j>Ls0eX9GArCkR=gBkQ9vqjV)>2)aw@$Ft1d|74Rz4uJL z6QUHIlDaK7_F0xt(&(Z0l#B+$THgck$Uj)!K7vwpIaC$Tz~}pxJfsRod-Cm|{wHVe z5TbI6&K){b>wR~|$`L0G+^)1!t}|m`XwRvas+dd3Ic`Fye$P^rwrfVo8EsUlt@cu$(_jtT;m5p z^_}7%m~4@T&^He7ojt&V`3G8Y)+xCV<>~^2(J-b-$(sNjuDQa}B z4>t^wJJ&E3AEk>Q^6vngA60QXIA7iwqz8`T+*BJ1uNP_H6H%Cshx@?I&Lkaer)P>-GHoo;3JA;f4f%N0YB_BCvG935M#Bk8ebM~oW!U7I4a z$1!iO&}|qUww1q?Ce@8P#t*6a3WZV%U&ot~(8%hR=wVJuF^ioV zbKB9%=5oSMRqGmKX8yWM2c0fm^k}^mA^YY+HKNdyZ#}E#aK)RZR>FjuzRwO-b9~m~ z($;ElOf5s?{Ko?wdt;7W)zoQMl>XbV^Jn>9eFdv)F%?g$O;U}_sU<~H=^naz_I)x% zVjARJ)#|Amu8p3}OqjxyI-kALq(2LjOY7@rDM)lm7d{P@QsaahK?%k? zxSgGDg#1y{xvl5G;U`OSR?n$r7rK(og#~ooZN1y4j50`R!@rcz8<@C4xsGOE+6kVy zoYk#Sr}~UvJ8;)@pt$5^lzJ~v?Jj!}>#J&%e^>oNFS~;{NvQ~?4@P*#Z+k?ejYDAs zv^KnOtJ~Rh3Y8QA%cw+A{Ia&QYp&`GSL^{KA-Z{|QSyPGy!m|6)J~0;L&hH0`D_ZQ zu9Q0BcYw|7Fdr(lu4zU@h)Mx`EU1#^k&D+qoDF*s5L%UbhnY6S?OvTNY~Wlu8~{L$ z9KY3gV7(b;Cl5~WRJ`%}AE|)vVVd8n%kT)PVuWREOwAF~qRE)lA}YTdG)#x=K0@rVs$Fyt3Oqr?RE)r?!PL7_sH>0dGN5toHEjTto%HR0EJC%}JAc1Mn3t~q7^?Y=eq45o z7G_zWd2XFrt4?)$GSknc1ACTAo^1WD7!%iOL*3@xLyspM7;IU!#l4)_wjsd_bd~Gq zcjtA9k9S)^^>kxNq4h~eJj^tz0IGsUAf* zHcvCajlJnJ1SyN#T!N%E!cFWh+D1@TjPv>?v?|K@enEOquW!18!hr9ihxQn8Z0g4; zn_Bb=xB9fMO0iJyU2lw`432Gs%L|W!5>SFs--za_ zOb0+nxmh#imp^U0T`uju$7eE~si%MD)Ot1Q*tKid0g$QQv=P3=);ce+IVv5vxwE0D ztoxXE`k9N6_*Y$id?QOs{9ANh7FrT{__WSbYG#I*U3Q14kr! zfg*=V(Pg!kr}Btf9y`o{O&vKYmHwJ3Q{ah0Yu*Z%7tUduwC zoS^mucczcqIl6vmO>q7iBgVRVAE?{$$t&)T!s^%&lDKpD+J$+m-A5igQR%7iMj%AJ->U^;LJXOaEfF^xmN( zM_jt!U%h)1X@g400M49~eqgE0iFoLJ>no%?r<{0GW4|AfZk-xCKW+4+w9mC;VWS)JKtpG8q(b*iV_?q^t(2OUNo;E%ZVkKbq5EffA*g^U+J}T(es{4Z97OW==WNQ z(l5AB?ObCS=n9f44Q4re$@Hj+YZsORe;!3C(M7Z6MrH?jNVlNpJ%Z=x%Zczn0)nPa zo-DcFqw}q~XC>YXLc=Da%ah}PL*DH+E=*Kh!mTx);~0p zq-$jfmrL4pZ){RSI5TPK?mB}ACtjlNg6>V1as9t>;6&e~*A&yx)4|GJ%`K_2xyFgB zNuVq3%_i;T3oWO6;!rjlw)w7p)$*KU8{zqwU#R!u5Gwb)e(b9cnzPKDtu3lgG*q23}QvPZSv{^33cCL~(eU8+*? zNR;P5eN|Q=w}tz6`WmF1#O5A|2yNR%W0=akU!K3xQ4HDF7gJJb8O_@@$}7UBt1m5G z+hLPa_Y*+7lCDHWIs48Lrz7b`P7!u&$NR0ELotv`^n|5CB%HUPUE5F3Ax0m)R)po= zx+O_^E|#9daVMDsMtPsyXkfVFiv9JUF`GZhUiIt=6r*{bmWIZ(+)JLG^gu6kLH!&uFUIGY3M3d9bMhg))|D4jr`1 zr>MdusEW98`7Nd&NXRN_ut>q6{=qAWii!fEK<^@q?<1JG!GFy??=|Wd7oZ3Bmmlk0 zyt!?}O8x4Z$%EXkRB2k|&1eE4&?Id7{{G$@5{WU6?|f$9%mc^Y{pZLW2b43lB~R#= z=N|4-bdOLf_6-@u2E#V0z9gqh#6CBl3VfioV^U9KU11l+VG2-o8%OyeGV%$b6KsL0 zkQmIo{aLt))jSfX3Romo-@l?al5~IiL8WXtwY_`yc2&zg_J@99xdzIK{2{q$=vPWx z+X}cuL^Vx4{$MmC^8uDED~A7UY1otI4~SEqxN*|?jb$AOJ0<*9yvp(rk!$k%G52+s zBeCt17bqg`&}Hc9{S35!9k%%aOTjuje1k1-oL7WaRKv+%S80?w@Tp|Bn~adZ6y?6~ z3ng$1cV$jafnyz-m&I$6*1CdS%7G4q)SHb8?a~M123`;rZ=Kr4Lt_(E6?C28meP|T zs?Cw(#SzGf#7l|PAvDUSs=nhc_R)-3nO{viSrIKey%m8gAe`%))TsMIn;y03>r2I( zu~Ito>oV6Xa&D$HV+!WMbIO?Lr>(pW96fMAGtZrzjKA}cunz8;n5ab`XhRNmz23ra zlk~w72Oah3Py6n5ucy`ScETV_*WTj%M;FTrRL4cYXSqBa29T)O5s3B4K3Q0z1%>v@ ziCf*~)^8V^G!)y4ZD#_YDlFBz$0K;IM=X{Mv-sK~4SV*SpAPFHpdbNSYlxt+6 zbYcdEUy>b~DAV_Y_!uJ;u=P&;jYFrKxCqCT^mW&)c}V-P{G&AH-itT{%AkMQyqDoC z`zlTC<1onAN52#?iF*%Lk82im`>2+~%2^E*FjSP5;0+~m$lux6+IBP`Y1p|%i-

m)0RaRat8KcjDcUrc3?8ea z!7GH-p1i83i-5$Q%wF5{aqJTMh%V&*BMnnc8~yvPv%e>&eh2w!UzW5gpm<5OuKpg% z>4akk48+nz?8i&@)Vp`m7jo9lNUg0grdr;Mx;L)v`N`wOSuy~mF*N!*C(t;b1q0sv z>%1b+K~k6a9nu2P?QG8d2rZ?t){`ffN$!E}Xp(OaQK8e(SbccvMdSTp314Wfg5?`# zwFB(v_@4o@6yQws6fPMtZjM5|lyiQ-#Ct){i^j@zGVK(HFp|VaNhx(i(GY#5&?K=z zo84nEiQDN<+6}p`kBR$Bju&EWMmm zs=}U+tlV=I$-nC>LQDVmKhn+jv`DSym(hCEWDs8$rb^T5hr|GXL?jKt?=8b=1{3NT zY_v8|h;Zx-ojG$gvi+7s2`;Ay6`8yKAyuWm%ngyGSrDNRH)&RKdpf&wN*vTo&0+ld z3V=XG(Q9m_4`AY5}*=?$V$xXC&fX z-!x%U2v>cVbMx93?{09?(`&wz93??cdgwMmRd(&*(J+@SCWQfP=DFu?96a_6n1|pd zf(RHSoTJqP%M(!+M>3!ABi!277UtFhI?*94Jz=Z6=;#1|BfuhJ1&S;^=j7(4%~#sr zbIQln2f?ob-wX({g%SpNu+mJ@BhYl|Il$cUuxg<-1`NoHwy?6g*Mp{4TK+OP0l<1| zJuH?iDZueAgE@O(%0%^n^>QqKKI5FG8;8Ehn4;gfwuB)`sXDwpP2S$T%D1N}Z!gB4 zB3|2XV~gi@^c0VBqt%ah4kcVfFCwr<=cQ?9GCl02Tk)kp!X-q~^F9yFCN*t}kUDI2 z!8d6;rzMtD8a=Y{eQv7QuLF@ouG1BDnWQlwK+liR{v@h!&WKEYeSDevz$k1y@5v?A zn!Hg1gpD@b@3_?)Mt=}wW1vV&=A_27Xcy7$Q*|-*BxSPzriY}P8pCI#pTa_sU#?odSp)YY;$T7N3OXjE*;%yiNh z-8~TP3Fy(8=b!pvfMTFnCpkIkrP)5APYA)dPdgC#n&JC=pP=6y(pJx;zmJDccQ}CO z7QlbH$(*B2RDFfCryaNdI=1u4>e&ype=R&9sH;P}Ph}v^n+?5yi)Jp^_Hu@oZ7qOH zB^U6@v9=0?d2f29?OGZcU}7F;)zEX>fWN=>t-;w5#3+7;sKacng5{7Xga(a6RwK`W zL{iS6XKW5)5rI=W-Q5R1O}hOC^5~d`OHToIOS47C7jCZs`sX}dV;+R*!$13ZWF3?= z71K?l$IYUB<~5z2>M5+5pGDJS{@(?r1)AvUMv(G~>?P^tAWlzCgJYLet1pm<;KVRu zWYb%3RmEY=dwQ*6#B~UXy-u0!n?GL0Q;!>Y;63<#!=*UAnEWRm(Xv zGH^R)*R__NQ$0zpV&8}W!oo@BjUHdFqHCeBx1Bu{r+bp(baQrJZyL7$p1Sb@?IBAx z|Ck+GYx8uA8(@;<3@JUE_g1KeWNhDW1H7@a8^-%-Q#QP;=le$peU3SW#B^>G1w^JiOlI zP2X5tSKz7H&T|8w)Vk5|*xi=rXnJwIF>FKg2DkP4CCsc*C#G$sY3SMjF#qnp1n+)T zl>9f*bZc*KZ)MfM!wFk!o?$TRIp*rkrcbQk!y^bjAry172n)ugFQ zNUc_vd$W!!f>#(=?TC?^NDdf1L^{wVzbT$3agBfne z_`J+fl}DkK;wUVZqtFHD!iYgbkENuvgkxG(47k*4={XK5kFt(v0Iqxd4&T-bhi?rN z^`pm^$rdC}l=jhzUE^r??;+97ww-W_*hFRQ>3k_5B!}O z#P3VP;4t+i)&mEwUp9OYa!L)=k)o zz0y+55=)U-RrlQkTP3FnWajmkt^l!bvCA9C#r1}O{2Ojx9Lxo0A^~A50hXDg3p(U9 zpt*FXl5v9=Xg)XEJmXC(CR-4zHTto85-l9Ol_v+HR$eNm3L{mta})DLc8;7FHInyD zQ*~R8DCrbGTyyKHDje+wqlXhO8n7?`E%)|$MJV+6zZr3VMvZ5D$gD<{Ma!-d@+=G0 z@_boaNq0Cg0jH4L#cCDlA8k!rwiE{(VpM2_%~vTkkRJP4l(T~AHKdh1bE^Sa4Qi7# z2IZzYtl&g-ZdRw-Bk5}uT0LV!4E_Mz7d(deAYj$m7BeS-yX5s-`#~+~ZbD2jm&f94*-GMSM^m!V){qyWPuc0~eO9u;skx zbUoz?z{scIsIkK~Q%j?R;&i?XJ;tKdoS@E-Bk$8Ynx>kn^lnFl@Uf;{q6amB=drHS zbKJqA?Oz9f&2=Df=vrykMu}PT?<@Js>DJtB*BdCU?Z6xE`9nIZ4)p(~3QqHu%Xdh@ z0MM=&v6Sr4tbM^SLHk!9J-3uV`ttC7w!PXGNdQJL6YFb%R`xpYMvEU$>} zkQ4Doc)f>a^LkrjYYj&2?xUMmr25S1&m>jbOM})|-jNa1Rh4{Jybh;dK$krEr63uG zB6Fhddac2S+ad>bT@|WBw|l)d_k7Q7i{QGH#X&+46ZQ2Qg-A-7&$STd26-IquJi!> zzU2n@!um0mL_eYynLZfPld8BNHzMd^Bc$BeyhnRCY1q@C+jQvmoyf4Hf1$f%){Jtq zYQ1B0R*vR+`;)P@ZMji8MFAQpZnv1)?bxmmavJ>!m4?+*aWef3Wj}KWFkD|$nHam^ zk9`Nvg-s)Wr?#{tr-*npAh+8g5<8fLYkUr4x%OXs^omh%bCf;E+yrLEp+IJgRFM71Y1Jdj5 zK5I%(lNvyLxUp#m3`NrK%H?(hHtSG%kvb~u(NID4Mq*th7rbGV4?NU&*;DYpK6$d% z2bulHNqIG`OgfVrhq&pp4wVj~PqY7_NH_sHmu&&ID(cfe#!`flavX3x;5M~uFZ>>& zO~<+jW2jH%)aT@O34BQh{W`-8`X}f`3^Va=|7T14-Iv0N45$wk=Y~|2I;MXSIj>gd z4Ob?Y>Jt{KSDsdVg;nY$R%yN5;Mh0P@lTMoyZb9%@@wPIM;Hw9#H&zrbaD4q-+LCc zQf6q`;me7*O=&s~kIfU8inM{lXW(9oFALjR$^Z$$$TksvB}^!*Z*W9n8rK`rYNzig z;tJ_m*ElB9jhUPjP(SsqLG?b|F4DoTllNuaqoZ-a$SzPjc8|JL%NW-sZ7s#FDO|A`f>%*hRr|HgE0W@QNsZ>mLFS~j zI#z^d)sR2vc<0<;cKM)Umxo^(H02rNZ}#nE)Vt~SruF8&>$}UR`u%1KALZOr&P4Gr zITKd>S_`4+O&h>s53~Wth3K^0D7Tzs1PKsJTOUR6)%hgp`}R2%gXT18)(pSYf8=_314A!WX;BHy zI8&*^*_tb=qcWA`eVw=B7l{nF-PGJNJQFBpCq32a`-NXKaA4C46QhRDiuz8|6NIJ6LYSA6OZX?5`d;HhR|r z5p@9PfED$(t)m1ZV#SnaMmshPjXQ^-pl@xx`sP^^&~lJsXsj0QIgd$=5Di@R1tOg* z=sJ3s2N)fO*d)ISQgSL}3~4B5!i$ZS3OfKmALO|)&f0-lv>_*EB=4%$yMCtrNhu~J z4#TXo^2OMxNWShLobsd1jxHvr~jefI8hiN{ogkVlfI>rWT!&SQq;2tu zm*WEQOO%;DPANxAWA<0WReLR2yA#MShGyQCQvl`{0g=x2s;T=F{3`J5>LR*lmp%T& zH_XdxzwsPF(*+=y`RSzFzMh!qnG>LMQ@2(!3jSsQjBr#W#-L z9RB&iBz32ur^eXK$k$N};I;>GgqUbAhB&&V zf1zCUHr%JJV>!p7tw$xQV<;rIwilOa8o?O^>%y&-b7}i7`wN_G67T0pd7EXO8r##K z$WWR?@jDn_k}MW5G6@AI5e645BWaBE1R|Ju5%$bX=gFaQbLpB#Y{g}J*wUimB?j`| zuoD!CwryEb@$q8$M}8BV(PEb_VaBy4k2$PIv>f(^tslByz-ee})70L+Y;n0>wLae( zkzyFUeYYilN#&aT6!+Hy*B#n|&QNKvC2*XRvqn(n>dhuuBIUU;swKLBugUKx{#b-U zfhcu+QQHXgRxaEq&>3g~QY58BK?^Y0bWd~#5XZ~mSJVyNZs)8sT_huVr+?Di(mArP z$aHfNAUg=u#3*&Auj?f6BQ84&T*-b(-Fu5-#|b@j$HRgZ)qwAJ(TBD|(fQ5tKZA;o zL&LJ@@6tTFl1RHwAhouip#A&2Yv5;QOx7a=)pO@o_-db-{ooxUBuPj{Ze67|-&uj_ zpm_597GZiG5n9}YmZ48D{!}u>oj^qyQ5FRiN9I5oAU?D3ffgk;_1bbqtIn9@(Cfd$ z%cBP>vL5?LTqf#h1Pv>Qa#5L-BoTo0G`APO%Xffv2pmD^^@K!CNWw%iGYhsXI4J7uY(7M+8_u;%RG3)VBuTnPAud|h!8NvN%E9j@_M2P0c-hWydrpw8pIyDdiiAG zp>$i{I28y?0wU#}gu_!qe5x<(s)#SG6|wxoOX|OOMNCpqvwrgVl}z3Kf7(FtpPmx@ z`TvrBnaWlaK5Y$Zp~A20Z%6TR2eU_+hC#gWoIqJ7fpH6#f~Yf~cb=+kjX)APByP10 zgjYBPW@p@CMYE63+`E)Gpz{v`6Chu7dC2HSsWB2rJP`JU%V!z9fx5C3qO?DZtQt6S z>k4wvq?uZZLp{T9n4%*&?lUqILFimiz7gg%?r`_n)`}nTc{qfql*HSRFOZ~*ZzzF? z@O<9S-tmQ!lJW0z_;<+;gnK8;Po7N6Gk;7E3GrR}Zy5P>5d^Oc)?lBd?e1=!%gmTg z$N9dKadi|Dvu#5w+hUSM)&h@NMvxbHw!V{jR731`^5n`^8)YH$@Oc(gJSdERM(dX! zlCL5cZ)m<}`!6nlK(hQC$hD0m=j2kmfBoFK%Fn1N8pwfrFuWl1;LI?kgrF^zE2&+B z;We%!vt=NPpD1yx95CXPT)D`-ST%jen!Z=jmU{vYF9jk7W`z*@QyqUy1)r=A7+~0e zo>$?qijuVcEyXI8+6wK5ojDDl`VP*-D+#b6o{%|v`DTfnOaF-4PHkJOYR7qh2KU>2 z)>QF}JxwdOdWoJTho!rpS#PQ6m4h=qhewf zb56!A{1XU5@lP{;T@R-v0?b1SHo12Xl;-e}DU&DDKawL{L~uj~aoIs1$}Qr(kVS0T z(DgVFo`CCA?eNi7P$mSZrWu4~hmqo-D=7d!QHEf@$RB`9eUz%~(5A_u0953J^78m# znd1hVh5WU7?KR-o@x*JYE%o2~4_19brB&Kj7W7Nsu;kt4PyL@&G+uQytU?RlO>i}3 ziZN=eR6e@e$2jpqkmP|T=3#Db4(i8<>WjR!*1&i|Gy(@0Z)f*7y+HBc(K{;N$0PoF zN9KEOL_pXQ@)bA9AUtwUQC`_()Y8xFevmf}o+3slgDT1M5{&kqII)m7!(Z>l$$_&> zGK}SWpj%X@XeDJ4h-ysCH5G*A`Vs zq$k$EaBksl9Hk;6KXruGr`Mj!Vx4Nd5PmCz#PYlL)24b;h*! zxtL|yr=s)qV4<;^ck2&4*|143;6JnR@Dj|%ldMQQ*STD0Y=cV|uW5Rh5{F(hsz3zw zJq&WD+%4ct-pFmbaSpbZSo#NOpePf9-sp@gP{=nN82;1Z&3l^ja+fyjJ>LN9@#Dv9 z-F^ABGMSN942VBt4&}KMsLV%xk;J@=CIgFa*ZmPQGKAN$i7=c(Yxq>V?292B${=cC z(yb)jMW-LKE6*W-5Q~LBp8d4i$}%J06UAeCtP0HPu+bGtqzv<^uqt`jGbT#n!`I&@<0&MVIvz)J# zAYJtsy?Xk292cYzkBXisvDvNUMM=WxB#YCI`#vLE#(|T!fI+t_i)@*=>cyf?x3~^^ zCglx9gbn^}E~VI8iE|OTjU|5U)w7A*aZ{a2>lwGb^owM1cdV~EjUJsWGIHdijx$cH z$YF!S<4K15WM?TPKhc@tI_}(<^id`!6G+~9sUu?R&@OxZIGj76h`lKt)1&C?OTFXo zD&~B$Sal#OrDEkB)!T_3t7%>Bx3Tgto1~V`GgJjnNGoD2$xy>9@Cb)Uf6#wYsUp zd*dQf_OBWCOl?EU-p*1udtVw1&LoPJkt+%f9#f-6*LLb(8E&K;gy&-rooO)QOwFK0 zwt*T6x0|gTnf~4FF*m%cdNL@i`ok_G72o$~rCLdiXFx_xEOYU7oeuF8*$K_2)(uNj zOXtjUuBRFpR9wO{$$@^kV%|alE+Ap^Z6R1lq}`T~CU-9MyVU$s-FVeubN#n-p zd<%)EuAW{64LH+|+YM;5Ibj+W*&Z&7OkM*xIPIJkm12yiW*zm6k5}zY#EuMSTdPx8 zZ$#-T@bt$>MX=TG{Q3?0=5F1(1x8&U;61R#l5WT8mgvPnCVU#bJfK0pEYJJjJI%UK zbJDZ{ZDjmTl?>I1_V!SV9<$-wP<^(w^*U2bU7F*1P@JgDcbhb`lDV>A?K8!gm56N$ z@t6gcz#n?CKfzhPiLh%* zN=i}^sS6cDV;ntH-;<=uR3BydYdse`8yk2Gjy(ICf}`#fdf$90D!;gtrVNzNKrhAR z$o<%_QPzo>>W1>?Ec$}v`dA3b@QEABVPH_%?&`jcj7qDl-B%}0jDeh(jUzWCOhbf! zRCJiI2XRcaD8Ouf6#q zosRCesb}nbt;2m3Hy0hoKtAp*+=h=b2A4NonD>0*w+bVS#^resAu!>M2E1c<7_WUY zclX=Zui5F2NFu;TZ`N&6Km0pIB%dw3#`7>FKhE8`j-itk6A|uY+Yv@sHSAqh7L=si zAC4-UgL=-qi9VI;Vr?sfti~D%SgN!fNAL^fE(!*6=O6jG&-z~Twm;Ts^0esPG9a-T zntLIS+GV|aH-&RU&X~kJnC7;VC!gmnelAo9_*vFbs0zJ&xr@(-mQ__{5|wO`MRwgL zXQV=d(cI#Kh!!uF<<2MW;10~A+116xrR*7zLd3p(?Hw+0k8gk}wXXAQYNaqC0~b7* zMqI7#Zg_mOqqv#|f1D515(@f!ixlP3Fo2@>AT~$7HQ9=lU^DuMCYyZ-dhn%_%G3wS zM)yB73L9Cvk~f12)wGwFRxTNO=;BeX72&}0&pQ!#J9ru#h?vWurXrlGA&t04>**3!S)M`okBx=1ym!=;GvTl=1nst`eL|GNJ=&flacfVgBK$&LrXRk6Uzs0+H7kA z^e^<4hK+a!8nlgYc&l%C!ri~-*XZMmURSctjmh3T?cMs%T710lb?1|6H(Z2pTW=yQ zA7v3?O_-MC0>rJP6zZaoT)K2wBJ5zA=)SlQa2Q4WA{zR4cL>J{HF#vOEVZYusz+jmO;V{rLn%#zsor>^92n>We>dfU`7^UWxWX6hBXT+bHtyX>`H_6 z2{H*3JFSqa9lD{DuI@a_4e%zW-np~oA_Wy#l&@Sq5X2=VnHL<@kU4YUGkYSQvc=%t z;j!1gW6w4M(mPxNts68Uf~~2lQnzLp;O;{bovKkHJW6eOfp5f~Z^nBEtlOn`MKKj; zmZKwUBhafG(QWF50l(H(tGMDX@qgvbMhEJD5Crr7gEwE?yEYv;vnmO2F7Vmz5x!+* zjN_~6{==b6rWc2nP?qv-Q>`>X&uh!>-Milpr;a=xZXQ0X@%R?_a5PWXjlS>=-dPcZ zM8x)|>{FIXHc!^#Zo8>c~*B-j|P+$@cXF|yZf3v3Ge!Yud6rjRf$hbFokzU3*m zXyQ<@=E!(IOik5{8d?x^@`{JzsP-s&Vr)tLF?ZisUiaEc5TKL+BRu7TM7WS5?y1X! zr1RgnwSzx=qXw>GT|>2X^P4(948bL;MiH5hKJNYb(W`)Q<%uWN|bVOVq>0N z<(%?j&=5?id6+jBa@?*xiHsYp5=Ck_bKltCPd{XqoB3rV2UZ@4587GN|$u znR5Xv?_OMYVGI?7P8!MtFtE04_hm~9WcZl5pB8b}Ygo(J80)~L4BFcE!Ef=W45QF^ zE{whR=Fk0o3l#5d8g%nT1%H1waTLQ+(~5Nf$x4w2GHv_kb5J_^>%MdzDW@%VRNhQyn2(gJ1M5Q|#PyV;+ z^hz)j%M#6!)g{KfJGGhH%>JD2OzF=&ei1GsU{9;A%x@13b->@BvSkkCq>rDll7~OH zQCM#hrVjtj*B#~%3!&6^d9%GlTD8LNfZoHV!T$~^`R+%}HY6VSuTJ7_BV?3<2tC{_HwY-p(uG4nek{>~dSS2Q{u9cx%)&F%+Ndko|e zh@~}kv}$Jz`T6TF-^nj4RSd3_J9HjDVZyG6zaQRyYkb_UYiLXVTZhLHnA~6V(VCXp zh`*igu$foaja1-Ri7P6l4^P!8+PVbw-FB0Vx^y`thiR#5x!2Nl4Lz3{cX74kLawlL z^;3M$t}%+RKh#b6@=YJR8FoYfO)cj^#J(T=pu{hiK*Yc*lJN6Xd7HFF#)o6gyo5yBF71 z-CEfAi@TOkG$#QuOXEdSAncx?H3i(Lv0=`9&@AONAzp;G{O$DBtvr4HcZozaEJbYm zl40+FLMA3uvlbvNb;nLdFi@n+_Pj6-kP$kESsIxPs8F?0*oc2#(O;FXXm|uxmQ!G1 zy)j|h-iuL-NEcC?7<LulRWtelDhdCTMHz z2vO+(!BusQBMPc+O;L<`RY)~Js%Ipb2hIZV@9lpgE4H>M?uKHS!ZHXw;!9EwLzG`Vd432(j( zj*b6m4`x)_gMkc0t6!RNjnno6vS7`b(X^*upm)OR6m>L?cAc4fJ%?_9x04ptc=tI# zQz;5mRgrcZ?Spw22M#F;QVW;ST36C0SDx;l>y5aI8+`~#$VXYUfEcB;?hw5=PzyRM zR~5vJAo>LX+eEBbem*JWS902V%|-YfHH@e|&)cs^X;<6gMas?|Z$fhq*#5ll(|_Lg zy~mDyMm)b>^JBargsd?{(dK$RApE>^c>Brg`&nM8=5v!R{Cxpq>B!Rj;_wFp5Qqmy zt8!hm3h+LA>UH32oFS%~E+IVwO};nq+3oV57xg-Vf?TqQXOtiThg)`cfGHwjJn1TrwmZJh*a+YN z_$Q5%NOh^&<{;E}2y2z+epdqSkn~<^JH+DItA(rdcD`evf0S)cuK^`2(6 z7NoMe^`S$D7%6WHJB6{x!NI|xCCq=YwCoPTz3QaV4n?l)zpK*kWHXq=o$P*zst~W} z?YPSdfQicx2B3I<^rFYT>7z%Frhx#IffXdPI%XzH%gICtYYVPY)Q<+HY*$(}yC)YA zZG{qMTCIT5#B@q%Jt^)3E*!;1AVndPJLjQ$lXM58JQ4g{+ABaYG*34uUSuJ#!bg*S zP1lq8@dxhHf%zj%UjDRkmKl39#6(`I*nlkcW;7L2mbPYQy$J5mPgY#6hpm3`R`25{ zx^|mmP-6hJ{Y3o zbw)yTB;qTu1p>=o27Iqt&@?+iOHpZQ4L;#E>>ixWfgDW8i&HWS;1ipcEdUf6p z>1n{(NP>4}UNnG-&;S7s!ZM;@!18nI6b`bZz1mjE3hF4RI7ozALAQU_TBUNWnuPMk zgnqzQ2xg5ukA0AeN4Q1sa+DLoGotrUBI;-n6iZK-NVCMLQpKc-K!cMjfzy@e&z81d zkn({Wy{dYhrXnT<%hPwc-jYR?ZpL?#8wm8?3<=;aRh;8w$@DkoFNxrgn$v3-AKgii z)_04KAUtZ9mxW>ojDqFSVLXd8i`Fn9Nm@ZanT*qr^6c_%u5Y)E&tRwyhVFJsipA`s zHQGN&>EDPdflS?zTvBN8$Z<)13f*(SAHnUkv~VrPczlY9Q|#@Rcb~80Q+cTRX;$8~ zD=}CYFlBFPUjtx;N-CYvyfVH@AKh&1i)3f$qmUM1LPX0R$xuZ64@_@Wqh<556da3C zClC+PqcsS@Bck|cSmUlu4cTP?0}mQw3Tcxj+s@&D2D(id(_&%Dfh(0qsP(8yN73N# z#Xse;*B%HOd|nYo$n8RKd*tsr+OI1YUinY$|BJ--|7ZW{1pFe^f;N@UEdM>c!~Ea0 zH`n%4ob1Yf_F4O{Ryf`E|M{o?WgC^Kn_)^KH`m;3ptWMJ|FhNqn@`sd@3*%eC1e;n REtmZ^A7Wv4WRSz3{}(pb-rN8H literal 0 HcmV?d00001 diff --git a/_freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-rand-dot-plot-1.png b/_freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-rand-dot-plot-1.png new file mode 100644 index 0000000000000000000000000000000000000000..0ad1637880225ed3e62014674b403f8999188001 GIT binary patch literal 299429 zcmeFZcRZJU|2|${f*&}3c4U*B2>{YhRsBB7+J+e|pWRoqM z-*Hm+=eobY&+pIQe_z+*zOFmf+j+ju=Qy6naXe3t%a_D=Y~8nY-MV!Jfz)~yi#yvUF9#do%tNhn*aTc;{U{BJ$w^9$$Jtvk3* zQskV1ZRqfl-3?07<@ZZAl`PIw2&h6f%oPF-x*`0;QZ8nP^Jml)Sar4vrtwBM3Pv({;x_9@dR9enhDz>K< zTKD+QD@-?7D%vzF%w?;xlHh9o{WUQ$WA%T2?*wL+t)k=q z{jEFQfv1Rr`PbJ$-v9eiIFA2&Rzytv-(XnHjQ^j5foU!W$=iC~#Kc5ZRn^#d__fyO zOJRI|{=}E{&ypSPALaH@?Ac>I@Z~6T-0Btm{TItUWcdw;<`lI=mCO{W_wVm+XiieT z(tfkUX{N1N-Ql8OYtdqKyq@)L_4qw(=FR&P|Y>wHMpoaQAyB)24_YBBbk@KHOOSj29kTqS9QSJ$n`%9sSXr>~nGP z0e)*1Uf#K`Vz1^@4MoZrDL*DnP0foTryqF|UpWgSxhn6BX=rE$Mn^}7u5a^sYmokK zTfwuyKwI2Yn6OKG(}};gzxv+_T&80}TAJDScelK#*{-z&zk2cF$Ncn=hlhvGiq?%A zKR%KP3)oNfx92-3Cde1h2K$F3UG#mcHkM3r?9v<4j`rI8r!o@j|NWs#G~1SGn1zLf z`+qyC@oVIm_mq3F73?J^=P>(m)-S<5^NOl!o?+vw^&2)RBwqVPzcTxozL#;{f9-R# z6BSdfM_OBI6G9oI|NXJ+SWuNqJRdzeSsjQ;6;8 zHqYL}ranA$UCHfZr|oz#H9jpQD9Aw7KS0Ad`-1yU#S~R`*5azQPl|C|p6et3&;3yy zyA-~G!h?lU1u1tbFGUDB%}wZNG#8O?-L{Q%CvDcP@24ru5e7-Of0p1U zcs+i6`cT;F$)yFS7R*cCLrkrHy(sE2r=q4_$l0^{%e10+pMu2+X${2>#7Ak}yjdA! z-|rt1^1Z-mA>UzUUzkKwY}q$frHj_qzq2j+L>LxkMhkC!e}||**z$&5YF_EUp*V*B zSFcPXxwe;E>fE^xF3XejxXc+TDJevc&Df7~zLR`m)pUaPv;wwixcyBrPgjF+&-15G z50byrtqOLhcmA6G-{Gio!%Z%VMdh9MFHuTS8Xl8Yw!+1(#9$Z@n*^)j7GUP z&Xtvw1+za9{2j=1h4>({T| z-rikZH{vWUs-4GN&(zP&Z-?CfM(e}B`C>zO8D2GhHbn7@*_bSXun zu)uFMWHYtu@A9pC_!H&fURPJww|BP^>3qY(Sts%itUg~;Jm6*I%?S<_1(Qp07PT+V z-TR=HYkg5tGDy(j-H)iJ_S1t-V;@MVSydlCe!Ry+BhU8rV~3=Q)%0M_wf+^X>m48~ z@xL6Wm37xA4@Aj)&YpsqDxMBneruT{6LWnL9hs&YA|fJoS470b==d!4D+AdXK74$z zgPDnm$<$Nj+3NGYc1>PBl5Q8iC@Hna|3>HPHQzaTN>f1=XN3#0K0{lO^6*JdPmkcz zR6T=FYT@$yXL^_6(NRs|?VC3%<=KvB-TujS7*DIOCSp|CKYcBc+U!oTwcPvfr^0-r zC|>BMmKGvdSikn5t{0Q%1nPHhPmjTaM|;`3rkgcpI07OfI*Q!3iJs<*IDPB7iAhSp zz@JZSOx4i%Pa3UVDAg&=2Iho>gvq`d)Al?&OUtRIWECg11Jb2cRZc%2@o;@a)D+AQ z5>;=MbJNC+#%(!QEvhQ;q};Yq+xxENmc)x|$=ClU=~q8G>CTp@o}XrCs>Ap*Q78*n zmPX$iHhOw{69u9sl=tV5y>cmn#na1+`{VLV;R?y7O@n@KOxkid^{N}TJK%>St%0ZPRovX%P=9!DcYP{(w7;)1i1X&BhiGo-AEKh7JLrWR z$GeIZQ`M)f4xIelY4*@qS;%?O*5^Q3h0a8G*@q7w2H9I$T7;Kpqx5>#B8FEX`TEuW z_bE*^?O|2jOG~SYvV8j1x9zlN%my10n6D+Bu^9;7_1^va zMh)?GudXH{4!Dh)Sol`IxVRcJseYfmeS6&JusBjUTdyYE_n2&KZ0sIt>f9BBuW6bU z{wFyZ3`EbQnJ6nO$H_*t7rLw@T!|wmC-3_Claqr36`dK+H$%4yS12Yb%5Cr^+Ne1N z7nyK1(LW+0A~n%*TToCC{_675Oowc^KoB6o?_uQ`_p1r=G5jN0KT~o?Ua4f7cG7&Z(-|&q6|m zEcx0Zt|woAJJ^)`Jz5eyJebR6>Rwxmns3^uA9kN=cu015hw7l-DXm?RE zi&EO1`x@#5a?>SRO1~xFqr{KLA{--?-K~Fp^UG9P?T0KwxE-LTk(P`&UEd1CLdYr2 zqVb=fuL?cHw_j0npa^oRFzL^Zbq+Q<1AHb&6mgP}knmd%@8!2P#zkh&UqBjY*!B1U z)$N@xZjd%K97GUr_~##!=FrZM?n5E3@6jp+RQNrAKJ|f=p3C@anrhYd9Xp(Uy=?|a zx#gydW?vsCTNBL9%)k(-nrz0?-J%!K_SQ&IQ}bo&_d~L&xwhk7)EbU;01*?;v?lEA z>=DlM2ItS;!|(ELDOf1bnQ%KHDCku7>?i=;i^4*8eg_e8@xr;@5M=uC6DR6k-`w=t zYUR1}i*R4x3>+h_%b|Av_e@h^({_Q}&`t{rivTu__SahCF(X zF~PCg3uFeT=Q3)9IN$7)l$2x;7vks7RV^+jTCL7GBu+cqvu_9pWJt%voX@#bJ>8n{ z1M#Byu2WN%euY#9Z|#30R05wC-M8>@|TZIsuObCauWYghboqdXmiYi$-Bi3o*x4N^s4)Ga*r#hzw>f04Z{h7>H-VB^o!#LLZaQERn z;}u?3K(%mprPa(O52z8sHXl+d6Yw(l;|Dk6VczlD5|#PUwQhpx`0-r^>2+85LNCRYR%;+*cClSq1?=C@hGd}K+bhdU?FtkAOu8#?rq8NG$hsJ**0!h!P>Iw$ckWz!ChL(S+V!y)gQrBdvujtH z<$!$sm1aT^)@4(^1(UK76$#OQrZNof}2A3q0&IiNre^)hhc19$hr$!h+iM~~)EkKC;hUdcn( zL-SkY4z}*Vh=KA|DrzwCCrZyT6IwW~AY@3>6;KudlCvrfGik?x)jm zS(;X}Y2yY2aR2zyp;HH)6wQdr?7KHSw z-O2_mS=Dm51Oyf%Ru=Uzw%+#GNhk0X*Nk~86jOW_3&U``a1UL)28!DFXZk`6{%CSZ z4xM&(cCx}tmS{EaOxj*KbkdcUm1WPgJAC%0xuT%Z?PQRhosIJP13=T%FVNN1_1&%S zm6O#mSmrcC?tu z$w|%}#toac*Lo|zHT1K+yN0`5D|%1_%JXO1L&Cz69Xc349z9E(11K9otHI|5G*qH<^Fyih zwm;T0FDfM5e5M=N$B4?7SsgC;9WBCYsA)hweIfK6a;r^xkKVV7PHs8Z%j)!)8pLA* z7YNw!%Hiu@)Ua+D(?qR%X|irdfz!o!$_+wx$DLVsNUmn6eKwH49jR1KFJ!5P&;XSJDU zrh46_KEMb(C&Oru%#Nts<)w}V9s^vY5j?c)AMQLq08)b{KYgOgxQz&I{;=u*b^8PW zs@OI@qTOhId;oyn8@+HJQ#^ihY+T%axmn^=mm9mp>7BShFdhDqeG7MA`t(r2zDh-H zqQ`d&)y=gc8dTosYt{yRzBScf2beQemhe9G^%c?F>yov4Oy5?Ivtoql`b^qD@-DJ_ zM1^VfMjJSdNhpAN>YHi_D=4;|v}az>>^X4Y)_EO-%rSER=g*IjGZK@_>e;p;;usgN zE6P1bE67I`VLWn=RF$<^nk}EpeoEhWvO17mtH1VTuc_YL^1^6MAp1vG5vsxW1S&%T z;?!fTy|aFUx2li$$#d-ZbDSuPtx@7+ zarFk4kxwufq6qQK@f_;)4rBV(D0NThN}Ui#@h4JM@_7BWkFlBO1y&^^GijN<+#+Ys z-bqco@oF12t9}W_$hXKXMuk}U7%Ackw)2~JKa?<7tqXIZ6+Qa|?WX|FE>_HzGpD9~ z^diYtP3a4Fs9q$EH6cLnml$bh=K=#70w0Y{nKkryQdf^B~SPhaeo`~$21ppOs@4cGe z4p#klIL;E;o&2xtHgQLGpEEX2(v?Y7&&NrN;@O}>Mhg$}uf>zWL?`ZGq^?Noe(q}>NRvsSgyaRYZJUZo+6y!mi z*01yxnYYZ#h%S^;QqY@8zKFCU3;7R*+sf#Do)k1vqHblx^3*X3!>*Hqlez@O#*9C^-|OX`*te zMU7yeoS)`Hn|8anyakEhL(MfyOgY9p$5~mc%gYJ=b097PH%N?p=6=~WqwSyR94h+- z4bl5V86AfrQALkR`){WgQspG(+tIwqYS5g|P?^KR)a2#mzr7!7PNf&Lw*=GlXg?3D z;vluU?aQ>Z+Ir8GLIA)EWP%DQEs=Nc-o=rjv@W3url+UV?i3%G8$(gTEp#|eUbO2o zTtsWZK+mMtwj!)OXax5k8TMUOh_U$`&?x~qY#p-}!6Ri32=638nSNOsjRHrYBlCCGm_l$mEL*w!<+fxmJIO> zA&d(QqN{pE&jnsy-o`}5W@FI=&`xuceR?`N2L8jAd_Z|D6Fv!hx%8isJ_-hjrdu|6 z6vyUp<<`a3apQRNx$ikvM%i06(r%o?RCS{h(+RpRTl4pODAZZ1(`?K_LhAWrYz4D7 zi(I#K`DF(=SbJ>_+L=_!Bi#mE>-+4Ph&gXqHR@ZyQ2sRHU(n=wf_Z-8eR#FPQ(TSOWLGPQ&vxMd?BQpDT?Hc=Ll&Y3(9;50O7aI#8lMAuu-i{z1 z)9_vK@ic$E0H1fTyUzp&Kk>S%w=`N%mt>&{+W3`R)PoyApwL?08U_4NPEpX+?Zv=W zK7D9;s$Q1vfMS63@8uIcXY(6CK^0qo);y`4F0xpzq@eHy4GXlWU!o`=-EyG*oE`wx%N9O&fcyc^bHMV zF<*oj!R@umnpe1sJ*GYJWn(6w78NDsbDrW9HR2SHhR3jIT-OLsN=;&-GpN0O$3gjkh!I-Mgn3 zZYOriO^*x5&coCEQ-m??hpU{5^^t|RGi`QMG5rm*XSrp~t>UlA7eV7pJ_hkKP z+O@sMk`E)7+=rj_xi+R`4}4g&AK1kl5vmJ%A5!LW;lcK@>S|U~G53$-;Hy0JFxW-u z<+m|t9h*zJMm|HsGbhC13DZczMBH;1Y&_9W{G?r}etZRkb<# zv#JfQK1p1x!}Q?MiQAx2L;0-AD=fiRQ8`w%BwRU0MyHv(F+47Ds4aH}^2lHn^H!d@ zok^c%BZcSt57%(yc%=HvwOf&t6QqUeLNw|WiaFge^K4b<7SxiIyLMe}kNfg$ItQ>s zEu$Ny)OK-CT#|(R`T|`BX zImR0?adEFV?3|qS8IyW-%=vHviZCSTJ-lu#9 zq)9xbk3Y*?)R)(Bv$M-Nwv+<8R^O+*wwGUWl_tnKvQ(Nhre?Hq7)dH$TzrzAN0bo9s0T?tf;(KR@LzeMYL4GnbyPdE1P!gvlXWL2>nC&1aq;g z+)w%EUxImqtD9f_5(+KD7g(ABraY0oi556V1(+yFd($DIB8DBtem=^Q`g%*2*1Cp zL+7e*X?MuOhnr2+6ZclhQ;7YVXyb7gWtBlc4yL(q;R5pZm7*BvS6^R(fv?I7R|`~~ z_$})}9RARKGND~3gqfJie+GTxalpt+@_pK6WyS@$cuo;&T~ev_SmxwlVyZt+ROE4# zyy*#N9WJLk9rGUfo+&#vyRfiu?8p&Yf6;W!aOvL^VY~t%iE``rT%agrxv6GkXHpWdy?`QAanxHCWq|^dTerHV#@HvbJC{!$Lavm>SEOH z3GdyDkw>ow1HNRmqiOs2%H8?_Zx4^U%CC{4+r~ML4p|i!7Y8#75@3_>^rs$k3=Jz^ zj3q$l6i8ZWhi!?no*M}%*-FhAQ1RAz$-XL@(7hhhv{{d~CkM^^%Ix@^WTw0j_i4j4 zbfr6Y)>Rc5HNJ}Z`Q1K~FpWg3?bv^M>c*jz3F~4|^Jvb20NlgO@? zXDi1k2T5D-cuOpW7!(i^y{k-~>G)AK=@O?aEqrH1^!AZ4t`Nw_UZV@d#TiMS?##a(3YrlYqB|$KQ#1N*WZ&;XVtD>57w0dFA5Ss8OXNT zI~z)w{hhV>pp*Q&5aaRV`e6T{LNy#sC@fsT7?o=|5Gid?TO49qpsb(}O-DgPlZ{|O zy&ek8M2!d8TDzSe5(cCo%Ss1+?nP)nQ%p}cBpxpZ_7v?E@kCd&1tG%y5n9%O z@*HqRq{LUus{5&^dXznd$0jF@W&Yv0eV;O~c96 z=lD>@De;H#R9hxT8=H*h+0kDO30E-OT2=Np0mEbdfA#rONy%XNjK6Um!50AQ4>9C& z4S#z(^q7C7mS-9tLx<8|m4^B^`t|jNjs_Pq&=HQ{%AK8^+bPNS?faIhAv`|&;>8Qh zo?gbe2_R?fgZD?p#l`jY^*IEU?tz@Lve+lw*VE&%u@KzT2GX5VEI!&F1w@e`I)Y$f z2~?#X17Xti+Z)Lv6K|WkAlZ(4C)^G7hi9(Lc$mD^`g#=J1A6hEDgZ^ z53(;WFGEhFtlW58fFYm95;?`nS&3Ylt$_%Fk<{bg2`8N_~hyuOp&;ezJxd(Qh4afK@wvv$n@7^uY zDf#qCCWu3na~R5xn5^p;o8eE5UMJFsn@_m zj1AE&K8k11xd+#;kq@q=y3AyPQzx(+G3;sHv+{!Lm(3gRy>kr4rW||DH z?@B!3P${-_rR(mzUW8LD4aM%=?6IdCoP8_PVT*Z z+qV7a1gw%&ucg!URQkVFU;+ef%nb9#w>jGNc0PNG{2obDCG9)VO}1#_=|%WvPRu9Sv3lhXtb(Y++lIKOt$Ly zsc<}T;snDJUU1ynmr2kAqeeLnjhzK))0O~(K*)Cf#^+gG9aJW z;kMl7pOT95J12o+l&|4hHtnR<7b$}(O*qW9f6sTY z!FaZt>hcsF|LwQt8FCSwhnaP1om`Xa1Y3vA|8uP1&rLn@-ft!&<9W%b(+GzmrbEe!DGS9@`SBJVzv+lh|^L4HdhJwy8#s0lgm(1r=L zaRb~e8@-sQU0hb6UnFkC9KO#-@t@!GBP#y8sTnhql31qixYOB}KFl)_ap-lgj0H8rDvEVbJgFw$|SCeztY)rpJ#K0-xsf$!g+{g7vW^eUxj z^cIeji;fv@-n?;Mn%}a?^lREn@V|6@&&&gljeAt53oXxT{p2h2l@&T+&dQ-LtkL%Q zl4^3Raf9A$X{&eclQixe_nV1-0m-fpu5z|R@L2`3;|UX^X({yp=o&yrc5cw!Y4AqH?r@l4oHeu=9-D1`8M6&ZelV@qy zj&Otaylh<=yJL?$hQ)c!yCn|vSudW08{?H?Y6_i2Zzaw2x)Tmzy{0EIk?PexbA^s* zmcYS~uyJ_0EtBOitBeV>xxw}D^>H148+m+_+UMey7?*Ov%hWAoQy9EBHR&7Cm=LH5 zpFxx8k9Z8M_ffX#VMxz)0>LBFw2|sqx>CX?3Ng%(7$B}*zI>3JV1FF46LK6s3S`S# zHc`^j8uzQlqn*S4q0DIvid0Oy*$MSg>a_}D&w_JAsHmx*&eO@njdE>P-SrWNCf#jw zmu_@lFS}2hEY}QA0O9JY(1y~L@4S>_FN3q0c8asjc>n%ALCe-sUcL<*V^xQC;qPxo zn{G`_k_NL?hh5SGe?4MHs8G4qx11`v-)|xznI3Mr(!n9^5eolB&Jpz+uo0riaepKl z$v8(v1>yv>vf>k*=)>~D@^3>T>Yaq5bH4H3_}_zz*~e`dz5GuSh{a7Y*FHJV=+N$; zCU7whG`P7HwjC%}Lm@NP9wPg)oEEIxuGoyUDtG)N%IFQsRG}l9!Iw$?%9ZJhhP#2# zA!6XhsJ4uB6s`=V7LHuxJK=6e9?{P-1kG=^>Z7k(&~ECzmEqAFp)j$e|4-sta83yo z72xoa|Bu7d4jB9K;|7JHynpHBnW|*TRgW1*3sJ1JyuUkUCqYRHdPn5>5ie3S&Pb_D54uhZ;jjeM4R+F%}SA?ouysfp+rBGJ}zFcBtQI91hoUX4(7ojCE ztuPs-dU<+&@g_$1Ue@oY+*f-@|CD71AG#)4#`ky^DS^vy?M3KTUXc~l`PSC@^w0$^ zElZdEZD=k`S6}t3#FjeDBhm&!6kL0Mr=Fe$-vjF5+L3gKoRFBu&6(n!e-!YLwe*jf zTi_byhVz1pOM!4oOU!7@_6u2e8TRN#34IjrWgK^M<@w)Eq)xm|qfeha`)+ex1h*KcQEgQ&e^!S~!;$6xfBS zfvD`d(=s-VEH%>~;%FC6#zER%5KL^^F}4!^cVbJJpmefJhpG&-kPEJWJdN_G;Ob>BN`~&IW%EKH8rLXn}apM zM>Vo1?AAJ#a?RxQAg80Y=kUz#_7@Jv-{nxruenFgZl@6IJn6&hC^lMX!Re!XBA9)x zES-Sf3{Gy49Y`=yJwIoQ-` z3M2{A!>5W1#Xj+&;P>eVz5B;ub{PKxo74-M!xQ8c(ijXBJC0q~VV3uB2>T&&_dY3E zJB(XIyZ&(MF@mQ_8vuj>^2}S^s(tj=-m@-U8M&L&yUhVD;PCaGr0G_I7O||<|3pBHo0$lpSP3Wk&ZDT|5h{mx{?wxnf~WG1rb}nd$*PDL#>`z> z^Hp-f3T9ZcegEl7*Wj!+REXG~^9g9O1|^oG?QO2X&q3UW*c0eijWysg&7*z?S|!mN z2J6`jMkpBz$S=U_Q@W>&(M7xG=50yMipK_U}*B5^EC{`Wqc4RGkXF>vP;g)J)u3|AfazB0Ppz z=9T&8$omf0E!;-}TSr?9%j3&Cv-uq)f$n#X~^|eVc?kLE&zf(WZFtg>w z?!vS_bSm@D2W$bw4|lCLS8 z2I`BcFR1rB&77?0kI|^KLG?qbh>MA#L^Nh{zm{HkZu`P{u;D~iAW>%hE7fcT)lvJp%OJ>|JN$Cim|a-ktlT zmZa@t6>H{slQs45AQm>p{7c)CO1pgKL2}i4Z`rZq>K~LTL(Ko)C>$|cxNjT5_-K%Q zS*rUeyiHaz@sbJg@yDwIp{oo9j#u-KHoWHI*_jl1yw_MQZkta4X>2~zWMFIl2!?ye zE%5RJ`EtRLgQ*w6z>7PYi@LY9f`|l;t|IMyU}D0;!k#`&LzF?n!4G*0Iv<4n%0kDA zddkVoJ8rI`Ni}UrQ_i@D*>Cmh&U5y{9muDfbS*jfam<$V>Fi>LcKe}ZC_J7br%hUI z!6?~R)%yKGH)w0xml%*|{r&pWf#C0lvOc(t^zr;BNK}VRJw`fp15{qhubs||GNuLo zj|C!ooWS0)11fqXWyj2guUgDmIS&XqDsh%n+FW9&*mBkehPqmBaFID%xKCWg3||!p zKNk3>e2#tN$>`0bqzen*dyff%@(N}b>JU@*ZOu=?_yIbg4LXY5kQp#CbP<$>#*U6c zxKNP8X7Gr@)_X01+-BEG=M7`Tn~T4Nb?MO6T6! zuS!*cz!HI%DNH3ghOVWkw!ApE!AJVnFQyETRWKfBt(anugU)%jQ+Q>r2EFdo<^;U~^Aq)enC&LXsA|(4=Xz9K;KtlEx_cs0u>1BL# zauux=q*Q6!>Q}sGrW(xJ@gNgR4_sPPVG&0d*w|!&jg=p)5=OCQ6&3ZNmtmAuv0(by z+t)`B!rk54oW9r0VEtnVYw9#pxa&IV=;r}-%YME~+{P1{GDjP%SlU(!$lHZBqlEQ|mU z0lt}-^q*V<#?5)Xh9eS2u9z2GTwJENnDG^)rK;t=Qy2X}iyMY%VArDLApdBd#c2M_ zV4zyLW_ar{KBGaLY|wy+ZVC9D0V{*1e;-PblPgJ`Amu{q)}{4p{*QPqE;3V()>DXY zqK#OAv#;7)wUoUE;vSV6e|xZFfAD4BbXzM!4xgFFP1?(uxvIq2+W%I;n-}(ME-jX2 zNnKMpYc{u7G>c7FdtpWy2CP0{(>fj}ykyY$>S}N5H4~fD^CLfXQ9OaBEHKJo z$xiSDf1w%y#ipM4?(HFN5MEK-AVsShA^V9nf7(y=su?syn4km9vaiJ& z;u>IXaNn_i&%S+pW`6`}9%4!f|GH_HkL4`702U;T`%hl(V-KFskcrPAPB4 zVr;fYo`?-7uWB=*oI#!4J3nY$Ho{h?>59rm zMtkP+soA&)XAb>N=0DxPqFaN_D^%g6Ls!qAsbLe9B^gg{>(+!HYwp1icH&9dCAsvJ zQ{n2bNlAI?diRcM{JpL7J3&7K{OFAP+WW$kJeRYTjy$xpkC|4JPk_`|P)g`9HgJn)RC*PPa@N@*_u zQ^n#k_%Ty5TuhXY@tpAxIG8^Fd?VYpL#%9UY>bR0P>eQWxoe@MO6}>N{tX63SC`M{ zzCnwJe0 ziE#R@yg+C6q5(|L^>@bbp{U<4C)>Jp->Dn#VZ-;q{s#apM)pf1$<9_s#?PvCcN;8I zvJ=Y_1|>??CKQ%^u=0@6v81~_j64nmH;2_#1AQHD=GMzhYa^h}#C!q+=Np#XXy$)~ zrG&@o3d6eARpzQv2zzX&C&N!2J0{KK`4WW z=Hb;M(d*EAyvODI=euvIeXgneR?|IUucoixA1@bmDO|t~myVs9nP1-(18$lQz;3)$ zp|Q*`Ax4n~O(w}ULOlNUd8z(UE1S^;U1u;oJIK)b>s#Vk--J9r$g?RS1f-Xm*p zva)V$4UYu;nCkZY*{G;Nr7HCb*bffgw=bP8lxwP!U`@ca?7#^g9!1WQZW5O1tGiRK zJ(~{l9P|00Wl0vYW_DfIvA9gek$^TNp>*vUyv2caezz%FE-hh-Zt`A}8@V7<2eT7) zVsKC}umy*{zDF^zsY!d>?hz5Rb~|*J!p;s@#XuAg#Fp0X!(w23pmQw4WL6QtCVacg zwLlqBOPJ15m0sTq;7NmBX z8c_^u33^$RNYGcr%FwH;+@^IVbepjDiEZOeo5)-(nD}`a0V0MULgowJu&u0s1le)+?GVT>CE4#WOlRdPwXa`_>`3aK`xa2dqB|s@y@WKNF zgm(h6qnN^W6CfyTnnltaPUnsr z5xK_w)6Izl32?@C?8b*5z#+tn=7T12AImjn5t2`pOn{$X42@Px=f;0Uw!-l>sLizR zU9|g7tY}2jz`0?3{$eX00GHNCb|0Nj<0l>s_%iIZ5xrN^iLi}OaZNu?c=kc&y$p1 zccB{=!mbVarV((g;?n5T2LxwP{nIzmuT-c3@(ozxv1FL9uqCzm@x0J{e-zsAezl{b zUo^u%K`P;}TT<}(e4C-Lb@Ja0GCpmsktl40GPRS>W+aIQnyV@94c7B`ntIr$|K6Lp zgv3K#?~#Rf@snjE!c?kw_*{g|7=QT4N95~=AX(%Y(Iuz&Zo_>Aig`45w7{XW$PKHv zU>%+u;BU&PQa`ZM{fGbCJ61BGXXH+$0~ZQI8^@H6KFY{p>8gH&F5WBD7)y{*(kbRJ zb%g55gq*%56Tii=bii`wJ}&sN)Q;GKVxeG^Ih7-2@|SCe_!%?+-%%pn<-}_zEeyNX z{|gA*DOv@*XVr<@%&{7ZrJ2Oz0C>*?zYd$KtRF;aZ** zlxMk~^0gZkNH#dhV7`<&llB|XfY>CVVNCyhpR8_3fP#(=jM00H$$*%IueAL635Fpx zKW+$Ci;Ir;Uy=3`o>f#?Dh~n=AdIsc+r9xgV8vVYJW%b{xXxF;FkQXbRKgE!E<6PK1Qb zpb6(F2)PTW5Rc;T^WL{m@pX8S!h4|~OvAnX_lEQ_^#rq{1aTp9{a}dGgu2P#100F< zu>d`3c{{N`=$*r2NdTg}%Zl^#US`?7SF^64@Lc7J2-wg{z6RR2DCzvO$2b{$WiUJD zJGePHUve?}cJS!YV%K1a2gp*yLX$T! z_iy1I-;{re8rlj*imxcUsH+&0M3%KN)QUB4t*y96vW-g%N?WG=w4qN-fZ!D+CH>1~ z96q)$SSJz-VR9MpyM+CQZ&|mabd?C}fBbew1|gwkVng7@80Lb?4qg%5Aac{_8`xcg z!j>#-V}IvJoB>gBxtwn3<)uW8yKvl8}<_SKMLYT%}`!@Wd3DNE4NPBDnx|;b*?S zQFQfqwm!E$Xo`b?#cm~~s-p4o;v7Rgt<|3?og2U`=-u{PkN|YOi)WO3|7ZHxaBr>Z zeBDVQ_VNjOoqkD@N@lfda1z1e5_Z!rlC{0L$B?V40udBJmnlT$kbhXjy?KfCc_W-r zRe>ntA(tu2%x?VZS?#s#eTFd9QbtSZuq)Vyji8sFOs`PF-;$H_*)qL8??`%!3D6h* ztWbpF2HcjY`d31}Pqk$DJ<^s)!+GQVIts&oCb8>6N@x26#x{lzvRJu-dCthv&qQ+V zc~ziHhVptiFOG{>?e!YXsQe=}Z)fVK+x2-h@!qQw`!52->I}QIKMT7(KV3k@H0;-j zpSSPhipR=#m(JP^?)3R(OHM&irA#siH^e=ooU)4YU!0C($`?RZHE_e+jD0U~=MLeAWd1QGnQ@s!@2ORlf&i}qJnnX3W; zn846|@}y$s(gMAycmCpy0w6&-?UDzP$1!m#WrQie@v^K!m)qhzjzx*+f}$>vrWX^vKcl|NLv}-_ z)qj9TT+<({e@O(JxqZKuCCk-UU6ABo>gykw6r&-=(D;Uh-Lm9fH|mkJyAfu;3qwE5 z&Q#KpdZ zLywnW=zh(!oAgfcsOUjYe&StyPh|qXamMV0?pIhLFA`pUY)1pjUe(Z)(~&kA`tkl- zH6$QzEpKNPf9yqN2k0ZMO=e`}f9HVNxRURR%D=DeDK?h$ODL(S_p9xA?*O!cV!Ds( z)SI1nhYQvKYbnj2I=m3V-~)R4YJlZyIPR)+NWkV1?j4K44fQY@8lpho`v7WU>X+d| z^iizLDA(f=a&U4!s%GHWR=#I}#o~Vok>=q)j4WQsQd@;fPNtcJ1cm*Qy$W}Mg+OH` zeg*)6OFJM_d##nS1FKa9frq=IZ4;sz(^LGbSjfGEiq%d%2IW{sCqDdK*D7;cA>o;82 zUO{jc;Dx#0>|`{Z);A(@+c}!u;kWV6kssy3*ca2Sgl24j=#K^I2}XbOCN@lYATt30 zT_Ki=4uV)jK9to?Us_Z{b9zfrZVt>dIT9m91I7d()6F)-?U&hkMrmMul zcd)MPA z-lch63;}qvfCZLhbOT@JUab!1mKHq7$SAfH^wu$-6;2Yt8|Z00iPwl1oK@|O>ifDr zXP5G~`kI=WtgVQGkkdhu|KP6S)QYyNs;aKuGk3r(;LDdUXkM{2ryXa_qKy9GL}3GC zvF*|>S`0|oYJQaRZ1Z0;js0X5kLadMy6=#4FmT(;VApe~F;P$Tz*Nz{;{Wu&;=c{Y zKL7)5H-J<{!ncPlh z(@%&I4~KtEPgJn&SM$Z>Wd&tn`;oaVrRe6!B;QA39%3N*tRreQol zr(6Qy*{_gQ(PQ7~M$Ppx_EMPPWs<4l|Bu5FgjQ=2%nn@*u)INV8kdE}*{H>MDKtL& zMenb*8EI!#%(+%50w)ir=c=Y)hS?{_Q7+ouxqw=Y7ZK>F9zgrzI`;8|C)VzE{TzJ3 zzcVTSVcyqE($dJ~u-z@kWCCB%)WgqKwYSV(4REY+14e4^c5fC~$pjBFFu;#pTFbXC z2Zotj-Pl((Fa)LKC$en`BFl? z#Y+F>V`lD@tS(R6FB?|oQ&;BUKR=o`jnz?SxVg5Z`oG%8rGFXGdUH?ibd!qj%#n0Z zt=hmtegVXW?NHNCXXCFqF;IKiO|_o-_>2RU&A^Q1aclk&PrDMfC3)CNG~rA{)Jy%}Gz(e&KA$@lYv zWQ#6dI+!n9Fb8ijp2AY%cq{wSYJM44o}ru0JX)9_%W{32Fe7T25Mw@Lf|W!P?5HIy zlij|ujEg(v>-49f?|IKH-mIn?bF)7}?$M`x8+)g=kw+TSKso^Pe`fiOKMc(U*AT6a zrJ2gHbJ=*?2Z#@ToYjLd)=7?gLbZ*$#C|297P*q9fx!T_#OP%|4Zi+NCw(Kgtk?Kz zN=hY-sq(Me;5{vEUNY22?R>p@V3IhnT+|uZaHulAvN?}?bu9nR++r{u?l9tEXY?8) zFgETYAM9}Bdvp1--#+Xqdi43zVIaKt|TJCamoVt;YPE5KGwEL zu>U8wlK=3J4Qk0)n3>{nndI@XH$K1Eu^rnuKtyKe_g$p<8*(vc@vM|}@k37ZOI{74 zvvPAg2zv0+KT*@gKnv+VGj0}p26It*h;-%Af5ZR3lWhO@LUGTf7<_x~Vl+uvLL>>b_8Azr_aoVtW zVjnF$-Wso|r~@z!jNk(yQ*3d#^Li;x7>U2DuSFXe2?#04&TC~#c4Z12qLA)uOa}*- zk2!2QJ%o2 zTXX{O@(o-OvGt0#;7wmY!OB_yTCpp8i;lImb>zrZn!(!h2NVreEvmR-lJ<`4CUYLU z4=Of}(TJV6Q}EJQz*PCQPvRMdbG#YBirov7A^Q9hUZa$tX;G(d*_5P=*X7v>kp2Sw z`WCNRdT=tS($yZGMf>x#1dXa1hyX&nQ_y_ zAdaKDL2#s~<5Cc>3G!7M(Md_hU}DAv+(&%G=_Dn*p6)|)v#I33tB6qZnRj9x)As>7 ztZsE^3zGf}#dW8^% zCZ<@c7zt8jh@f^?b z{Qi00+i@RvyR7vcKErjL=XnjEPVp32D3~LnE8>r}s2AzAOmEQ0aW`MOInC-Z@s+|n z)L!ahaz+Erk^BjjebRQ{Uf?-5 zxjak8Y~$ex!BX@XLS=m)j|tP1bsiYm$e(wFvV|*QStch9S5sQ zcuAY}E*NQWT;IxRzJo{o9Zi38eiGY?Q2rQIm|_NQTQ$nS*rGcf(PE~w-+ts}=Oz0z zX;IT`lXvUeuPh==G?EY?i6nt7w4Ph=J8B(n0|(*`Eql)PylkT zkf75t`RJk;VL0%pD3Ncar8nMfKbe%AY(N>R`qzri;fzLDJ7mbUOj;c{e7FE33>>YG zJ|>d6Zhh$Z2aK43a2P!I{U~QV6pz!lr;;+{vl;3)yNCh_Fz;+Kiu zfsi<%$9Lb|6aQCx8xK)qEdPF`xfeiW0eMX;_6ku`(NSRv2#K_Sdr{6>TD5=)^dXux z8hV_EgGIi|=reBwO&~G()})<(=Y4e(P2pGiDQg(GNhPAY6Ou<)NYuXo9~)Iz4Vt8l zPM|I>(|E;A?SI;Ve7%FfoUf&jT8l-DO0Tu9W7y^wqLh7mK5h7DqMvb{-7d8rlowH; zDy%4p#;f5eDPo}tW1w|-EsTFJ{KlKwBFL5~<+k`xB1TS=)(HuK{fsDr{Ty(thd0Uj zo>WY%q{ojpBIOjV6kNU>8-4Vq#nh>C>H3>!i1PBF@=Yj+b!k6{c9fD)Zy+wMsru%& zbWM!dX5`NhHP=Y_y@r^$ppcNf8uDS@;gQiwLjisryYfu*YZw=z9{F@$G`rGrd);VJ zm&wuHEB2!dR6=4T3;P*uJqY}|ManiJC1voqx@p>Hunv&Y^<_6}f~Ck1lc_4pJW%Ps zY1=pxgmna7N)$CNIHNzduS{0$(YRX0!Nm$w9Vd;gQkIPmcgx`3Gh<;hXd%@ES5#b7 zRC-38M6yMs30f(zL@ZROn1U78h}9D4u|1T*5-e%6bybjH+JpU<-ph5NCRp{&{@C}( zINjZ=G_-P)sgJL31Ga&BT?BHVLP5BCT}HBqWsdCV?-E@Af3WhwFeZQ%v1d%N9`Oq1 zNxq7K_O27@t~yogF+}L1QVFfyb@cOX^zXvx*o|GrWMFL#LopCWjWYbQjr^mYOGHJv zs{5l$%F)SWzT<1*E8>8zf86*Sy5>n051kA1#)EO;eK|GS+q9zmFLAfSLP zg_hH0R{?mjI@BE>!zdF?QIG*(8Ylxh2}Mg=Q&V&7!_Ba;&w9`OCy?nT z9c%T+u(=>o(LdAjto$1?r{ppBvr)H+$RMj2^P84%Z>>A;bt>1K@fh>XM@&L?V|PJ) z1olRpdB`2UUF3%<)qd3X(r)fa$WB5Z;X0*b6RBz$uSzw3DSK>tBgZ7w)Znkf;jSZBT+dcn z>ik{H7%o#8zH4=^Vq2x_Edior*>?@6>arW<`;cD+`VupqVEk)HhJoTJ=cNop#CjR9N+@pvG47ywr+~H$rH?hVFYxpBoeOCyD#KU-{ZOu@@byI&&47ySKTgjPh^^k8>ZRY1(1Mo@mQUpQIz8U@F7!_EJnzdZqWZr%iE%or$1uG_6CSiL${^HOM7=cK2#Qs&Y2=MFIuTTrJp?XD| z#Y0zv?)?s(F;vNK_*dVVoXDLas?`GHSIWZG6KzQJCKt9m zZz??zoI;7?@$frg98AkPRR5kp|>{jRj?BL z6o!8QL8xj~+*mrQn1g~AqFW4-3zpT5C!-le7E+pTU+MIFAT&_4*!jt^EOcdnJKb)= zNCS2vx-9|^nFk)bKkksW>|AMOdb)rK?E1Qa>bBIdj?+7tU~D(Q*vC|CZIoI@dw67{ zW*{= z(uI(SOw0JTk>Kavz0U12xnm{PtG(CDZHv$vK^5P`wWbOEU-!g$Loy~xV&HK)I$8Ks zfF}uXTA6~x%&wE)t5PPWlN- z#VI9Ty*A(FqX+yQOhcbNxOwemnnjHjTq`h(P10tSoPUe~k;Z6uh4+`^UebRnqQh6; zA>f-^z*SaAUqT|^JF9PKc~g&Ml-)J_id(dwx2W6)BP1G30UjRLUxQ&--cfu0=_Z(Y zENtL8pTIT(24Y9`%RE^8-kqjYdj7CAeXMP53Ne{Pf^E=#1oYk*H2rH|7sNJcz-G6z zo7K?!gy>cHwXm`B}EEYF)n}>9#*`6q`32gbfUUFX7H$ zjJ0VjOWSeEwPMmXWabAoOWvql0aHO#3q8e}H}JyDh>ID?!ZSu|NlW2aqrojt5Lng_WiZFYiVLq6!L zuZ@GIwJ+?CA{w$@K(h}#~<$7hAW>Fcol(5m|qoaWMm3|I-6w=wimZ$d_x+gbhC%JgJ) z7IGv#$0QoK!h^_9$=a~=+`JhfkCol6ymN3Xq|q|eNqhIn9>Kk^Acpa7upoSCZIZJJ z$zHrOBG*lX*zkNApcf2_oMZp_E+hM+XjZ=Fq%1-j@qBUz9Pq$^1eEWIg|KYir(J0# zdDXlRkA6*KSRv1(39YwQ>pS9IkVY~MJVI^05r84XlVO4_QJMJeEl02=j5{t8BI{_I zWc`NKtQ_bSzixn9y)-Tv&GCUK2}^^H4x@)mwmy7ok&x3ict+_LgXf5PQxM=qvfD{g za4c{#Hm4re=yrcyZ;x?aLD*dx9nkVY0F?0(xB_exzRQO!ptyi5g^3s{@~u`r6OyW% zBdv2w)U>lo$M09du3-jq`+XB4vbNnZbgFb=`k`f=L%;Hv5qt*Q!?HGMJFi7GJgp<7 zd!)-;1>&g5PTMrM*wBHFe(vv^MAoQ?ozAIKeQ3|&j9%c%6wh_st}QB0A4L- z*uyaaxmp_d|>*Xklm_&AnWn=aj z`V)9+p+svKd+)(U+EeguD3g7u2^2!bbnT$}ufCcd1u2L=HOxS={}_R>%36%vc6$_O zCo@er1g~C*huBKuvRk}>9%12NnPYFK8^$hdT<>mFY)(MmO^|4E-shonKae{$jL@2z zXVy@;Wv=!$XQ&w=h{NCY3a~pAja6|^4f{sqJHU|s*a8(2 z{hc;hYoOQ7S$eWAoZbg73oqJ#kD8lHd~~o#gGFApPRczzVVeC5@qI``$ygm&!~~>A2n=;y z!a_n;A0yuR(+8k+<^^Tu=WAI z{zhfniD1cc_!#hW`~_2tAL4T;OTmqfUvX7NF$mFr2ETPc7=SP%AkUAdc5U0%f_0SD zhdunV`DX6uz1+8G)Q1%a`+^SOA7KUUMlx5vFzk8&2t;Hz6Cr2~S{=3<+C^P$E4h1c zD~OLgc|RfeJ7JprUB~<}E9g{U+?`E5D3Tl>7x$sM>UW_cJei})SHN?=4hi2=I9 zqQeVp;NvwEj28B44W@>85hxX{tyQI~{f)*qhyO|<-nOC|O)^a7%FPH}N; z$dOX*U8Bo~fV_#9geZahYiyDcB<~^T)*b{AjD85xtqNJMB6BS)r4i{4f0Fc~||#2z?pka%BjIZsz@YY*eS%jdCYT zJjy!#cO@kRZ_}1ugfGng@ZEWJF^6apzbwH6f~lY!apBn??<40@^e3tkT+~1NBIziK zx^w2oJ*o{b_l+53(_0$|ci>mL@LQI5+eEZoiCz=9C8}bv2>y>-dO@a5#dpDm z&R+e2{e9w?>B5(U| z^dAR`{dVHq&oc>rzx?Yz4i>v{?_hYj-N?^tUgxvD{Xe$MeUN~4#Uzl~lJ6VtEeCC6$M z^I}b{#S`1<)*GAph1t*es(r^LUr&{VWS#HMR(g%7GXzo5gS**Rxb56@AKBII9X&rCFo!3A z#8E!)9{n=~+d6(a_x}yR@ZVj>1efaQQHnvu8*@M)-9t4~SH1ze6hRnH^-p&ok=WYW ze*DDqe999UbQ&7NhjLTb{BeAp!!tw^U@XOkmzZZDzzk%sPI>~?38m;b(@663OCeS= zXC&!$>+c+d!Vp?CeISI4P%+@X|IEdwEJiWTse&>x6QD`QOki8l#^r78oyE%+pUNO_ zShoAcnm<~1e?Pc>*-`hpnQ}vl?8(aME4RkCU2v|oyHymD;}Y`l;i@|azl)#BILb$Q zXALpn+|HZ3(X>3J=D_yd3ccqscb(t&p2}FZd~rMGs&)6lc)_&?R$zi-1n{T$rB5F) znUW*)yAB&WdA%Zj0?>bhq^!#?{x5Y6|1)a#-?g;=3oP*es$0!?<;dv7 zGv0o54|)75boR?WJb>toW~ zUJ6LM{c$xo-iI_iG3Ao$3f(eyijmvxkhRZ`z$&jsUR!fBmBm-bw|F7aF!|$x_F!au z7xIa7DUjY=h7Dg+j8 z-Z7_?1%w2X8zgxYISUiH{fb+S5;YTQDuy~X-WYJBvCZcKFvT$X@wr=H*jXSMqBcI1 zH%ad;w2=)tfzKzJeP_yD&KlQxnDfDMok3FR8XCVU>&{V^w#EIak2kp|Q^<|O*hBOL zF9K#8?&V7r6XSMn`1sspNTIs?G^-&Oa|G;vp@=tfDB`e4$t#J(TfGmNQ`Fvf+BM*LP&Be9;V_f>Sel#pVj+uNh?Amayl$@H$7;@Qu8^@lH+R(2WeOPxY;+`budRcO}reJ`yy zYSAsGU%uw~;(No@+n;rMm-ULtN7)DajyPI0hYeD44z@_1`1?c03rzvcOyLhZ>02Bs z{8XRuUJkt)iu7M=r#Cj$>{+z$>-L)pMLM{Z@T$qvjhlLS_sr6$a}HLX;Q^&m?Hye- z9n}iwyiU9^%jk4{Ar5jUeniNk1^GthBNSF%su-IR|Mqs>gg2bV9+nebwTty4W{(Uk%Ee2`WV;RS;8?4CdYh5yFb4xgO&!-*y+pSkP*ZR*m zb#A}ew9YttY?T8et#Q-n&88^>ZsAqVwNb8)14Xa=8^)hBt2H$oOVJf#q=mTrNH7bO zR!@mM)Rj+CsSso5mJOIuI4a_rzO_bv*Yzg*u0L<;5VJn^goXb7%8Y-MrOv*U&FnwO zx39fbnbp4n!V#`mk@rGB!Puika%JABMd1}vZl_FZa?q>eKP~tKgWQ$80{+Ei@j=4W zIE`586|LyC)|4qpOgdd+#Af@fO8>seB{$)=Atwo|D)YL0yY7Y$?0Kh>BMMt=xC+fq zGC$;8bo&VLH5L(>Jdv-#U5?V1(ix}?|L&00;lxi3&5EBGK16J|zAf{%x;8^fD5Z4G z3Z6&dSim(=ItBNbA28AQIBT81NB9tXaC4nliKHjh2NqP4>&p?++eC zdDpgYh?)*@7{_hyw76tPSR4^H(Sl5G7i|*LWaJ)Nu(OEf@VZU8G}-Gh(kh0>I21h+ zQGVV#GC|>QMMt5Eu_9u}H&2|KfBSOtRC9&{r~7z!N`QPpz{iAv-)&3zsof6O=zE!V zNgkD|%%>m^BK~B^sS&Hr`qXDHTV9H{3#WUghfAWS4=FxAzEn?u_!xN}f{_OiQR8@R zo~oTt(<0fJDdX8V||O~$APPRWWtHl{VA3QNsKDyY3z}xpD=KQ=?yDF znKM7?!|p|ViRGMwZE2oJC3%bRCgb```;og@ZsE|odLdK_~Wx;A>> zLF?!rADSre4J<73CiCxnLd7gmvohnUYK2FOriv7|S7A${&uZBE{iX`?(>m2W=WfQB6-s<^Uf|j@AHR|DWgPI zULR8D-f@zOp0WX4Y>Fj@62ZQ*|1{u83g&oyAz6#2A--F>A!e++)i$HS%GhH_nRtfL zn+u>L%m&_?y+so5i&Y=tQ((geuVh=A9?J9wOsgr);|YbL@Y>;9~%(KHj958|CBT z1)RnL)Hj?;tiWFFg6r_<>tl2D?t1OU!o;pjr&6gJw{PeQlTf2q15oEQ)s|P>+JC8) zX(q1C@1*ariXl-ZgQ^v79I&xN9n~f6%#l#rF&kTa^*zOsA*LF_3!5Xt#V0fQjR!JILCS<;6@QbAp@kC6xLH)?*3JZ3*K zDYP&J^j>nQYDJ|rxwJ*nk5pjuUaICEKQ(y3^vDC|)>B=$sIUQDfC@vLZ}gBXL_MCa z!cPFLWJWhhMOZ&u(l~?|f9DN#JhJzvL38Nf(+wdxx8#uCA`24O#KmzzD0Vstl(4 z{bAjLWA_u!L|1MXVm=egs0R{JBvjQ3Nig7;al*Fhs7P_Gr2632Az7O8#+>d1^V86_ z+w0jvq)WG#g}JuG;Op0~70*N21kM&(?X#hxs6|H}2f0qR@aWZ4!PeT7E)k%i%6y$M z8}B4hkBm4aR-@J)f&lfP-6OG3Sk8HZEQF97tJYhj z5PMnUrLK@a3ifkC<4=~cdX$z_K8&W^gGJE1v_Gihafe3f*k*r%mDMYCXAlb#KUT-! zUzlrb(XFToeyUivL_%35nKAy#RX;E?`nHeDmPW7*Mw&!;P6e%l_)6c<=p+(>@dLK{ zQk&MPF&?;AfciB!D?XOD+~?!k)s_s6b9Po~49f-u`%z>SEvTdO@62ql zD$^p;X)Y^_-dAT{C?LGJ7+`={u<#0kPlTyHvsUz7IIOTVndXdx8MeBeB5>1%iO&3B za`z=x!>k6O_4mltgdeE?xy4byrOXeM7EG=Xli2Vfib-DqDLG!FZ(6A~f7lO<&hnAhj}!IA(Mfrd$^Obc!%rFjr^RJj3)`8+%ZF`0X@>tDpL+Rs_c$ zr9ZJ`1a${x?%$%w+9H`obB!aG8T~&mH}U;}WFej^lR*NLtWhL75@y_MO>6lviUhX? zD}T~%DqG&E^pE}|a|tEZt|6yX?I|>fXcr=6!k0e{EcUG;t0e;_wM_nnuF!^ihgd%& zst;LWdV{$dNrln9f3ht4*-$WHP*AQ2Qm(skr0aU711!npw%30+BzS**9NY;l;g@s5c5t)W$cP<o%R)>&uXgyaV1 z*WaH|>8QZA#c1B)G!9-LvRPPKLhVQ-_lmsB$&}BBO|8>56ZhMb=*>NMKVprYh*D!E zF!$v_JL#%D;=4071v>LA87E9H80F~K&<4>fkYXTFZlI@k%d6WW@Iuj@6KclH8R5=N zoFfEwHa4picTp?j4D}8e+?R0U0MNSJW0XNl6L#yX9c~Ri#&5rU$|*-*$lp}(Ka4(H z4p0bl6H7#$cIW7HE(#uS$z|syI+IHqJa%pbB$fy&amiH(IT4nYUI#vva~Fx%Lfbp$(V&(|GYPjo{lHm;%<%XnWKyd&&h|}HVmLwcU1_s9BRMN`L;5A6MKl_ zvoHz)(VM$|E+Z?}kmS;-yXY3Cu`EivEWQ8$8;ivXa zAk)T;!^oo}yyNq{f%!>q+j{y9Ic-brmrN02q9Lb|2i8r=&c}Dau`3BlMm9CU;f3cN z8lw~D*gRF*l!j+{HTC-fHAQs~$LpaX`x<*oMx!>#pk1S9WP(&g7^t&5!bYH|R+-z& zg6SDoh*gMS!Gx>?i^3O5wI*<>>()y16#61M46O~GOxRs8{D6%mK%cHV@e}-@k`-(&*6zwpbz#9PB|;V+T0BTG(OglSq)RQeMy9D zN^Fka2{<`eF5@_z4h2gCMjC`i6s!Fw`=n2I-l(XFqxyz$dV)1TR;o4_7sqRqB$b}x zF(A}GPh&<}Rs*zPl?=yp@CkTcUN>apy4D#GFEvA6@JjN=xlJ{BB5d|cD5@JhTQoNW zLgZK!4#m}nB)oSGTr%M{^$znW9_6plwJ*x-z9%_q&MMUryByN!B3l>N0O;XGN3;*j(+wg*L(T zm3bm1FY3D;4xcG4DH&G1A8S5=Wmk8Rkrq_a7MD-F^~lY68%v}kE3tzA*-2A(^Eg7LFqNZGCYKQN)Kn<7kG`1AOMPAkHm|vwS`Ux-~1oO(I zXSc0X0|}~TF$&oyy(0O%JV}Lc%poU+7?Eaykr`EV8!iArq(;o)uH_3D3G&X!lx+qZ zAq$)sAQcf#zS6P{M8T&Y1%%`c#g=&@x_Wx5S#4wppV5>SNq6WCkOc@tZb2m;io!ep zP=id>07g2YMtrx^fK{m@v=Lb&inmrqW@d~WmQ+}pH5X(Jpbw89kkHbZnz{3epKGgS zd_0re7JQAcU;I=vNfS9Yj$uenR4Xad9ad?=)H7LF?zJB{TPpEdkXyv=5xb^&4;sPZ zPXhO}%d+L!tpq_&XLO@F)GGZLe^qOnI7L&XBeN&Cwf{~<#~F6D323CupF=CWs#iAt zhlSM}8qzi}a%j1TlnkHNTT-*e6R!xLwu1_e=+s<$Bo4jt_4q4i?NVkjX zD(|F({fnVv%e{-kdK{wUYSZ=ysj7}QW(Se20^6W!@>4++>NA<{P(0-)!2uC+LX^iW zkfd^d9bEf`0UNHaMLRr7KU89o=^b|6w@#a}0R)9D4*~)d3CCs3$yzZ#Sq=p@-!tPw z$)&t*oGnf{^z3Zxb$)7x6U0j#(_X5+J51a@;>2wlqaFRYp~-79&KAC@HU;ghox9Zh zh6^!sy2xr6c)V7uWH41f%&OK*UP5h2RCQ(W#VMzIvykNaJS34JNF5<`0bDtK>K!4- zQP=K)%x~H9c>7XK!7x~H`@`QW>G56ehA%fR4t)(C*)MR2X>jh&Gu0zOC6V0g?;V;I zz-sI(95;z))?SMIx@%uzgH_j@ECbSi;c(P&RXo)vQlEg=&TLu26jiuT~FcpX6CJ^m+Q`lSI|Zpez| z;7_JMUO`*+k>fQ~tYZ&xrB^vdujiOVIgsjY2pyg+B5ZKE@4tz#K?mc{t1?%Y2-?S^ zHc4xv-tNnw4iIr;P9kU;aQOZ#%2-&v@Td3kzsyU8)msKDGJHsDZl4U3m%EZ!pQcSi zaWr^45ipOYh!#YenJcDrWkP(cK_9BwSkOPbw+LIF$nmT;!2H5QpS@71GW3u0-*3@u z_t+}|C2rFeX#!vB$9*oJa&e_^VovM9e;PHa5BRO7fNiN-kqAihJE?Tbte*;_b2TJI zcr{4xLjK??hi{}aU`SDP6mPd&o}7S=96h@dZ*ENGG$8Gk!VLr&vt@evS!M9?YKK6!u7*W$={ zRV+U>6^TEehRG9#rEh3140PGmmo!fI65Vt{O2Yn6$C5uIeayKBugU^b7T!BCFLc0i z>4_Pb{^ib*8Gldo1ldrD)qXpLGRinh=p6MD@(RR!v%K^I2}dcdy(E`8AB;WVKF(^j z%W4SC5>teGds%x4FoG3&`XI%i{Z4htMLiq&k{AH=U&G1C4OR&W2}%%1zt~A*GNJjD z>02uJzxR_XC1PYPC^a1#Ke?*JD2e##(wG< z#@Vcmijv%3Q579TpQd@bIVbO2zxEZ)6yyOG>qjUx_H+0yp@yHz@fx}z5E4oX;k}5KjHfZBrc*D05F`35=Ll#01}y*B+eAu;9f^pYDsBR*ftch446X1#2MOy z2%BEbEw2Qf?(d&3KmU9h558b_uTK~iZNQpmXR3h+Gn);6w(Gj^+{fD5{7uP#ZN?>r zL#noFO_X5!xH#k(E4me=rkXB@hSh^sv&PPa!3^&<)1QYcVShX~B;qG&mgG{kp39ly za__Y&SG1)H^HVqNihIN#HPkAR9!zLEVUz~&gU2gEtjuP~`~1!{fGFwoyf~o{(UM%( z8JFCq_TVmu@BFP7c%~flAz1rZGWtpBPks1yu&0z{ZT)apc<#V26BL7rOv%_2825+Mn~cM{n%SZTn+fSd#?qI93N zG+;G!YFK$&sm5Mk0=H{sym(3o7m!FEYn;0c2}12=cOEumiMe!3iPBQZO)mZNM;JJn48me~X9!{|oAEU75vo3r)SF%Tm3N`#=`upA`05co(3aufIz)E(R84w-4lHe)bzR?nKnHLoZ? zK;H<|lcRt8r2CfY?L)CuyWK7mvPFy5-Sf8g_UjZc242X}b)TtCkao5MGAn6AVvp3> zhm(GFbf1q-Ii5UKIzzJd!{FYC*341h7qiM=GaY!8p!p@Sw>ZF?B|Rww0BO#1nu4IN z%WryGqXPsXfu=G#HhNHwS!BB{u2J}o6-aJ3=Q zG*V}du+6#ukwYOSSK;B5N}+=CUy*ExAs?3V4_f}sdN|hSqkY5R`@sO05~dh$F9syt zmvMGAF~ePnq0FfsoiWR8f^rGXn%)}}Si#V)b*1Hn*t7{fFUl~gKNNYp;f}nbngruzDSchw-wSm1Rq{ELryCz z*#z5C(E>wGcuWR@EW^i5`eX0iyVvqV(nU=5#tPm_a!x2I6M1EXBnrb0!+VS$6Ojsb zO$hSPw=;A@6G+7S(_egHh6G2A-3>?KiL4_JS%clp{NR~Ez<=s~>=#$#t)**Gep~ zdsLsw8mdxx-emS^UR2)neEDz zE4HGZ#=-kG-EaAn*8O*grq{&81jkL$NC556(3{=j_7Ly7nk^0YbEManvR`L zsV>d1;o5#((lfmNgT0;rmxj@FiigFwM|^i$gChCc(wKW~c_<YDJPjY|Pz?JuOEPt2GbmN+-bf{#MhicmD*|vRnk@xj|HV&wF|E8BAh4-%hknk z^R+&gakPO$RtTv`d(Y=6dT&;|nhGXgw7M?9)4O3%(@VB2EHu=IRGLBW-Ja!uQ4bBj zP5L7vW7pm7W#c^?jgtf(wRt-^_Cg3?Xvn1pk%bzABRjkc^B+Fj6`@(0VaTb-nkVv} zQKG$>{7hDmZ~-i@_B2aqF#n5%CD;%#i7vCi^A--Qe?*=s`YKzStE;|l-$3<_p4Wa( zTYOHY86O*qOSS2h^4mJ({W+mUvcM?c;gN-StU&cPc|q4oD;(T`*(^>v#6BC9Y+Ou_ zC-f2gTy_r%+H7H|hg6c1!WMoiF{x&OoteXpuG5o_f0MsN#KZtK5rJ1up7<9$wmGdUvuC1F>dK3VMkxu;79wo(!D_s~r z4{8NdY-|$0i9)7U_CCt0qpxyMr_+SyE0Hr&z_~s!;X!q#K=D|`N9}8UDQvvQE5yR; znaN%(eTDO!3#-pw58=vZyHcuo-CpjH5z^IAG0|!ZCYq#wyq(Y6JLNBI5EJ8_tzG|6 zu=UZoXXN-@cfk*=kMXSU?C3D#{MXVyxl@94_fV4rmh(E#OjA1YzI;INIoCBzL9k`h z_$Mo6?+7y-xu^ z_)-5Y4nEn=9RGvSBy*;(6uhea#t9Zr<{MRiZ!pP1&NKYC!;G~1xAIip7w@Dl<$b$P ztv`IPutuBLe${QF1d;;vROEmA$dt0|w z<8>Uzd`PPg2RC^fdiyVOhUW$oEyUnsV$SPQ<0SpPp4Zg9S#nOmz|Vxhat#G$;fZVb z=Xd5@Yy~^x^VQg--$K8fD<6|9lrYvRT=#Gn!&yR(*xoNcXfBUFdwiogExN{hi~r$e zN3xhtcAYv0f3V3m_RIRq6(?t%PIfOvoCG^le;s^|s!pf0}&HuLw939~>1sSY$=vB9~z zXH=@}8|)k2IY8Kr@8bBiJ53SVi?a9IQ=cBS4m1`rlfcSQtWyF6z*}aQQ`MB(emcoJElJMq#@F5 zZ-I!R-7ODMMz@B;hu9|nlR`eEMu0VIE35T#{LHm=bw0Mr!a^)9hKRr;`nGFa zM|yJ*$1$Z%A>xl6{FLK$cemx~wW1c1s%pA6LajJ%&v6>vFa;=@&!=2~UIQalqB(A+ zXkL=2y$~9SRL$vW7h)4jdX9{Y3^?3tz1Q6qe5_&+-P?8kE9bm=5e9kJvZV?o3PX)M zl}Uco>cCgumdVM=dbE5Cj*S6I*OjLYT}T!!cpGvoWQ}6ruCf7vVm<@O_MDRyXFf7g z7|R+O8uE{P`BAag?Hr93Q^Yv{687iG+1)eEYSl64pINRR8=lC~JzjC1=KJ7LwYHFl zXoc9j74X0NZKA`!e9Cs#wrCF?Y1H0hcrZGAq>*!*gn_=kkYoLo-Xq;R%JpgXm(nxi zm00(_TfOIWO{%U(3+I&&g;CVX(<&V~0JZ|f+r8$T!Y^|{z1b1AcbYwYZf2Y?qLbP)y8Sozj-6 z#Fv_PTB1w>BXJ4LY|&2k_kRY>y`W@okN<=cD^Sj{uwO^BTwh-J2GJ~myt?_m^u=d} zoZmJzn-p$lYagda-MQ|+MXcN^{ocMXmdWL?1|N^GGzR!i)@ZY>Dp*mxR~BzET9X1K zvT|s2^ys(C>O{@PAN=dOkc5`Krg+1?zmU?do%KO^W}UDrW4)rL@|vkfimaqf8J^uc z{yfy8aH(nJqZKL*>&(dV4CRkHHUcT)>&d~!_y2*oc^6(koKtYw+`P~4Pe zuUF{G`irp4Xn1=^$DKPJuX0=97CN@E#5(k~mj+EdW3fi;d8laST3f^7!&M67L7QLf zp6pr{Y%*;rbKUh9)!%~e#s4y`I_bMavPLCyhw|z>@|?zei>pR*4n7&&H#E7 z_i|~z{ijaHSD#&Sy%_JQH)o<-uaRdYSLb_f;Qj3#cfQj`V;@p~ze0k(bx7)dc|odk zp2$(RL0ZaY*H&CzY}I9<%zuqa(E1ekZ}^5=^sSr^)z2EfnsMt9V{3cp?-S|&JrO!7MAIK z|8S)3x`B}`lDnzrmpjzcE_pmW9^|pfH*T}WA&VT~Leh6ld8&`kNySSPg8T_Ok#hWIwKHPEnS=hkbcN(Db;6_J8w^jSMfLY z`0Y~2Y(zp58mUP%_yM@}B2rIM|XBkW9sq=63Pf4-D^RMbxD8E-yi?>BLVYZXNb z&TB=cx;Q)Qez|`29a1&j|JDv_ANvtSI>nDd1^>VOG(WVoAc<5}tv&eb@^-#sfhLdZ zGv562W3}1Vc3nS{ond~fOZ}o+f2?5Mie;v~{^RUW;=X<;}LouhRdVdu!Ta+!eMAe6Hsf@#o4Oe>&LVbNB&A1X4 zH-EBOL;HH~rfiuBEhAN9nzY{&2KO3I_@y6SZ%Zz;)L)xiZJUZ6$-;S=%jM+VXPS01i zjA~vg)sbZuSeJIc^^w0`L^Z{GMmsAzdvbazOP4+G_gKFc{Y!*PSbamq z`)g;Xc{JF84cEv7yf0@3cD4b>N3r|meyGF9rUexLyay*+1Sv9g-57o0wX7; z^rv;~8m+Yal(W_yLf^T>=F>Lc$H%q53~6`8cX@{SnFXqhd5B6#NLY*-Odw%tTC@4y zugyHtqtBWTc=L&^>Pz~wQXFF-EHjONIlb1pOW5Yso~{X(#)A=W`{V^@y661nb&0Ql z8Y zN!5!U9TWO(wv@?Hn;Qe44IOwVR6bFyZ9(%n8ShJ4Z8Sk}qCvx_ zz<*?+6Vb94C6@kPba`#$So{NW59A{F@sq_w`o}~^RG6PUv#y5a>V`Qf7Ty|($mkte z`=~<95kdb(06HTf0E)rE6as7eSBR}U^w6YM*66vse3pWl_0le2=?$K-Kjhot9{?){#| z-h3un<}@@n&1{yk`H07C8X-tMuVK?zRE5|^!&tvLx@M92YXNVxhKe{1lgAJ6(p zyVvPhyX@51Dle$Sy5!`sXl;Qe5jGUfIntZWnDFG)wO4b|R2CM~iwq5+0-G}`1d&Jj za(s-+uYV0BhX1$_cM#NyH}7C77;{ii5CY!;JomFo`J0lmN1$&2cO?n1*L9ELgWrGW ze{?Akd`ERxS%bS zNIme7Gou-E?N+Uzmfm^vQLLeNM1|j?TZBy|n%KKjvO&9+o;x(=cY!8eaMV=G!sPAq z6df)BbDA$}^fUdgN0HGU6j-4nt+ITZ7=p^)hgQy6_;o)mypoom?L)phBQ9Kssb-mdbxuQ7D+4MA0v*8OiY}<6JX9hp?lfu5SA|I4C_x_dP?fY+$Tj zCGL;!PyX!Bk7||e-F$5}p|;s8Z{!GbqyR21lgZ)mtH`9_w7;8DjjUkHSf5NfUBB7+ zYI#+aFB>hcYy9hqew5)dp+&G*IT5l6xg@c4BBs3nJKw;-f)-^aJ(hAt<=qjLXe8cA zn$Kn&HG9ox`~e*mB?%NKnFVs(tge$X^>`>gnDmE?+wU#A6F8vz5$0xD_d4+m4AFY(3VzVlZa4CupmOHAgKD}3p-2#;au4m|)fAcAG^YHk~Y@0r@ z-oH?9U?)Q`GR0qJ$BE@gb{k+vt4Gv!rPqtjE?}AYECjqwPft&QjlkWlsui#c-<1Jm zI19_Qb<}-D+mJW0Jao;@DtibGcb~l-a1Pa0Q@O=KWDuyU`|`a*6r(-NXjOVT@(5!P z#t=>kst$C}d0JSA1hAr{_etN+kEK+rt7}=zlk)q5yGo!=bzZhjbHeJ%aqxX$W;%<@;$LnlOlCa~>G@TlZ zoS-w2(+a$@@+Fm7;E4Zj7QDmz8t+r|A|{6OY9N8ko<2{rEKbtxe>s}d(oa~AeuR>) z4au6G@wKRWI53?)cPo^(hwncbbBkkT&)+Is{)Y>=ipqEz{yg+X z@wt{DU-4#!pc{wvy_`F~f2rRSw=Grf92w=Vn?+*Tzy4$U1V-+y!)PpxO0&!vvH57I zn-u2~wl#m#(fU&$=>(bCuF#&LWI@x7Fw1NuynyxM1#f6Y)!O?75>&PP zK!A{F7W`XHTkE6R+oJUvYx9kk+(JFhvt3}I1m!d2jA&>xE9dMiNfJ2Bp169T-(K&^ z2djbrK4qgue}`Gmn=qgIMC@1!g+}B6bx99R&}#c_Isc{XqYo@@tC)S@?ibL{!&`h$ z%9}GZ_|?}gc5KR5&VuA5XP?x-r?C5qk$S|g#3;|=4LlKyZoh0I?Tyf7e|jU-C#*jN zPD_wpo#a$_R14bq(DN37g#CPF7Gm_Su-T23W}^N5Ozi_^Y(Ay^SJ>0RU?!N zv6&%*nN;{*Bp$@2s#b78*VD03VpXlUNJHTM1$H}_J52kd?)71QdRUDkXe2HCU&(sC zQ=q^Wj-zspY8G-$*&gZ}-9NYX^HV)U_l|NDdv9<1VG>t4Nuj0MwJMsvIaXjJTWi%g zan(!o@Q$}k-Hv6l{O3I7AyUvZVxsl`(e>rwP_J*?ovqWVl%k>zQP!k}?43ke8bUP2 zmNjFd?8a8-r|eXgQDX~PGh`XUj20m#22&$@ku7P28cTTZ@6d9+*Zcb8T%D_!G2iF8 zpZor7&jFny0R250rX_lwGcjqYgsX;JIx`0_-R1DO9L%zDk`lET^~PCevcs-LxNXvp z`fzX2M~IK;TWEH)BdfVq;7A1&?l~JUSMt%&4V;M333AI5!zh)={ZQX}{W5?6`H>Z0 zaE|z;X)36vRC=K#!N|bCU|PZt6AWEkrFN{QWY)#|SAfxcg)k%108w?h)HGZ4$<;rv zn{hTZD+rA@fTK1N+0Epcc2{6f>{p5`_4kUImH8j&05RBzH_l|nzcfxA2?Q_2z4(X+ z#V6NUb^xsZ#>`FB@!za~45W_;5T%!h1;0VT64l$w35?^39S?@-Lx0$qr}oxJWe*U8 zv7&mZ0*`%qU@2yZ!_eN;^a``yxxxi>xv>o^KsS5MPYmvat+Q^PqS`B^gTm#$2H(U( zP8V-07J>5oU*_NY3~N?SS`?a0F(Wq8w`x#B{m9KXyJUz4Z7VqETd(gzRVc5p>2xyc z1;Uj#*WRNLkG-BQxl~DXp<}k}63UN{klzgxn+oHAQBA@_mNPl)P`$u(P@l#?t+y2PZGK2@X@~Y~;0Hd%SRuH(6@rSRcy*~oD!Yc+l5@c2hM#6vY zI!CZjXM@y4H&2@WV&TvyXyHN05_ezApd74v5#HuvxMO2^aT5yYxaU`oC2b}k0(AJz zeyK#YLqiTk2QNzlrhU|Ha_0xab{a+DI=CVfW73Wz2dN^QoXyQ>%Z`%W-AV^ln(Y8F zMwF=wD?2b3;VsBzNfgsA7b{tIpk;^fbs!@Eau<}OyI1$JykK%{%*is!2c^Y$5V-07 zABXPJ)@{+xNH;G2%{H!S%!D)Zun|YoyqG30wvM54axD+tF{PryAX-RT;2*z#9S``zvUHVXM;Hu`t;-dP_xU zNPK~N!?LzSp7gRjuBN6_of3eR{C+YV`q>j)K}ftK^`bf=kqLvRj|{hB$CHh9)zsAw zdFy_AQd=8rqze<}UB5$j14Lh=>hI(7<3Cgt;z)np-0;Ohb}TPgF2hK6B)KdJb-+|B zB7;IqRThw!gqad5`g6+4UR*l+E7)iob_J^RL#2@t={+GQem6Lx0GpY1xm$rTUDpz^ z-^-GIBc6eM5D%xn|M5-m`fK+!Eufh%W^|>+kY~TGrJR+G^XqY)in$KkYC6Z^C5vB+ zmwpUpWh-@Ok|Q9uUguU;gZ_6hKCE+5)7N{Ku_qERH!-&{nIQjh`?#P!%p=jSD`00Eacn18QgEcI!nnj~wJ%ZpmPv!&ah(~( z0n;}JR>}u7>g*LMBVhRH;t>c;6Yt?F5VG|d3Jo*7bF%=@o;`UK5Z818+B`d(3kG^P zW~U{Fgu?d%3EdPOI75%+iKPr9tZ7znRUwnnj!H;M@%ZypN49tbrly8%S6!Er<>6YB zAJka7%H{mmkNLsW!JLXf-hg)p_Jj#(+(IRBtiGmNTUb2r48??FYHS4H=sq?yg!J~J zI@%9qJ`D_jHJ^6e^%y}yC?{1a(q!&pDzPNIMm*xq;>wSm9sH&CLqm*0b9I!gu3&O! zixRS}n5aNt0+B-}bp%FXG;=2Ka#S&^ehNo+(98;$hpW491C9s!@F=&vBJ_&8|UySfL;15kqyeyY^P`h`{6b zBb#<{5fm@b^2%k4ZyRQr#XTs=^N)thVokpY$63Vn~N7thjIha=U0&S0YI{=qR( zNzIN=nX8NO+NvHMTDw*b&Eh%17a74RhPQz zwd0lBk?*K=+gpl$qy|PCe3uJw@jOk(E?2w>k6-ENslWd$dRtEmG(Ay8+6&?9ghz*6 ztztMA#A5WoQXweocV)|DB@?9cM8>H5CqkiDXzhj{&)z0T~gp-d!*_c78#;9jb~Q&kAU?M_$l-g*gX-0L-UTIr_2GFN|R z5cuE^ReKw5uYQ^xPk(-zhvAfwH2(ZP%SiJ2KYNHnXoSD4v(0&aa|e|9gLpWnZT||j zxnMiATX7^xPPQWHjDUms&<14Z9Y17EB__gS5I5ugD%Xzh{@Im*{vG;jpwh4z`Xv{Y z4x!EiEl(6}1U4RaBM-Q!{Qb@OZoJnVBzj1siFVuXTC`rCheLGZm&wV)F`4#74u3D6 zsK${?rJ30NzCNTA_^`0_=@ZcR!8uuFsb%IM_fK60^Di*@+}Edm4+Vju{tmD$n13u_ zK-!YB5hO1nwLI)kpLQzlvznQm9i>&Ubl-Dk*V>&iBO)Isc&;Ao+xmF_1W{B65K&a} z)!iD}%y@5e8Hotdhg+NvCVLQ4rLsP;**Ev)a9<3t_wNQz&>+B(3Dz$bw$dAD5%G@c z$QnS_0vAsXoc>Tn+$a$Tz0lj_xby^F2|&`UzJh8WJx7!;N~Ev^GAZf+5k{4}?AaKa z5H_?YoKD?E^DFhDwGf zJhqNRL(7|O^%VoRbin=4o*2VRQNxz+oVZfUupHno7X!R5(88c~W># zl6#;7w=c@Be#DjQK>Slbr(xoNhtzl#k8l9M+=$Kxrd&`qh!;@4KI)~y_XLr$!CxWc zrA_?^TLUitSynNKJZ0Ij2)DWzy!?|p?N1(<3|x_A0Dh@B(vA{pFtpO$pu5(n{@)}H z`~>hguc`npnfy=zEG&T%yv+_mZ`x7lSbNd|0-@D)Y8Zt+(&|%bH-NG`V`3tQpUngj z0tmgG+u{bwstRGNKdw)#J&dR=dk=5=-2C|4kgQAhAvb02$Fj8JColkZsH#E-e|K)H zM7wk}5x+{Qy&l1AVJ`xz^&mgiCKPz|>`RTax`*2k3J`|pDgXk&)Q7;(dHX7$TIlA% zseOYHv7f5};nx!GYz_8~n^GE?QeB>?K$-;oFr4Atzkn3zha*=Wy+61N=A-M#TLYB? z^2V_rn2|oK|hw6|J#u>b9RNoD{viVEWV9hJ%~evN=}DhM!cOPDul? zSl0$wR)VOv01O(8R|QQ>bI-&{SvS4aXSL>uc}YKe$X4)lXABwUi|bo8)?vr*{w zA`RN9A{F!eTwJ`thJ(k40`CTjPoD-SB$aCMv0yfk2Eu+2Pf$#&&LFCwm;1=$*xgs2 zG6$Z(u*Jf5p;L)Q@(9(rZEv0K%WB!BN=GtS|MUpfeR<=gl>?>k&tJeVL?^T#4?3ZW z?qMNCCmFO*>O!2L`EYI3_@a~7rcZ2^UA^q@e|P=Sga?M~#uVTY`EX?nfid%_`ni9>XW5!gFILqjn&@E$IkvARTcLTql~*^710h$m5! zpwAsXVeSsu2BAeXQWkwc-G01q_O{o4bM&_OF_Q;n)Ia z!aIn?OV5AwbfB+NAv`c_g-R}h@(!*E6pZ9ASoa5Xwz4nKs|KK_Q0_*SQCTu?Tx}Y~ou0=^l&<}!34q83d zPg4(cCY^G0Y{-t=C}9l_&fNoD+z;f}6XAtsts)w2I-}ckMey``mf{Hbu0ZZPb6-*T z`W1iwJspX9We|m-aSL)tqT~pvR~P5K#%eX>(MJ*3N;eOa8SJeWD|&qr*g8NPok-aL zu0O)7mnX#=bTz|JATd#{Z(S1ra=?=GX<$dP5Q!s_autY(yg?FS_OtN41K>~ix-=bh zZ6CY70p6eN;b1121&0&A^8TRF&!61{){a=1m>i^Ei~<>a{T(Q8Zi0!*2d|?H4f)K7 zLLGGfv}~Lq9~OG_8~4MJQZ;1{gsh3lF1z=YRj-uX0D|$dG{-{$J-7JHczu+s!XEsD zYX!dBJKb*O@$CH-fn zbQ=h|TaZ|mZq(#|nVgU`xY}H@qS($W;}WRuS`6dvlUT}#j4}ro>l+PfKc{mYUVolC zpM~^9Ly^Qd+<&-A5@^J%c#3yvr+5~OoT6niInZM3DGmFRMz*y6vY!g|M)9t65%fI=SWN z%AFcEmdwJmRVx5Q`48r9L{9wfhR>fr%M~i7U48zj$-xYt;&H_OmB9X!r(ihfRwy@@ zCa$n~XY$HexxIQ%iYuTE*l~ow z4>!B}LI5@lg7Ja6KpOaiw*YN~K&pp7`OAsttpeLMa>u*;uX=fDfsV0V6LDSpm-Nop zTn2983sRdvQDkXpX@&=xV$P6TH31aBU?UqI9)47VF*PwEqynmEeD@|jCmu|Ieg2gm zKdMd5HSTjn8e3Hcy(B)0#KN8`KqTNTO5v{{PAO*p`tlt|>I3FybhgnD3WZ_{I_ZRU zuTY@TSc3c-EUUjmCL$YBZyCqz0`RY8q`jlQQFtt(+11SJ2rxoH3z z)`MpRPP-$!y{&3y%VzqJ{-66kF0cFfY`B*AM?OKM1MI+cPoevKrT6fZDbCIXIKP3z zR4Ay<07ZIV>a@5CNGtTbf?wt{z2iY0+#6* zKK3FtK=@C>x%z`}o`Myv?J*{pz!5qwv%m6UMR#vckF@s+V!nh6IKLvDgo6>-j5@^_ zT?s@vp=Ag`q8${#M#prbvd5Kw&wQ|reheK4v$_kp_mYC}pE{=-?_lzO`R(4QcPFY<~!BmObWU$zPFXx0#fEI})Qlk{tCQe$+d;sUY6DoA_ij-_!CSe{lfP z9_~paejuDFAgOUPE7xF@Rx>UTQOM^$`*8XTMzBAogsK42=!e+kxE%3*=a=U%G+?!9 z?{laIG}G}%C?myG;$=N)v|zfBl=kWx<9Xb(g3G{f27^?Oyj|2wOQ`VzAp)*Rp}2OG z<%eWN3AC|UoDd$uF%@H`%ZxYeKT_y!)}n+bd)}p(I?l7aCX)9w7#^u%bqRdU>SY~3 zGi%td3jzZBZw@Nn{Jp_DGXTF`Y8xJfHcoyn&3^v3gn=Hi!k?J`qP+th{*zn}Kw)&$ z>u7JV=i32_qz#S-S4NL!`QX$Y@B!8oi1vx zZR8Fuxis@|`P_V6Q-;b2Df{k-=4+2RQT78$HoPNK&EGS(%|(~7SlE%JrK_EQ>kSRA zG|NTr7WS|1djxPX)ZJVQp`igcD_gO2kPaYK=!!aZbZW{d#1vQ+ihAKa4rDlNedb*) z#%*>Gr-({RurqmR|CgRSn1u0hJo$@a%)xFnUJY%`L4acnJM%b%n!DN+%YgG-k_^E6fqm3k-9R=niPe z!EfKD8G!Ad>BrPyAY}YHdxg+{yZIN}1R}VQGTW6E&s8V@kcIAqu+peA4z*pXYHBca z7*R0loxX>XO4w{RzuJL#qkQP30Mte^Jxc)k1+viRO!7_*upPSL=YUYtiOtE$(K3i& zg0f){gwX$(MDkAs5gmZn0yh`(dtaOWrQ(3J5=Y9<2cyye{&OahW`_(*(Q?oonN21u z0t5y{U7Frh6915mG(Tl52Q%dnXnwYU`UtK&O@gYUhpV__Xv_e4w-op*7J-BriU~(v zA401lV5%6*8A74!@8stfP~dFLWiLR7ghCJDcJ1%dm@ftiw@%H~W%W(9Mk8D=(_87E z&6jYDQ5=PO{Va8zHW+#D>e;|Ad>Cp5V@&&dm(W_=3+B7zNu?Knaz zWQxN$OOVH%%z|SIGBkZK$y>XD;_QO_Z{0UO>O+Y+LtQWFIjMG;=g*%9P0Li-ImQ;F zy491w`m)n(S~wmiE6$pOVr%+A|%1ez30aK+VmS$fOrGhxy)LhZ`a)RPJ|f-ouG}fdT`aE@Q5`{P$@L1A$lg|$v8#qN4>~>z zf$r!jGP>Y}>Rw3(19M`9^>#XlCx6!hTs!uQ4C|bU7;i4Zs>a>3>8XD}X_>YtM5tgH z@3YB9e04C1f!TmxW3mt2!}DkH@S#SUeC&63kT+C#68zXr?}=Enz|w1NDTZwej%9B?*fL^RWv?eLr=UB`k! zPi$Hgp9qx(8B<;;aiFOJkmd1Q;}ldzR5Rig1t`|b%L`O?XGwCWh_CSEL9a8VaLI%X za4lzv4zP}3&I4?_rwJ*Jt7=9b92to^g`bu0^idu6uSCCMjF;tf8TTzwg@5j^r@%L! z?7@DbA)cLni@x}_gp$g=c!+XJb`Ws11$LO#6?gK>WK+G{Odn%hY~sN2A#`|jQ?g+J zpfl4sLvSAaMW!6N$Oqp;{`2H(xF1)e&j*lnTF+|RyX9wV^{BcUEHFryl7l1V09rVx zh=r-gy#;O#zl^jv^62T=Sqz^R(E-dnOg=jUBaoZ(alkU7(swWVJXleVvBB)wQW@-x zP{yE>L<$ZhA|Yck3<+5?fGPnzjr{3)lK5!(K-~#XB{WGl8mQ#5tMw03WhjKXTeO$ZTlcrzL z+(*i0^@CjXBLslu>uxiwJ^Vab9N*jl$7e{muGPfU6oARP0WLL3sq&rlslJA7;BUHI zp~?U{bI%*y#|khV;mIDZOJ&Ih(E!aTOn)+F2)6-J150xK&H9^stBd~^@z{y~h3Mwp z@z9Oc#6zGB_2Al5BYVn<*A|O>)^N{gQECL|jcwyp$?zY3Te@WECB6pKXg}EE+68T& znNyF%K+h2{os)H|xF%u+aa!8v&tVB3ixu=!HN2rhy6=12kq@sT81$L5tQ^#J#rNX< zcPSt1Dc6*@>?-)fD=s-bkmon-a)0gGs{cZxnj4+-5>n=VtJ7P-sX>0WUnf@c?_F3t zMJpR&jy3k@wVZf0t~k8sh1dFB>y_MFKzfNb9>r~}h!rI)uj3uvs@ohXcdEOCE7sVw z{q@BeQUIvUMXQ|DU&YrXALIX^@A0n8BCVF`F4$1+GGcc}X~hbZj9>(YFy0c z+{P-i!I)Dxt|`iZK{_#FyY6(>&;iB}T`5QC(!8jtRvZ9!dP6&pRCiuNj*Zi&PuB~m z$#B#^zLyC0!`8b|;R=imD;R1;`f4!TnkUH1zb9CAKr2-*fOnbEwDyAmaaY4pkhP@1awy|&3}=49K(Ga0eq&b8xqeSO8P{11bE{;*(ZI%?Pt^4rHkfX?|UABY1tXghWRuJ1wKDTwYoJdF9Y zNZHdf;bEVS@!#f3O`zgr+}6;9t7aWZ2V^ST1mSFvuE@{N5U+x16FwTQl@dIoqB=YV zdM>A==||AUO)fX!lcrMPf9OZl_Hy*~*nva`EknfCO3HS~8Kj%@kI6=JOvd(u*gNnje< zX7|#jvd*m_srideL6c2oGaHMS4;C@%0ChfHGn`*lUEMjdJlo*rY1$4eP|S!hQHa=O z_loBIstMJT`^m$9)MK-8Gr)Vh{1-9!NIas3O?js?QmAG4p2n^^#F*9^tlOe7?^%`p zb+>a&S9wBCXXtzofEQ+m_&+jQ{I6nwjj=alacD8Yo2wrJ1fevc{#^Guar`W3$N;?s zd5D#!r*pyA-;SX(XwdLU5ELojc@D5mg>?2Pe-YIA8t|nWd7*i^}k!|eyzzgH* zCU{Wi$mPtO9#biMQH$qp1vy#euQsmO00aL0*2NuoVLI9ae-((U7nn#GTj&$W{9{_v zzJ_oYq!HWalb^Xy+XxIOrgDTr%-`8a+tyrze<6g!x`GjlBT?~MS^C%r=;fw|HJV%~ z8mFG!@F-+2h(~Cw)!{--Z)<-JJ(th&)xkLvCaME>d!W!ZGC`_<^w<1GWZ1K`ehPY&eMnyY5vz(aZ9U0=z1S@K`jVH`) zo5segTKtb6m&p{@jlJ$}PA-v#G@+rqUFQrS8&Jw%EQ$Z0)!&-$M>90J7QonTx1pyu z_pG^Q)t#P=Yv;Xx@Zdq4ufnDS@84@`QaPlWxeJDDTFuc-!D07tSmID@v8}0VmrT`p z*ZCSAl~)IgC8yn)0nN;uzq5(vU_ptMhKdIuxywkPLg2hn_f;|lijZDC*VgvL`c&;o z4%(V)$7W~7j1jGx%18mlX1}*U1+-L_9fOKo9m$1aS$YXjcG)=3Qi8zWQX;kZK6wqVli>E^pT|6e!E?VCZjq?JZsqEqCC)f#$Hx z*>}x2l6L>@(c$rnbeZ>h{Wc`Fa-Ey1LE1NrQf#o5VskFnXIsQ2)kH>pfY&RFf#%u2XfMV-2rU`ZEI4tmf^Rh1-9Pb z8!Krvh+^+_-vbta(+Gnn0s%D?&xday-fnS`mKut64b5>#9Wf(9yq3$@gu!FpxT!T<8%LnpSK7Y})yp&px&HKW-;2JdX!$x;Op=$N3rP92q@ zDS*ZIkO%_%RofSAh4-=pz9m+4YS7|j^LdCSN;WzgY0`Gz39Y6QZnnjUmk#sB05ypxC`>A7tUh!|k3dkLYI}hBVGG1W!Xc;25L+4s!Cx5QA zc_QbjE()E=Uwb$#464o1jGD~gEngP1aoYX=qjH3;Ta@gg!UTZi1$K>e;BEqhAPKu+ z!U>hQc}-0NJt5ir{dSb?#W+%CW@eT~UHYU=j!AZ1LUta<3jS6lf8^lz?eIf>KDo9_ ze7{K7q^Jmv+hvNXN+ z;){;1>rpS6kh@`G^6u`HTkhDx=65(8xp|r@9?`l)$8oJ4vsau}^7DaqUR&jArK!;n z<Y%{nInigNmC@j;d^`5IA31Ft_0&p~lnuvhM-aQ#Gsu_M-2# zH$t-UDLR{ST(yLn2r-?c(yTSM{J=BUBkMT4$tP*jY@ zY_J3Mpq3#V2oc(X4VE2aaOqO$-vr$>xdWc+#W#b@>hGvBy364)PbkK8N#^%vkcv>~ zFE)5`VLigV6`GF?D(($AL7xC|Kx#XGgPZs*DNocA?$yj$l7-N|U(%=^i*SMEU8&MeuA#l*zSXyiDJe-?OYpl5f+cLlgi z$ozStCa0zz(BU3|tggAeRzi1RXoWz?hR=w&?6AJ-1Arw42NCk@CSVV27c~x*S)_~V zfI}O64c(@6mmus1JvBWBgHfA{#F?#GV;Zv>T)JjW-xGmM%k+0yVZQ8IO3h5)(ZiQh zN~Aqn#wefaQmu2{1b4|+t*t6ijW>sbL4dueYRyDx89rB^_X2<>^sFDd7DvFi+AJuU ziZQ04t7Ug7HLR|$e^;}ippV`Rgdy^MPJ<*@g)LHk6nU_yf$C0HHj!s1TrmLE2GQq@ zj4@xoA%UtaB4ZXI-g$Pq`};qbaOzUn4Ywzai$_FcY`qQ0R#tEwfN+3*qXK0UfWZGz zY#9E_kf@lS?>Xb1TXX9KZ}{LNX+8ZFyzy_1pOqddHn#!JRPA`0@m~#Kx%4Bvm6erd zq8iiz2niq^uzRVu|8taF*R@>#vi@VrA2$vWv&XC|$F9|i>Ufrqf=WY~2H>aG;1Hzk4SBb?|G5l)qiK|DzmLXA}J_lserZMxR z+8Nwc?>i0BtAomKKTYm?__Wf^$7*ed5U^qUZSjaG$n0sgiUWaA@xZ^SBM?cT>FHC+ zf#4c{e<=fUDCtBXbdrCaydighenh4aE_kZp^!ZqJl#^8xk_u~gat|TBkjOs>srZrs zC@u&hQA_P9prp6mV!FF%oGNRgf(!={73roqo=tnV0%8R4eS6PEGm-A?ql__&+}Wjb z6dl*XV2@i%-2z9^X}Vr25#{r1WtS{q>bosQVt($Z2ufkDCY*uI+wMGX1I-n3N} z=HTWb-TQxT17;8>oS$C~42@jH}ghGJd_@d1-K>*&@^8E8yVvH`5&^F?pChTjm?;wP$X;EUz7!7 z-@SPSQE$i9)vXSlLYCQ@zL1cW`UXuCU{&7LuRo#KG!OmmleIw}yg*-K{a1PwXko#Y zU`FhkxQ{Ox*~36aZB@qAg^7x+;2Urjf#bx%j8DsdD7!->hS#o~Fiv2}>>+Y3HbHE1k-&Z6Kh?vC* zVi$rSXq(GH8aNvNQKx=@awB-!#a;PK8gvh3k0*fLjbharm4zWhk;THs5i01E+CVr4 z8sVJNs5id&rb~G_DI^S5N;sMFCt1 zoy(}LgNy%$UVWS85@aMmp%d5hG1gn6Tan3 zk5_SSZvD^W(0dJ87&GW4`T4D8xk90S=t?sBh4u?OQZ@t-zke^Py4@A(j?$Slx#3ad zOWgBvXmI>0fNj|NL)5Za!`$Yc(9!9@rgwL1LyHR%+mH2^pP4tcRX>D!Z(G!pAueM5 z!0XO#efmxD`==O56*8O*6<55&jAl^+j2FNKb0 zN)?!&LcHC}fU(Lj44%dTmP4=s5IL}B@MuX%P6j9B**n~KMBUuaSrvNt z1}nxuWs&a`u_eDgC2n`d$%$zg26JNMsfdx3)KqW`cL?LBX9x&6r=ntx)E0XX8SC6} zm^G^0Wd}f%2FRZW?Rs@(MOa<6?hr!?Inqp~*8aL_Zr}7;;-N6U>j8OlX5T`&3$#v& zF^)R=MzR3oHDhH-*w_M0F3inOqht^m$QfNy{e^YStw4pAw`3KTnL%%Bv` za;GZ|ke?pjq)a^wk$XegftLV0c>x}TXT<~8JfNj16yFdyXH+>vSVC~1-4dysl>$Rc z7Y>|%3jUffO~Z3UvF|7AFOXSJU!NaHO=Ti9{5ytya&Rz1E%3t7ow#9}EWy`TAVfH3 z5WMQl5!$hOr+Ij(XBYIOwIad!sLG%`z5-7UX}l);j3Ly`$0tV#sxI`CSOD$-TdJ&7 zdMQh!bWe1ZQ{Z^tq19$HuX#UT(k@E9^7{iq|KAk{0n;g=2T)8+!}}f`n)liMBNl?w zV(%la&!E8%CI_mu5!%@(`?-5ZRDail(@=VDG zZJjs5ddHA?l6A5F@DSeuqMV%U~0E>zIX(;p{_mpjxa@02<#u% z(l(A21-%x0rBf1_?g*w5nnE#Ug1kya=42svRbrHWR{N)Y*uIPX0F}N}vDkBD>OZQy znWztCN!MAszl$odKQt|P<*jb-zQ_H;nuieQ2ufelDNa(NgPF{Z3RTw2eWc<*YpiVksD)^%04Adb%2VS?9-v0h^%7H^YwzX3wQF0J4eap};DkkF+ zNENFdGF3&P3q_&%qjrW)sdf|>vAS#oH0=dKAcW5H%s!qofp@q)jYdNB;EUD9ef0Za z_{0`ecFVJaHy?VKiRnxMjT#phmzD8s93oMvHZxZWu%k(hCDJi-YuzpL^TDGJ%@dS3 z8zFB{?2U3{!2CN{dlUXK)I+EbTh0?1NtzGxZ8e8LTa>kUql@j2fs~LNH7AvMIu3jb z&`R>-EER}|z~z%c)DdF?M>_VNKJN*d~U-%6%8$(1@Zbu(1_kK=QzXhmC5TrGIbdrQZ(@S2d(UHQXu3(u)mXSw% zVvLrSozZ-Zu#8bawQ;+JHa{3+nkvw?0u@aj4pMfYer<3I`+bevq3h0yb+?BR(-S_(L zdl~rmDtj}{WDiL6hWn#ke5!lBt2eu30t*}}b*K1|jQ}ZoedNOiw^wyDOq9~daJ0NI z7+%?nVAp&jUo@7K-RNJ$FJc?jIQp;J4>Im^g1`v~RSd2d z;3ky38!APz!s5G?Ev>AG4tXh^>7&Cr4hVg5Yvru_Ij8k?L#&(?S7hUDnTsPmQ|ViP z>CZvqIUUwz4z39b*K}*i&Zt2r@@t-?TTTTHP}4iSbYc;>Pc6AWC0han75UtxnU>0| zf$Qz3P$@?NDeR(TZ@(&0;RPwKJ}nMrro-)4+Am#9 zm@LVc#81GRzf;Ba^gn6(K@eR_i$oUE*q4B7xpD_)!eM&bzV+_i3JqcKoSWgjda!(2 zT^qCbm2Z+=%ttH)V#4It$!9e?lk!>{vh|1woEqHjohhUs9+WZ=L27srz@ z;b&c8=&Qt$3G7AFf3+ zN9(?ofiMKog0Y;}{-CqIuQSZczMwvEC={@)Selv(j>DOoYmbI*v2)Sx4}Ey-FNODd zr_UYQxpRqhE3?*JC15T7sDbsJti|@DE5DfF_Yw)en1G=WD~nkP@h^qtyW@Z0kpj ztUdyuvSy79tZ>V4S$kx22rKF|NnV6>9-@vghl+K^}JRh*>@E3@Y zUocxXLWCxE|8j!9zP_guv{{iEqYvw@kg|JSM`*{Dl+ycs+_0Kl2ll1PF&Tm+I1nKB zj!&zlvZ^o*&86-A*^m{mD~AS^{Q$#5ZQIa=&9oZ0X$J`nIn6)9@%r!H5zh%hxZGL%^Y0@TOcWfiblMEgIv%dO1d#Uv1{OqLZxQF{aiCjA@Y} z>v?b2uv0vW(ugc9o0j?j19U9lK&3;&$y_7}`n`9|w4eWwu2MIUJ}Daf!6-=i1<*|vne*i8x9vPhQ~ zEe99DHXs;4_XIGZXKm9*bfO1yDG=9JRn=7;$?*XN2Tc~ZL1rz$;faVm(~u8d=8(X_ zR502>UVQ3^mf=hDO%NE52&EKdI-o@cZ5Hj~^8#1W^W^mElZVM6 zfwKf-tOeuzOi0$7bO}k-@Gt8;PSQ9e$}RQgdo{8mUY1MWOAws}X zsF-_OZ|4NyPHB{Akb&FQ*IPSZ*!rzj|9J1qD4v+t8KBf~=|))aTk0}ZbGSV7u`e2F z>1(*{*FLQu&F5_8OyEA{WY4S;eH0v-Ac|wxE&xBA!cj-rU)Zd1J`NxO2haO((G8jz z78WD)x!eruCVz?(WZ3lsR50MXO*Y%2N+mOTjX`(K+a0|M349i!Uz%gw}oxbtSNcD1Da ztkoJ7xg2#1#^2=Tw9e}K-PhMr{$=LKggB=T`E1;Dwa&)5?32cq=F4*bc$+a&uZQM{ z&0)#6ZqsI9_^t(jo{>tl**o1QlfO#e|FA@}C86T95;sm11N{$6_QlD&Uo^(nzR`l3 zgh0jmnt*Mpc6p_E974smB;oG(JW_zt=X4TDj1n101`c`J_22|G<3#%p! z^m~YKGO>!^yr{9G3!s{#wzaq4aA^8FHZuSm-xmYN)>&b=PvV2<@U0W-A6NPfo*!H5 zJiu~paOox!rF;+HC$oFrv8lvDQlAP&TeNkosAUJP|BN>5Pn!oIjhJaI0AUjBkCh$* z*^8=(@L{L;hAVDBOa)^F8@lk~#}W9^FJ(k&;tPIzJFMdF^3X9oCTeEE$Q8f+2&4=! zQB`-;d!i9WC!{X+`!xMMZOZrZ#fuk3+9Ak`lYZW@(8W9@FxSA=1SQc@nT_LN@@w7p z&{xq#s!Q0GB4u@TxV9FO92TziP4%5O(Sp{otS7{#mDIIe>-OIJ8kOYO18{NtMFTzB z>vD1!D8<8r`YAAigHVigAf@SB0a9ZbB?bBUoG5NDacx=QyYBpnzsm9BoIZSFl-z+B zJG-b)avgX!v=KV7g8TN#!axZ$A~EYL-zh_sL7HppSAZ-b(Fk$P0yH(C2)>HkaX)yK zTRAGt@`1`S2G##9f30{7qv(4ePILD7v4Lnj>*_~b6+&d;{QUfOL!Fe3PYs(1?Dy&g z!yKUTjM@1wc!c$g&{mWg8QarPT!>%gbN>Bt=J~@CN=lo7K&&c$f6{^8H&QUDj96fL zBfs3qhUn~xgtkN|=OGFccC}rvyoB0EXdP;F=JvqjI@>I>q8*e*AS{mwWA|7m?|lrh ze0p!T!O`5y&YX8rN2QDJO?W4XhFjrT8uQQm<{{!>1%~9nzge^!aRp798l<@cyqx9#18{mDEv{|8GgRLVA_$Ut1?E^YNq0W zk_6}bAk0oT02ZvQY%D1NYR$Z;;u#KrLsB+~;J(#xCxc1D=X!rn_E9#hi?xFVf@Homy+;*N=Z@%11@4OL{o@-(;H9 z=@%D4c*N?8V)Q>y&8TdxBXvlFbu8|mZ!Ri;&jU0dE;Bfe%SR9xgO zS)IlI*X-8(eC!+t_wCWD#fR-&(NTigkllQ|}-m9w>-ufdH^Yg(T&_omH9}&Qm*{-^Nd5Yh)jh74f z&Wg`ct5TveX?;9#tNWb^& z_9%_L5S04#O5_Kwt_jGG&8x~@b`y4wpA&$_{&H9U0mwr2rpvHYyn~r#2Qu^yAG}MZ zCFRH>m;`jbj18S_AD9Qq=Ps$@U7Y?C35=wdoT(TD?NA`?2)%>)d_Xb#xW7v~>h(BOQyj6fHmSW@_+%Uw zpTN=n7i-_P+8nD-E_bC~RDBX!dR|i}cCu*diInF$rqq_Rn#W5)&;~O)b&6v-jSj(z{>Q;QO(Jv1c@^6Iklg8Ja6Vs;?muc06+eEc4AQoV}4p)CwG zpNyL>xa?UvX0}{YkoKua94wNLE-QV0jIr!czBMTJZDa!#T*7ekm=)YW_IgbbBy$E1 zSsO@*yfuJd_T{pWIK!hxca7D%WPh4XnRvvOjz_`E=kxQS)U7j?tbKckfPE@064(#- zUMx*qzG{A?RSRwxzk2of)r(?RvA~qWKYT=`#^=oBjfTS!k|x^t_#6Fkt7x&tLgL$v`x(WCg-PEYBA$SH(UygKV=o&f4R1{C_Ra7%b21gPU#!6>H)_ zxfN|>ze!-HJebL!_c`&z6zkT}^Qm2Vjr49tj89lu$%aTcjI@rRCl zOP*cgZlE=5*v(2gi#O(tmjAo5^!VLk$9aznyj^cq4AM5FphPlCXRJu!VGg+IIID$y zH!gYxf7SSHV7Z+@D;m*@yv=k^DOIkluFq;|N4vly*iTxfj)-qk*jS4o;wn34lV(gK)6ne9oB>-2|@!e$;u^E!U;H zyW3o-_x{k%_8hgEK7ZN*5Z(?aZ-hbWr2*5^7aI|l4Z%&p7raJgO&zLxKY3S|NW%ws z1#9Fg#WkWyMu-4YKZA?(COSY)2HY6rd5OD+)i-=cFem%=?%k{T9Q!~jVPr-KPmZw% zsiHY(3z>^PhJ0c=M+`D*aA{#LfQpmS!xo1T<~8cZWCC&I*PBD&B1|uueSxpCOf+DT zp)zl#|2P`oJsv4h9Cp@~RHNn>1TmG6QhAu^12VXcG^;-rh(R?X3|Adm5-pvS5h)NaF$zd z`~LSmFUR-1jmra$dQ{rWl9x~f9kOv77}xOynoego=Cv7S5>i7iK9eb*DMa`yLxd~H z!R1NUQ zY5$)f7p{hT%{8B_qgC&5c@N5!y(|+&!}Tq;-)@cIRd`~n7Av~GREu)nQ2>+#8l~7b zucbr)kWM;#P53l$fnK93qJdKBe@Mv7g3M5x>ArEC?qytV6<0(FAH*Ep;hfL*w*#%w zv7QZ-@Pu`L?J$C99#Gh)m3)5>f=g>xm}qzp)33`cPbF#Q;M`lrh8-s4U;R}iV#N2? z=1jaX-wlN*=aJlOgQSeIr^hxij@G|yh_T%aE-YW)t+z#Wy2@Xlcnrf6SH3eE(>_GU zfaclDGEzHMv_(ng*aW$Qd890FtgXtvK=H6aTF{&D7v9ytStl_7IB{QrL$GGb%|5B> zco%WyRlUdQA89t!3a((;Lw_OdnZ-#$*9k~8YiVbKQjipnBYC!VSx2p+op&KZP^q%3rv#s!sTEK(M2X+Ac z_(EX1371y^TL)N^ohv8eFO(6r07?`0)ys^NF#~ zkIn;j2oV(qBa)_B(nybnkp3_!u7I;3cs9esm6!bJTl&^9jx%K+7iw@M>!3NYGZEZ= z^}^8Xo)rz^8sgJJ!UbMKz8gw}^uUSEhCX>|)dv6NobWe$W+F}QChk$sAp90GPRoD4 zs(|?C7sSHSGF;n`&yWv-99Yy3K~^cC#mw^f1hQoi1+tfxYR0Qdq`j)%DaHV=1a3;2OWAHhux3c$dMDE|xdi(ki z4$tQ4__snt#@zebAH1?>!hG)@s1pE~G3@2h+z!$S;lKx;SFg&7AlfvLFwl0e?D3A( z5GwB7i23Y^bw*F55N%}33+uCcOvU42LJb{KI4%Q3f`==xyKlJyBi{968!J#g$Tc&d zH0I3CKEmANRuk&4K!)OohIv#>!-_Bxaa86qoann3ouytu(VGb@8e@9r+6bUZNtz&J zgCNY2IivJ}v)Z8F6v;^GgdBe0XZd-B0&>}4ES@LsXnA5IV5KZm`$vnC3*>gZ@*;yO zK-18k9GwBpz)14Wdo6ERFBQ-po}Oj)k7f;X)yYTHcEEH6%!)E^TXAOB6x@Xa4s`dY zD`J%MKO!>Ol4ZxnjLy?qrd4&erMwaodAA6Ny}YT$Lb5$E8*Vy)%hNQhTaMD9q^#d{ zHwUmMA;l`6$Qc=_ONSE^>1ZGOarrrH(nY#Us(N~l>7}K?owSFnVM40I-LJD7zAL1E ztT4+P3XyaF>nI!tjqq=w{@gk%U?X5O2yRq2bshzK)6*q3Y8tGs?O=#T1dQ7KCBsq= zPa1{T+)3>I_K%n~00brHU6s?^**igDbnEsNxtL7-(9MAvp$8?ok3y=!Z&id#eSqYI z!u%Bj+7sl$3yRAgwe>RL1+`Y`s*H+mGO&pSmLXls_bu@V**~L<%q2T{_>W7{r#^o+ z)ErP`opNDAqZ6o|)*cGu%I75{CIWxi2^nDtl@gYrN4xIWFlDXx-og^trU4 z6pxcpnHzd~M>~JttB|*unfpTu$jRZR5_T#|-KI5{FTCo9&>v3M_u zkDQmNuO|cdyo_=zli+)3tyV7Re(D+;2hqREh5XL7D+Ta<*CJixd>x|mvlm?}zz(i% zjUMqrq6v@)34}Y}ydzXSa2~Ghv+SrnjKPn{q$|6E(ibUAkH1ZErAmZUV6a|6+8K># zj&a%>vH;g6ageB6W$W-5t>m<{Js_(MYm0mAgjTZMal7ZH9i$Pl1q&FZ0Y{D_D^ zNw5LnW0&p^f6mZm#`I_lbJG`tgjSl0A9~bloNP2sIa@DvUb8mld?3^RxOH^&mvt`A z^GEI*6n#NAJHB}xX#()_MWcup)Y0LI^g%^Ov+{qh%-&YWYM$P4=&Qb7FDaVRR(O`i zW0sU-03JqNrsv(+NjQ*(_jxmR{9$MikfH)$oBxgK|{c?9Iah8nD0Sc!YTcsiXSH|Do&46F&IO5suuA7)|8ecAM0?`xe^$j-=5;VEUbW%k;8dj9LTVq!bC{MTU zilOj&wi;!~lQwT%94@YYA1;d5Xu#IxI#^bg67 z<@nDnYwtQphnO?_KZk!Go5V)FR4lC9s8bo3sd4Y0i}3?&vYQwMUms#O*m8d3q;!a% zx5;;s;}V7SQ8Bz>ITFW<2#VyHs1z(}ob6eaiek-n)Q`t(kD^wOdlYo~-=ONXHR9Y7 zDeov|tAeTi9j?G|G}y&m#7PTsh4f1%krK6~ffAl=K|?^Xm9I-*@zh zp|Js_YtQ1sqC+0Mfp8NnDy-Bt9z3)!7jKho69geGe?D*Nwie1IeI|@1mQ+GZp^J~) zVe*kn*abLnGw6a!M;XrRD^9dgsbBi~&Jw(B5RRln2nMB>{C2IQP9<-N9RgG#gzXR3 zFdz?E6w z=r>!4taXQn zRK8`p9~J5sp3GeeDPkaQE+dGW09@;3&}fV%i#geEtYGo|{p?`}?rrAaNnAA2q_Yx| z3EFjk?2Z0py-tZnW?4x8bB`Kl0Oz3SXHm~d+9qsFwd|R!T_jEXw_iMUN=2KsL%AZV z?co{2Xj|ViP_i1JmOU7TJ7oB`0Rbkk|0~p}gt&ye3RU%1nd|4F8e1?t zlZ0u6b^6e0UWnBCrP-7=Dcz2}HBQ%|i8MGe8Q%Dg!!vVVzT~H+oznsyZXGqp6t)C< zcF*8TGtzdG>RZExj!oafETOBr$T$9LiAIR02`u8BhUi8IOM8lmcv)e!&G9QPptz}# zu?Mbvy0Uu)`l)SqCNdgP+a)!KniuB@ntdYJCj_Lsjpxe{hEM<276^}>@&$44P+JLZ zXKp{GB115Mpk{F!rayHl=JDkX*m+1~+9(0WcG#X*p2lQ z&OFHL&OFGWw#uX)G`s8A@$(DGIvs~TerMC+>nU0SPmqV6QsJ8~KvYuO8nbY$(WFFx zH%e+0wVQ}JopLd4BdX(Cz##6mQ~_fF9%bz}F?2H^(MQ1gbRU3Cr<~``&0~TXz4dgd zL|r8Qe^vI4^Zw}b=l)F?mHN&!`FSZM^0g^E)7gtC`dJUs($aRoeYa zG%uliP4vBTM+!6ao~sICd1VFW`+*KV+48OO3tI0VtgMGY7=o`wg^aqn@Y-Kl`Sf4M z+$Ao+9tY_sC$^-j{mE;SWKY^~a?8rV?eZ0{SE{3(ixrEc-bZZ&6O8wFv1Bc2KK=LY zbRF+ao96y~;>SZ={?`@X`Jvsq6w68uQbg1Ki3Of#NUTr0DfqiS*#}%>hZDLV8Wau} z;c`x=Q+Z*AC&oo6Qo(OiIvUaBj*T%M1h+PhEngrBG>($kg*VUgY?+Q0hJoT?C~O7@w1PmOE~1GhP^g*VX%A~)}c%%6Aq+xL@csTSHWUU_ig zFuu}MHtOs`Qgfi#BL+!M=ft6Xq+hKq_agC*S6Ycr_b zGgzXVA}@C&}r9axm{k;}HiF!SqI zFd?zHXA&4K3Od(Uz`t5xaE3Y0$glZNO+0KOdskhm=-p0R^Wz+}w6~6Wm8#h1hl&-zZuCxMQ(;k&5kZmv^2G&GXQ`2iyI^#wbwVE4 zEI{lIAW9&08re7tPv@qk?XASwCt2rS$(-sRc^m(S4{)5$I=vhCRBT5}r9+F1SR{Z4Yd@AsO>eHR+ujG<6-QU<*7^Ek)r&yE! zuA$-ZeoR;FByspokz_PN^P=l_kfM}f>nrVUtgOw~eq!prfD}Vg0|pZ?zIFX1U?e{k zzpIYlGgV=f&s$84;ac|6koiV^rG2ehXpNVdz}Rk#MX}N1j3EUgm)yOw=QSd}oIL~? z^sgcsOdpQuI_2`L9YZvO)fqQj;s`1pCMTN_?Kk?xTLV#7I97U6{1OE5Amm5$Z3vd& z{bkpa%wU&WL^?NuKb@WVg-H8~RSQLcZRO{+DrTF$}a%us8>*zg?L6a5MM~KP^Ui*@3 zo=KRk7MnI}^_7x}-rxFL`DT-Hi=i;D7z5M5sEryKo<-z4j*Fw_Ogg3a5zbIoD zc$bv{ckj??8ER9|;1Tqm*n?REz|JymNwXx1?T*YG!N1y4HSqaXXNvn0GhMxaYz6PTUvisqn}PN?#c0GAG$&Yofs%M$}I z>4kgVAi+ifC=zkbp2iGsun=z@1Wz6=Tz^X_N85QB`?5r(EZw}{mYifRS_66D{l!pE zR6RS@x_N&Vx%Ni?za-WqpIAL8kKi2y;KgH3&UN1 z9oQ?m2M8lf^tr4b>BCC16xQ;s9bjK2Z}6Xlj{_KsRSs}KI~3y$*(x<(Se@|-GX0>R zD*q-7gppWaTWZml)thgU47nC^D3s69*p*=ZdC7RYXTY-;&ZeloWy0!H0~T}lyTO|H z=GD+sz`VEeYs#0>dpQT4T=rC(iU>iNVjGb-hBH#uo9=kJ=x#Mwr)g znZeq><99^Wr%Bo`e>u3(z@HvayLPhspuy7;78NBKY-0``qLqc( zlfK1!(VOpTAcP#-E%M^meURneP-M|wOGdIu=uXpU_;`m!QL;$Jkt-ey(9;OsE22gY zKis>ufdk+fjTR_s80($X6`*t!h8YpPVW_V#MTFB-v30gZ>*(L9&+g-U980ET!T5R9 zd1WqD&tAQz;DFJlksMIUvSsW8G4L>i?&mn>{dhC|GPrwK z8n8aoVLWxO$%*+@S&PPAl`SWr_C$V~DnuLW?R^Xp_U-fvc{li2Ydow@a}&NNOk*(4 zfrwv5>ZH5SPuRyYYLOY2AZTW0hFNchkTFJi?;fDX9GZFCrY!b{+Vx{^F4wzf74Vm5 zE~($ZM|F7ej| z!FzAs*hOgro0~NP*St3R!Te%uP>11jYZrW+t)u8Jjzp}>Pj)cKMH>_2c!@u@RHVv5 zj(Y>I4=O4wwqO-OvDEq9F~`ZQEQ~1dV`aqWg2a5uNM3YgdRo>85gJGm-m|aBVqeyz znIZ?N6QO#~Gq(aT%xzay29QC#Lb1UT72-kts(+KNr&Cek!9z{2fgPZr>~3&0U@%Hd zsXN%fKmtgRxldpur6AeE&C|2=qoKnScW+Nm&-^YY>Et{lbbiZ+bywwr{dvhp@!@VFa-rBHZ^r#DMG+VqPcb&+-JBuEvr+ ze^`*NV=rClP&+OMV%Lo|{!Ld#rJ{qWU*M1kudZ{DR5IP+P#8_3y=6lZQ5XTa!nS7r zqu}IMJv~J8t4g1k$OrR+V9DNfL_+%^(C$28haAgLDM*%pm8f7qQkNIp@+XAYU}^zF zNA4;p4JY!$#DLXtSAp5F_bqeozWRCmyD#ay^xoACM%&;QM=KGXQl*r>i$GD$KH0~E zi!dgx5t{zz242+{7B6xrS(!F!M@3xpVj5$kQq!nfn1r-}UWG%9$QRoibD-KmTwk z13F~frC5!Y6c|d43HXrLo+vtQr%H?@-7{09`|bPj!{Lk?WFT@1t8dO)t5*LodlGug zUo!wJJ@R4}mify6fEfGw#vSa-e!kFbcggs|i*#yKb^W-9 z`~bVnKLepVTv7`x$$SXYo_}3&?CpxTrBb;)IzG1dB5nprC~2E~y|VC*+kc&0niXL7 zn<0@xw9uN9MY0TwvoP^Rr?)m{V>zGF5Ja5A^f5!5nX-tZ_gT3fT=Mi3Nj&o)O%`Xf zRTMPjimQlh#!+T=GPbOe8!u!KCM?G0wcwur%%~89Dd9Feo>#KEaOjpt-Ks44`qQU9 zM6lsb{RD|Y+ZD_TYe?CY#eCO67hBG3w$WpceED*~=Qm!UQqUO4w3~lG1`E;A!MO?2 zA+%RGYXsMB<>0$_ zHSS`o-@^$R=gh0*r^EV!YGlmPlXkENWm*$Xe;$T$s)WtRLa~f2)7fj2QOg!SruH?q zbHNMwuO$b}N6BDPDK=VPAdqBMq{OSi5?h-uz5>poP>#Er=_lq;AiDO+5YeV zEYVf`(1jm}-Dch=?d9rf_#xF`!#m#0sF4BPid|k1y3cK2^2Yx+4~ZYrjGCN@Ze%OoUpvnB zT$Kz)wW}j+_e;P}bKpi-Ls+R!BQKX@rH~z~5@B2qBh}%H((vyWCS2rSM|tseF}>m) zxaYrqGVcZp7Fctzgry+@EF11c7Qoyv0{%eBU3zb)rV0r;Qm$~c%DXz_Vndq&m0kqj zvB?S4!>$C&PA}f3VQn>qnvQ9VRdY)$*dNysWtz)8oeG27vzf+j*S%^QsawejF%+#y zVOp-l;6>@$vHfJZ955zM_7{yb+0mI+IIt$uDR)>;G^(X)p(IdDD2 z8tdbM&j!~JuXVWQ4PyT=YB}E(enu&@*_>z{rR@9cEWeXOVQod|FCZ}R{<6BDI@8fG z0rvRFeTn_D1M%AHH=#%#;-{Yhow=yK?(t+ylSeoc2Waa0)8?59g- zQPkF?Vp80FvWD6ea6Z_=Ha4VYUzq*=5Vl6zHAxWSr#<1mI!f)F&2PC3^Hp5YU!P)T zpV+Wqyy(HYqdWw6X+*vm?Qra$1tt zM$%%Y1SPR2KVzMAOC1dk1!>$$o3>Gi$rMJIXdKNP6UHCn8%KpC{KOu?nCiVKUJ0AB z$p0)s!H0|m{yEq}zi7@R6sFRRjFrbm5+xN7lT%qF5bcC@XK$R4N+>VGL2EYoH;jWp{Q z9$JT5Ps3O9q1pV-vzlp!y1J{FGHo$0<}@3?byMarq^Ja;MqW5Xh5^q+ zBi-=X6@haP>8JFA(7YloAj|uky1+B$<$HMP$LFpP_hFGVjd#Z!PQFefCME>XR5_qR z$wl%`4NYAWH1K5155x94m3 zFNVUH{c;DkjD17Y$D)hoch`KA4p4kD5Q!@bsX6?u7i!Cs5D*IFw0kQ%ZvTw?{)6sKAV_6~Pd zf?&xc;0R)!|FCrq6%)xy=_uK0X=A9i6Sl?GH{n}7KOQ$P?EYsAmoEV-5KDN)RrpzA zMB>DIq!-V6GU;=#6TdeO>h7+t5|z)9h&Hmjf44LJfyb#H!WIUA_wG0^I>-3*blNAb zbRU357h60lIi|+WzZfH*dzRjn*G6=W%?`eum%@_-FG+0w_K+S`vy28cMs>*n7%h$c zUh6*Jz472eYNJtqn z{#VYM0@bNG!o``P88taajnnknoV8iix3hbvJP4(F?CnQB3fkXT^)&%wA~sRGNRUwT zCl12z98~_Y(O?Nr^!`>soWAj+Sd&G_NzA=3bpZ?CPCb%qkHW9em5?o}`}-OO2iEec zM!q=~CSF?0`C<%h<-i8!)p~U5*^(EANmwSD>bGC3`P5<@xtwJ?E_wBC>1*R_v9YoY z=znRnhx1gtZgj+En}4=8{mL0Dpd>eagP%r=>hT(PtLr3r-PXxMC9Smwcru$WM^a0F zI@`9@_14q;SCJ~CjZ21MOXSXf1>0Rn-7aItUM5&`jh2eOc_HX4Dplq7)Im6LJ=H@; zdOi7=<$xhAIJ^(zE<3>UHdJ@JpnsnD{#&W^VYR9Bpy zj9x`M+KcA3Cu}4`%scaWf2s4Y5w}{xSAU(~xJavKA1G~m8V|*A6fqCw#OdewMl~Zn ztva_aMy?^*Lq}ybSIuRM-kc2$2f32`_5%r>nresA(xEdSp~B0f3J^rL|7WG;qBNsu z%ShpJR6h=1rt$W=gckLPJ5>(HEl8w*gvK!{$=%Jk=8?8*q>FL1FzwA@S=>nLKgRXs z8QcZ@#L}(mdnpahCCeH&BC%1#Ny>;qmgf9IW(*HHkCG;0&kZlcC33N%T z{PtHR;aapsLJFyGV)vXYJ zE~njYEgwf|%ZG_sIoiu+zw7WG{M=0=x#oAh$(OA3Ky)hHuMwRJ;g7B^k~T(maZbAy z6GI0NGCu1IvD1e=Z+v%Rr_Rr1rfn~rVM?z*C%fB-B}{zro#0xhw+3n^`uf=VQ2HK>nv|;|9RnoQ?BcW zH!0o`I9w6rg@RfBCvz?|koj>%0A&(G@U1)7S01rc7?lpuW<_=aq0O&AC!7tiFrP$2 zGpR+F3`wMDm4)@WjUv~MKortRouC*nqmM(P3E-PWF_wY#ISAwcCI)+Z&k%JHfJKo= za#xHaOe@X3=4K1=mG7CIW{xnHbfqGG@H~6t8q2pDmj%|EGhZ~;uqxgf)|PJ;qf6H1 z5TWKr7YGVFR{TJj$H#M__1S6qF>Ob63OeH$$I3hSu+KF8F9QzcFh|NJcXazh1J5tr zw9IZGOTIyw!A@`yBy!VSr(zt93=OFzFAtvyaxGq-2&X-Rh$fm!hh0wlEaH-?uk~?T zOW9=L7Z!8eW4Wg^&sbL%ZuzcyF;@T-?l@x|73&gb601h$Fi){Ya*TTHR^m0dT3##0 zEED+iZ0>}onE4ChBs8$$mx&^@h&gT4VcBY^h#d1+*aD%Y-;T0ilI19>aWccUXVMj; zf#NDsC#YqwtsRc;`-iL73of>yu*r#;_BPtdbh2yDrhE zQqfiDZQB!HkUaO0z?Bb#B<4jQ4-T(6pz*uH*N2-sJew^q?HP2Hx32{~bPSsuYNOf$ zNU-e(NI+J-=h|7lrvWCZR)3bYj1JF%_OY@h?>MZoU?j@+P6fz-;lrLid{>C{s!Gny~`g|zm#yJiZ3|z2Q$_pXb4@k%UcyDR^|6_JZmn3@3oGqtI zH$hW_j@->HZMB^(N5=C%JKuKfJJjv&-z3f8+w*(wMydxk(nfaaK6*zFJ{WaJ=FMS8 zzv)dxAZ+=!7)RNw?M4U7MW|hfg}ySHtfMk=U?clGl~)v-#H~$!XE<<)C2Gfb7D1(p zKW5;tpnYLa<9*QabNM3WYeuC~#jPs&n>6EYUwe>+bEh8{ej^I7L^ zq8rv3BfEnAb#EuA7MET&{(=nW>T#2Kou3I4odK1X?ghz|2EzRm!E?-??){%t4#cFy zx(Roue;t1)@AB~kL9VLoG{`5QrX<=voWgu+X=z+wr9eCxLKJ9S-G1pgf|k954Yi>d zvczGd1JO2Um=I(|(Qk8JFy)>|60f`i+?4UE_ac%!-;;y@YE3OptoF@!6XSbB(ME^X?v%C8$1Pmqep9yu#$8TKG=^jHwV>9hBKfz)et2N@{2+ zge#TqwL@-3BT->1(HXS2^On`i+)qz8G6M$Hgw(n>6Li<&>S%+lh0E_c8d4%1m!B=2 z)M@`lWDP4;J#{6TO97U1_Ucn19!LrDDnIouhI##FMQml5MQ7O~D93<<%hR|l37ALr zLC&aqbt7!!UTZtR(sHcP`L26^DI$z3If4&q&|C6H+D(Kg35WPC$rdhTzP;iN9KT=N zH~>dE^~Uvqt9Z{NUQ4WW7q50H>OfKEHs8PM1|KAhK;B5zBX&!idv~inO|b^q0y~aP zBV|)0p()#M`>nWDtl`W7Cx*ShE)X|IzZ+qS9_!c0Y0-_vGH~1^^!hZ|>k|M>o$tz> zw+0UufmP~Lm&^<`UYzF7`-wlxD(F-9Il_~-z9G?L5ARIYXT$AGcL2cv`ehF7!UG+L zN4qG13(@J-&VN0;JwcGLt8tt%X5Y7GN7n-4E%<#6m>_8-aq1%&kE;&%?>*P^_}KHX z{rmQu?3qN+Oixo9bA{g__YomVJ(E!fF_>e2G+SOS4;G$ccJfRI$l%Xf${-fvaJ zLA2{~qDeHlmU1yaKf2_7Y1_H*iF$1o-nFr841c6LaO0KM%%^!g)ht;+7l_Bj7p z#`5=Iq4TH=WoN;F`$)=!MtY51!M;jWt#3s{bUWE%XuMA=FEvjmRpEUSvcHL>+A|9$ z;e)RXqlIf?(t*;KVx5+Dfk6KU_Z_t~)9;z|t3a6pUP#P?*a7uPXQrhM7foG}GY_J+ zx+`eVnWbzY3hf+xbzt|#q#S&@f_To$=Y#H}q|Ko36NjS;Mt5j_d&SpPSQl5nY$9g# zX;imnU`C!*6 zE^~{W=@hLsHSq7P8Ta5==}Jin{eTJj3)P%M27tw~G3b&pvw4*lTyn(+Uttsj9(h;Hs9`MTP7D|6RM*(crjszW zLK|pX-h3R&7yOz$kBwk|GUz8f@Fl=^9%>JK4z5UH%F-+&Hg%Nglql`+`dXD z&YU6A7ByhCnqQDq+Ft21G9#4ld%gb zVrW;aU!&hdzThc0FRu-}(hMk@?RlgaF`-xbdM`q^@4v5aUbXm{gYY3|qb%u=ft}%4 zKwkP)S$o2)80&r4o`?u`p3b0fKyE~bnCziq(U>(mat)uS>u!JxY98l-U zOS#XL?l1tV=Svz7bX&tV)E5)iw>Q@e1a{{;~J_oTOwe2$%f^8V#=M=)kC`uevd9||{MzQS_J?=?f>~MqJ3lff zYA1pY^s#$KhG_`lxJMwnrO*cxJB2S_THTR&z_biSa7#uI&mry&NW8~a6Q%OLh!83k?&~YZKV`}Hm@+Gt zVZ6Lisz{Kz86z%6Wh{z4gxe`FOjC5|q)skOa<3@NcVk}a`(v66TBET|C?7CABQwKs z*^qufH)b-loO}{kG(@2)%6yPkGyV#jZrS+-ke!+wdpkUgCGJVjLu-?GPTWrO4HHsyy(DqH@u+Z z=4a0Vn+QU3mx86?Twi`z`hmqGcllE6-&J*(Scz8>9;yCMk1!NhxyGvha;*DlnyNO@ zTbfio1#RN#`Xj3loE;k%=Xd4?)*1o1T_}GZo#2^hDnHdp^2fD`m7SLKxrJ|{20;eV ziVtBSl=(DAnE$-=yrj=>ch6^_UdxthW~YDi0=Vz^;eFnFmcNhRa;|53Fb!xiRU41y zAN^;rK2C?+Q4S&!8`ryz$cPSUD;otfrT3!2yO=9CE6?&>KHq&-%Shfdj*yRS-V=Xl z|GI0!dX!uDlG@X$$bS!TBsRJzjg)-EGUPPQmbyShOYkpu$JKHI$BEIl$vB=KR)*cC zt@tK&@Q#X(dv&YzKr?dEymXQv5JdMoL=T!dv|yDf@? zm~&%?_`2y0See{QhKmUJ=mo}8I&7jlN`u1R7HNWjl8!pf+L6XlR^y-JhHF#W=V?#huL>~F3iyLquya+Ex&Zm?o94#Ro;UY zNNy)XsOLhRz51uX1+m(XfKj3vhAU+blGb~!iigE#rsck@^lC~(C?9W5K9NcsYsrj7 zkHT)*bxKk;)UrJRPc=aHnNnBdEN;cOGjl^j)wKzJ9aoWo4oW1$1pWLKumao7&4_j> z6~E^JHL_Aept*I_0S)sY{{-YQvM9DW>ztTT-t(MP2s%;*Y&SsX8+=7lTN#nW*8%F=)>-El>$&19`mQ(YI zBDi*6xk!(Vlu4j9p$D9^U4}9;} zo3Vf9R+Q%6;Mucd#Tv_3Mt}t>#y)(oi{IC03KBozAB7mwja#;AvqJQPtxhjqYIUB? zqaZcc{l^62do6MhZm=hWt11rubg@Wio70ccG#_#AqCtwBCMmJ+kI;hwn1|$ePb4B9| z?q=?Rt|5||$u{Es`S{=dOF=5fTH?kY<|UzU&>cEyYJ;g&-& z?p|K4k0}NLNtuLt?7eMqvUL=r(6v}UdpCSo-S}fgu!^!YG_o0}ORo0^pFM5Z=z>L% zOet(Ml(dg(9Qy(m0B!56yj3$G0YTm>g-)@eRMB#HYewW}FX;%3DF9$x2 zlbmv#O1E3Ghh-yUNIe&gGbv_Qi5F>Nc2>CS^2G3(C2Z>Tsm{f5Pdi7)FqYpz5U
<~uAi$m+oeKTz9ErK@p8?#+?Snr(g^BDT;khic?wLfFgGC~N38&%2 zT#L+Vdb>*~dyFGuY?WyOmd!gHjpX+Qwv7)nGqV1>pM*>#^gh@RJnLD)vlEdNpz*uC zC}t(1@#8>7C!B{_c`REJ1m7{KmOl>|$3tsFD46^z4*R_k;xq@B91!}5%NtL20S!L= zzM+2s34t!~DZ<4#o=F{p4u*RJ*E2oB72&eE;@H?PYMne0O*OO;Mm1k_eZ4bF@IDq2UeDe<~ff+YY!Oaa|+C9BzP7I~It zU^DvR!@Hslyd373bJiT2RQm-K&=hMgA`W8XS|soh!9KhK1QUM;}C@sH2>`J`hUt_@-{7B*V^PFX#=;lBMP4 zr?q%NQii6cWHe4rjlCy9yF~VJF-}E28*~+|wk64aD}Bac z4qDnQF-FHNS=;|0uHvtO-^K_GaefoT+<&c}jo&9*5u0Lfvb)U+o1^@@b0{}u} zTOfC&yKJkH2uL94n6nR!k@@yzrgZjb=$+BolT(0jMnPm=>)pcy8@>w8E@+;Cd?=`| z>b)rad>k`wi*A|N#(Eh~E357`*4lg{P)ejzbu?UWx!U6JIf%i{J7IwCW?iiIg2-#O zD~OQaX*Kw{*(G%J`32ix-t8NH9eVn#K444vdDu72=5zbTXWC4uuLhDP#bS8GyTx-n z0yQm!ywC>J{g0ZqlYMWNx(?X&a9{$hb*kwM$D4u7;SejgGY+yU8kJf`@R>v329&?3 zK>s9Gg2K+4G09t-u#d%a09z2r#M+Fo%XcCR(jBESg?4dIWKSxeI~OV?ZPSLA+@_espC zxnL&miTaZrMh}41(SWgkZb9;&$ABOD0d(Wf-8cIMW!By8!ZsS%UR287V`!NMh|Ktv!OAj>ybI}XO`{P#>31#C*|294 zpBI_&tV+{k=S+8TEe+b7;mi-|Q_`nJg5^tnk+>E+d70?WOVqshiDTSVp9Th$ zlq+g3=Xp3S&?|qiBmyth4=sa%aH5O9BOpq$R*`Ny zi2K=cRSxM52GB*oBQO{`VpBiQKjnk}Xu2A>C!i0AW(hSK!>*fkjd+8juVfaCM~%RL z(jqRn)8KiE<=X9AQzw27dvwn(PJi-D2!4~T7=0YgRP|*j; z-ZwF!o7^hzz;;OFqWmnGHF*>-ttJhn>E^ltcM!K(C$E7gMx@= z>0FR?XFmAn4xl_uJ#Vyo;N*A`rX5fu<8gH-p|hH08dD|DeT|QV#?M zNa92P-`q+_=lp%Z_#7>v>c#T=fVE2I!&hS>yu)WslszT|J~B0P7!lm*+w`8vOiqo1 zc*aRo!@Gm6My>>7$)N4?X!(2@pg8oL+*QQ9t4Sb6YTZ4rUJ0Wu3+%rFBXrVzbPeEG z+tJQ&fGtF1c*zUb!%=h?uPXM!9&W~Zy3hW%2*#o{O7kQn7K;@02U0`|t23xkNBT6n z-KWOxdF1RhepkFu*}##3HAgJA)y?yZy%oQ&?w_15^S7J#gIYIu82S@ zfzKC^OwZ>miIRzsUhps{lB7q6hJ-Xuy2eIm*~4-pDrIqU-{|wB0>Ubk81@Onlk@MM zaBNXTeuf%3K~Qnk5`Rcu9-*kreAdPw31vmU?wLBP{+Jnrd=Rki%r|HaBsG$sSzL-G zuRE*F+70>6Orn;9D>9bWfgZLAF^Zkd?x!fp-wEuXqQk_;(lC~>`OAx&Z}Q<2C%A^e zjYBk_1U1HIb~1?A?&F_6WslAz*E6L=k9zw4M>n|liVj5xywpvC?JsSDZdWIc)!wMt ziZ}PgImRpNsfj{3ogNi&{xc>jLd(U%W=&1m?d@T@G&~WJ*Pd|fdl2zHaie|Gvp3#1 zyPvw%diz*s)zR1$Z@EB)Pcr7Q^55SG$p6jR7S7tiktZ#NLjW&iw zO+7M3C~y#+twsj-VPBEci%WD#INJTT+@=u&{W?gmn0(90(gnWdeT+=PH2#}`3egb_ zCC^x-qU$6z{3;&TRz9tv{i4i{?FS@}>7S305jG5Si2VJzojPV94Be;qh2dSu@Te~& zd|A1xv^z9h=(L7^i!!n9s&xHj#b~| zG&k@mwcWUyDUgG9~SX#^ugORZA9TRWJ)-_?!ZL+?dl{inh0hInInt_LtZ zJ#HM!Sj)Ys9BvH@v~+%{eOiH7;xuTp-i|kf7zemJA;uweA-q1WQ*bd_^(VNJJgk)* z=0H2HMoq%TD-l|mq0QsMv>R<%NEpyTejjv-2470L@YzbTsFb+NSk2%53-NaK-ln%7 z*UAn@EV8S$KaQ#_)X#tOqNBH&A8&JpC5UYare}*Uy`bqNZ}gj2&?zILC}h617`NfYY*v~#N0YR-Bym;SPO9mch%-z&#W#!hp$8QR08)?Bfom}>QCMM=%K#c^Jum+ zZ9@t@Qh-rheXjz8uF zP=&@1_~=YF(JnjDAJo?3a54OvF3qddG^X|f8~qr^F;DYaukyHGlOC?@IQb#iGjT=u zhfrNw;C43e3sM;oGMBwUdc2<3HNog8@hFPzMr79deP`PULE!d@vvQ>(1AeBf4xd^a zhyUBZwmEa{44b+@BvItT^v}r3X+2^2O6W9L{^qlNxEamsHCFY%Pv8+U6*&0T@qHdLk21<<$-%mBTHr)eL%VspXuF?C_ZudOfun>{l z^F4gb1eNm0s-mv_YMcFo=lXckeF(OY1GljaLt7xD!=qoO^>nw%*l&(w@Kda9z0AQ< zoId3}KiNU@Qfsy&_&Ho^iFJ;pd7T&TmWnWrG_GG{rvLGSneIB@<4q4@N41D|Vb9YGriFZGtakr%sfBM}8Fw ze-M8F$1wrF1VlXQUywiU-}Khk%{3BE#(%OtV^SpuYWgqhlmF2vgC0(UP*i~wCNL%k z^M}1y=JY3m1Tt07XoGoI*Cb7J9<2!xQFJU|a zHugUo&2?XsWBKcv=5F1vp|jyrj$eZ$kTBOTNcbyae+`2U_?p~TI4&iWuB-dm6I3khekC9^d-hBT7+(*~M{a#w z5c__VS7Y55^Ro@}=sfRi+#!Eu^g&v)Q?#D?kQKHmO#2IbVT5Hnf=h^pojWCZU8*gi z>%{&FRkRjP#Hh9KpWHQlhWfq;i+!}}LrDhA8?P6#6!FFlhzs7RnYZqn_J)_7&j>%` z2MAYTr+aN`Z}jc93~GhA@a5yPa2ilp6DQvv6MCCsKnZ(Xo=zF0W}YQ^@ps|8rW{Sz z07rVF-23L2(2qm0Zpj^M@P#wpn~yo`-=G>1(RY4 zHdFuF1#!gW-#QV{i#} zTDPtBH8k>~P|gJ%JpM>Jq;B}^GzyG)tGhBgP+}xu0{3R{k zy0jH#MjRCCPSNn;0+#?_L#}YBW{-8}mQ5zn@HS9P*>+5zue!P#RU!C`xkLN#h&*`e8+xa-BwAfMP~uzKWXQzMw-rsdN?-DlNDJI!V$T71B6#aa=S5dgc?aP2jN+=zCsxNn+L5@bCnueX%~G0; zP_*9*oz9k|JW*E@Zm_c0>eP#>O-8J#m`4w82uv^-OP4;u`V7)WSJKMx3qn7Ie*_(A zC}m&%!rpq{_nrPr1mzOUT-Eu|`u&nw2j3>IZ{l!-P0vfAPs=ys5a`SgpA#tMSNP&7 zw*Ik?{dM^82H_SCvEAMEk44--?civ1Z?qoBdq{dDpJR?2uOpfkgGjHM7Z(-ntqdcoouj7yZrUR`#w$XG z+U@S`;E;{Fbs3Lv3bSshmRR+Ma@tmidq9qijAJat;X0oqY`H&w(#-GcyMJrojkaK& zA#h!y(&OvL$1(*ykQiR9=Se~B+Bw&Bbl~Ns<@&m#ChkeBi*-YXxL{Vn5Ia+dbu5a@9D5=35B+4E$zl?W#XwXW75NCaP5)KI1_4Z0!)H@pYx_8-KIapWs)H zrC$k-Nb0n`7oQS6*?mGpUyY97=L)BNp^DREV>?GW3~oYh5BCnED21Dw!p|#fhoL)! zo%c7d@|TAfj@N?*YRn6~>}n!JW}Roz{ZrN=WfKrhO;BdpX!7c7Uev9-X*!~k9?fU( z-NvS(!$xrxI!jpdI;IWFj(7YV&ZoBOu-Wa$e$ClnRm3uAJZ#(R-FqTaL@(IiOwCbXq)_&7iab$Ify4*Ocm4ES7wnO zePTb^tG(*5Leok%fw(>2e(6zP>19Vb>Jh!;tGdFe+pUv_)P9+LWvgsNm#qEiXRkgn zeaBYkZxP;tdknlC`C1a4&3Su=joCVj8cW!u?D7Ro0Z?J;4`YWw}DN<^{3A{ z`pv2jCQ8y(TR=|uERlX#S2tJr$Y`mgoV7-)F_gGQ1wDcDIa-|-BUBTc?P}D#)?-r9 za=-WQ#uL%4UotoR!ugOo$Xt@2HR&4D1S_%iqm|Um^7_%)!-rufAirJ@qDT?T9i=9! zEj2l_r1>MgjEWX-2H($fobrOpygum5li<24?e|l6V#UV$UrFod8%PJDlW%@x_bT?) zt}t0svS)U5&8$d;_^thqy#L16iORbzpF6_WWDkz}w~Ko70j1Uu4PbKCPp6IrQIXo! zzH_jr)y>N|TIoc`k>X7HRbQ682CG9=zL8Gm(QO~8q+xg+e-ih=Tqkv1%;#g-oU=v8 zgSmS{R+tj>9wg7*b!c<;o|>$ZPO<(4$p-c*ow5%G@GCt&L*@28+&v`OBZ!-Su6X3FT6TTyYxdIOjcY!Nf|D?&mFr!#bm|K~cNZJk3wEQL&^NZds>=Cg z@AN>c(Vv^@uoqO@JSE;G1GD8-hg-+E%=rxH$uEVUn?+lHO&S;S`KMpff{_yVu)(TAZ(v#WKCGHQ1{@kqQi3m6gOR-7vo2)}S)X zr-37}u8dwRtJJ{JACq{-$w6nicbJ`#QZO`q5Gl<*(rPB@iG=bY`HtkoS1Z0Q_x--C zO)Z;}_=w(%3CMIAP-fz%a_%21i z>!EFs8d6CiS}(`R1-d`ry(lj86q_7p1^ZQx-FGN80iGqQy7)S@V1^V!8~*;hXpIU1 z+FN^w3J&cKlE4=eD#HwFt`q%&P(~@<@U?MUe=W-F9GyfZeR6Ks&|vA!{;w$P?TLM$ zvjc#IeS=_+;nz2y>yr5ji;JU0(wU$1H1)^0QA!AdlGLqaE$d1&M{p6W0&7AIwyq9v zs^;zvPEg%x^Y*lHa*ptkRYYNabN0(sWfZ#1VT$zcb7E>R?&@82#2*@St3Vx)Fc>d% z2A>?WpykBWe|yFSuxH&h2x;>-?r1cw5QoBNcFTg6YvT_=We-h!9pEgg=-s$X)9t>G z3Hs!6^Xrm=U}1i>*o7|l(k8{XMIol84=!C`$HvU~1Fsu&W78HMtWFXaNl8*iKsN)Ut}jjW>9@9JME`%VAK z_=M}#$FHCn$hYN8oAQHX-v*h8l>4=l;rbJbJ1URO-ZR>zmheKyeiKu1@W}nsK~0W< zgRKTP%V)QV&0StG*DQSVIoE53*Iet7l|Om=Px8DT?aTPpzPV9re#hGx`4Dqb{T-3} z^Q3uuLx%B9O{p;JutDdY@AFKpWYz8Yt9%<9k8g{$XpWapEa*1>M9)4BZAyJQe`NOduU|K2jNg=d6!ocf z`K;fS;h+8=S#KUtQ~v*t8)Hn~MM;uGBnqwEc1kH+Z9=J=YLeo1RnjfmEp4Juq*b)i zA}zO+7UNRVMz>`u)g;N4l=cPv9_L2p`}_3I%rNRW_nhbJ`FuPd3sHz^{m-92uTP!# z{V*mQv+wVI!=?H-62#e9y8aVm7-;33-m|3U~bkXMP}S4Ed}wzpSWp1dEPOTU~T8EQj3tzgBhP?z~m=oBno zP|S^Q((Mdc`U^u}GC@$JO)#HVRq0wZPhmw>HvH!wVctU_T$8#z)QJoR3{E`XV6ENK z(vp+<{D7UPKy?x}${pnM-5>$QDSjT*{B6)B5WgH78~b5Ma9$vXbzLvo*-e}np>;o9 zxlY!5i}}h*E>2X5eEH3{xamVCx@Bn+E<+tW@pJ>&iWccK?{?YOoxC*Gzs|F) z*N*u)(hZ zplbL{v4K3PeDA7|jKfVn(bhu6zsFd6{i6echHx}ct1`%y_EU;*cVqTe68?fLN?6{I*exwnloy z55wi+^>gtF|A1@{RnyqUmNY4vr7JUsp-Ajhuw{Zc>HW)`Hv^C-n$uEI$jb^LqYP6H z1a#}9b%$OE>I3-k-l|b)gZo~78gkSdv5pE$7VJjXkzIC+}Ira7Gw$xD8!j_&Pr!C zQg+_FP<`Q;dXl$`c!zQ*fiR!Eg3_-x)-`xoToNAJ?lLuotjFv8#K}n)Lk2S;a{`W1 zTbLl3G)x^kH=b|EEtN$6Y2x>t> z2DQ}J%d6pjo9QJaViO+Jz+3{)Y`F8dy_RC$JnB=X@qN*36aJ?ud-f=)p>iNxZ&&_=+EqvoaUo2)Wz6;}co}5K88JLQhCpyO++V)9i^S3rO zK)=-F3ERK5`zFLgxBBL#ZGKuHr4O?j+pC4oXcXz>;nD}R#Udt0DbgEA(T?@sw=COY z>vhuD*hz8Y(M_yRz=r;PcT14`gy2uYT9v1ZqtY&3;dOSlWjdE=AH7>9NwWs*kM@&_ z(4N$}6mE#IBy{w{og6qTIc1T?|Q1j~UEJ*AVdbx9{rfCs72qJMStMb4+5p65dAmkk|D9)gSFo0|?*s@ty) zN^c2HfFH_Wl8d8A1)r8hv#~Li(ePL0k8ehHpu-|=1&jhs=BF)fP_&B61{OX4UL(YO znGv~Ghwnvj9^df`vLdru`G5aG(}$i6(`;N-Jr@V&W4)#giJRzLJeqm)Y)Dps^@nN8 zRRmqtQ8B~s^V9sMeJ{!{l@8SO36w|%qg{DJYG0DxLu#j!cQn~VJ8ERXyOE?1R@eKK zvh#j?c8v#o4qqQ!>0`lpFpEWhz3&emJUEti0u37VM!C?+NNCxKLCwxRoJl<}5_R4eP$Fhf7$>nh0C$)lXh3bdm9U*h#1rcFMXMaNR#|YX)9w zNxZQxp(Z03k6@_WQrp-87!Gd&kH70I5OF{nL=Yk{+AIR0Bv@uFdv&}kT(n0i3enI% zyqEv;c%0n2$S}o)9C%OaX=uXURSi?6SGyzOy*vcT9UR`iDld*#%&VN2kJeJhFt~t- zyFPHz=8AZnUA&*+ScBD(BT^oE@av3D0c7^>@Nh30OBM8M;QgYe7N8w(>+jGjpfbSP z`t<1}{FWRrXk#X3_!;u=Z}Z)S`8YN{Ue-g8^MHL{IQQV5goRxbg}QL@I;8LDM&L&L zfuw?b2T&7;y7{rFV_-aI$D|yvN?}OoY71wnrq#%JLz-r9At}8w`lN-kOqUC=%CTAS zAree@*Y>NxJz4s?$Csa@>Bg>KertL0O2oMK#crv}NlQx<<>R~xzE6L#`VmUlP#R1e zeeW6i`mJ{n7`fuP-|OY|cc7!!&EDXZv!acXuKxs1OBNE{yxIILGyx?r_5bK-Td7_s z2L#O>?b34~$dMk*o3{tyy+>XgI9v##7`UfJ6UI1qKcBj{CIV4& zM@~f6liD%xwHrKD3QgRtk7oFUHfc9G480M)_D)obqmG#&VC~xB{#3-ZgS&eCZicc_ zxgTHA1M`pf&a$i-n1VUwv0p8T@}S9jqImp(G-I2&Q=_Z*+#E57HQAmx6Ybvbe{|iz zW5vatq(`PVnXgVf?lQdnw^#?yGwV2U%O^9u(PkcZTlNTZW{?iqIpFhNn0R*6zFdD7 zgYxeF@oDPu0I9QtzP&o2hXGA%+U9MGtU%&qy$H6XISA+o*T5bL#RP{eVMKEx0vuL6 z4A?oGs9#!Y3rnGj?CQm?wUtvt1oGH)mWo3xCuU9G^_2U1_eVOa9{!W>(6fAc-}=2p znIXHiZLrb6Dwa#L^Zkfm%j_&EJCXNemfQpHCz*q8wWHop5+i5S&+RV&l|2T*1=RgX z)`!S^Aj7%An6spJ3sB0IlkcF(f}6~5sa>pm2sTnSMG>{f!&iiwUXx@r@UCCS5rv^q}S3ZM8uVBM*oJE%}*lYKx)_&6*k24`C*8 zv1~O6h437W(KdKeR z)ox_~P<8doDkKyh5^9O#-4V9Rwr%-DWxN-$h3@0?x#X76>XaDLZ@NV&x(``i4nx~v z?mHA}w=waS|JO$ZdJ8hxk9}zIieCks14*mKRe8$BfsaD{9UfccFgZ9ai^~A(yIQNV z81VU1iCuh{pFsfaaC3GB*Q8p3UQ4bgkCC|>u#>Sse8@rs5tvMg8tbk+R0#AARSTXS zDk{j!@$t%~z&<`-`deuqoW4O3IHaqO+sm`=kg+SVjQe3BVf^c&@YfBI&&k+MxSW1E zdsDikK58l9IMaIk;^?(UkWFfQ47N0Tl;IFGOW^l7Pz=96)L|+u%MQk-(1;=T2%I*M zP~kK9ppW3LzYzPxv}c!yRu~cJH9_B(h})q;V7Wy2Mvnav%e^3HlF6*++s!^DnuBxNZGH<%U zWjX&oJKXdtB%_7b93?`c%Z(m`lMKn{?#iPZNU7qM(dX9rQH2T7nXOsQ2QM?$S#ps- zA6BYeHx5-Pcy9AzDX9?)EI3eh-gvT4k9qt`RB2~rAHQaA?DmYrW1RNDblaSC_g>1u zM@fw!Stm$xA_!RuEkiro@^hmsO=EZOe=6Qrh16SgFQ5AxQ+igRd*9+5q+oC*#wEimZYON-=dTc0xD#-#m^(tvg#i2b~ zpU~DD=YrMp0qNsq5BPo{37S8<{RnxBvMnJiTC)Na)ZWB+38}knDO>M1u%rHL<*S#r zycf%oKjhHjh>|DaSdkw^S%fa{gtWh;f+s>2=JaW2((QWw$m|)rZ{8 z6zZ5}=JQBx0p&h9rHf!){B1u$;?P#%g&s#HxhPCN1zFV?n4w3Fl5usA4AmGoUA9a~c(dR6*IX}Rr=7~(*4olZ+j>Nz8< zP8@wl2Ja~+{jtADE4k;4{Zw2;jh#z%F6S8-y!vJGhnOw&XR10r_azdP!x&F$WiS&sjIyF)xN>--4QZ&1`a(Jpvf#OoIEJSWuOZ>) zETkn=VRUBHV*m@b-I5vm2)n($PnBj9NwV;;0+;NjViSy$V2WM1h5+(&Hccbzf+MgZ z-uCZ%*c)X*-Ie(Sfohu;7jA1=m?O|n$PAo-%+%!QJy5Vez0M+u05G{`Y0|6j{@g-W zAmrU9QyMPH2rW#e?)KvY!?z`2ogdMY0&8YNu10LijvXE#IuMu#1}Dstv5FxbC?wdc zQ0tB{*zH96a!gIRr?01Hy7VQ};JkiEMS|oF_ycY~mlM{uH?h0AKvXB(M18k`^#Ity zNZ^ZIftIUUw|KE-s;GDf z@~ux)XZVep$-wfkaB$yKz}A+qFysLf|GDtqv6U!)IjcRvfVvg+?hfIp%JKF%u*ctB zUx_SFmYIAlv_3ssp`Dat%InPy@&&`&){+GqwxS2FksF%+8e0`q+{wPmTKkfTSANfq zS>f;u*Boo}5b}Z}WumNvbY9!#B4V{JM^E*isnX`a)Nd;}o}pS##iwuJzy*I)-cI#T zBXom@j5n+Z^X4zbql9FbO7)e?w$$;J+HyQ2k5mmdO9tmiA-?9;y3+Rwp}B$C{Lz|I zb|ASR3J2cH`6ol}yx(YYR8XCk>4N6JM*O!$vmfk#=>?g7s=FbZ+a;O$`#&R-E&QfZ zpC9@keyS8Ft{O7*dP#tlvykxW#hw#9Ed?2DU*E;S+V&LbOU?FFZM!a;&qLFvBfW(+ zJ7z_s1538BIi+CUsY5^l{q?HCeWJhli0WLw@@iYSo$$bp5Cuq>$;1L~Q550yT{__U zDq7n_6q@U^2SqAQcg6M<)e?^LpvjF1+jAg-1M@cI#=2}}72qRrP_V33u?W^L$^`d( z>zJ`FS{J6A9*aQxfcUR~AnmqC$enmC>$xH9YqQ})B z2sU||HJ(}C39R=g9S$PHO?9In?P1GFacFXzU3aYdjfM-1^TS=K;*tbl zFlsjeg?C>oU#YR`jvcPGSey`iZ@CMnxA;A5cVv%S#HPg1sdc7sIJ$10)b>BjvK%Aj zT*}8xkO1Gm<_(JHuvT@+Ute$AdK=pD{}%6GpyK04k5FuyqdfSqFmeYguQ2l+rc28ZuLEw8OD%X=AD4La#(pB*qPo}TG>v;(H2>tM zvf1|yj;d#%_tIyX(x^ffcR5PjDv+$5O{5iIzJs+VA#DYlps5w~s#~_3ws~WN#gw~Y zJINuma^Tu0SqXD>X=82^-E&Ber&~FI4^yBqqz+WoBcCJBg0g@DDOXJRQvhHR(9wu` z8Sn?@7WipU5(KrbaeaJhJMax-|LNn;Wmv^UHFa8rg%CLDNkYt}S^md>i)VZ)JEb}n$u$bAn_UIT>KW$AD8$-{A zYFd%|z=n3Tqp(Tt7@3%W0_Juv0*%Gni^mUDEe9h54xzBtt=nM9dK`9@XjxC6Ia4ui z&S_)@kfS}@(I_iMJx}(uuoX@&7HdAO8~-fr!@uOk@e6dB60iwt_Y56<6&ofMV;7rI zsaU=j15_u+tj;&|@W?*jhCf;Y>BQ5ir5#-;t;%LxH8VQRA_tLk^A z9Ni+dFE@K(U?V{M8aw2PB*lPHkitw$t0!3u=0(09Bu9`V(I;?e#;^meUk%2^#Yxi- zaBj}`g}>TadNRbrS;>`T^Ef+C&#Rt0zy9IS+bH+kSwt(+EsffM^e08uf*ag~-A#vQ zfAvPME%N3&WmnW!rLz^KlX7pin8w;&v)r3N<~v?+HWx{luU_nT=#AyEQFQVb;@qX1 zbD5u^`&QW=yOlm-`e_`LuF#h(6Q1_6E2EGN?_Q}g>?>XUoW_eU1ig%W51jcytNA=P&L$3Z(0D_THc6ufhJBZ4Da_DMKDo{6F62-sZ%X>>Ljqbq zA!@?W__n3ZhTsImE6Q=&%KFDCUEv|Ut*dqB%fKB3GY7%fYHd~P7i`=JEe$ox3Y0(v z{4MIz2&q1Q|2TBISmH}l=JlKjvlg=J8t$MmB^zfA(=7*o^^;$}z7axaJfflRRC!gO zwb!s5D<(0CXNG(C2UvsNE0SRp;i$-#yt&iH7;?Z&Mz^wwv291|g&m=Z+Ti$1K_kkB zsn@#(>*Azq!u1X}#l6A~!boY5x^9PxO4R536~buXs2MXxj2q_b{FFl>8R0+9fx7>7 zN}MY=Ztm{)9Rz>4CihT2mpkimH~bGE&h|Q@kQwd59dM@QC`==-hbUwn)4)Y@q(Dzv z6_2YFdfcqKdPaTfcMvl zY;5BeR>gFowxlJ`v8v|Iw`}r&zoTJO$v;De?yo7(49M|Zj^o!@tLDy7*;p)$9l;)V zqbcgKjbcr3Ewo4!`K}j#eQ_)IYQ7m5RMl_ZtnvLG#bCU_#u#QP0RuHaypX1Z{Mh(O zGNXaZ18pBibARs4`MLJ=C;dvf7s_FoT{hJ~UgVTf(rT1LvFC&}vJ)cO28!@3fSBji zs+3rgM37TQM*Es=uLkcjHr}y=LomIR)Mh;~1YeE`cwhx?iF7^&?ar-xJaF^=3V9RRWawyha9-G12O?rftiN;Fr?h`At65#zv2; zYjV=PGIw@Luli4enhg2Vvkk+DVt`7C3h(PTAE(vz4-%nJ>lU>8gett+sI@3QFGLXf zvk=mD;E+b#*zkt;PA2p|kFS0zQ3?A-JW=KxTD5eUF&2*~lfE!CX>yfr##~vry^aWj zwX|#o_aS^tA>)~K5&ECrNjV;VGq@v5mq8f@nuz<6uTggKJj-s%fnmglk>@lRL}XR( z|67*!7zFUqAJf9bIk-tUa)?{+q*#ZsX{_@7A;RV!&ASs7x#M|6;@ZU!_hC|IR-BY< zX(`ceqPso;FST0lNKI|=%`nqNi{mZ#R^*3{D*Why)SmtHU>3QV(W#K7=APVwp-wpz zgN}J?u)MkHRfV8#(~XzxC+H9FZC`u+CT%fnN%*U)JcC4qY%G1a+>P=xt!_!Q)lTg;YXEg6G*qmGA<&PopVb_(Iy)tIGZ;a(4h|sCM(?iIkM`c+wN(~9FF2=nmR_$8 z8|)wV92SNT0f`N3m^t^MIX!4LPNtPMQ>6n%j`?)Ug=c_b=Z>Jrtx((Gv-84M!s|J( zD}2m~9i*zJ#%c*PT~tX>w@-)?u-NG>Ra;g65tR4>r&5PD_L%!{G*m$3nH``65hc*6 zw1s>uL>};+4@6D#s%!G=Oz}1l6 zOU~-Ygt|JASCjw&acPh#6Xs;vM&jnVHGOo`-XlZ@=_~?;_ap3ZF{AYKfDw*;^!C?a zb=hVTacodC!raZewyrMD#nudpfgWdybjf&_<2pZV%n9Bl2U0@v=Coyc&q-xC%R97z zJ^L@URf2P8<4 z?JquXU%ZZ}xfcmrtWqLFnpolh1&m1n5JTLi3~Z@3Jen0LfhG!PY)?-lq>5C8IkN^U zPeb%pPx?00Q$;vJKYqL_K$Cyp%Wf$Qz?*}gQc%=#ao@nm1`L|JT;ls+DX64X07a%D* z7x;CI!o-U#%^WKk+D(`+JiNSaTn31hozoE}x*>A(|2 z$5J8--B;a=Ucpomml;cS?Q-G3m%Y89SR>^iNXPzGRGvcj`X^(A+*Iq ziKT0_UM+qIBa{6sxny_`VxEtGZ7%GHQad3&nj^)kJz4Vn1=E(j&}G{q$V_wX@7M8V zG2FMczg50HW_=LL?ez&OI;O?R&}~L|?E3L|?ec2l6kqI)l65U?o1*hn8(rg4?(-u7LB;9>3x84Pz84E!F6jarWi*j6 zTWtMzfBbbC0@*|CuDwUlCq;|XhOR;({&2$7VO{c%mHKM+pJ^3F8^~{C!|l+~!gqQ; zGQZpZNp~=0-MwjgX?q<95p)(ggLSnKDvCLq0+IIE@c+afDPkoE@CVIV{0HP{y7zav z)lz#8!qWftXu)wb{fF}Fb#HZ9V+}CU!9v%pWAwtr!#g)7CC1NCZ3(%6@mllY0sakM z2Q-o?2Fp&VD$J5L6uMWX&lYH9tZ5J0fL00m{ht9>UWIQMt=HI`xTS}j5xii7AFN-W z=`xiNlm)**$z4YXq z>b}$1JVAc#@)>#T=;A&Dnk0u|89QDw-l39eahDJV0Ogb8LB`IJv3ttc6}7aOnMI&v z6_dPF-*B*vMV-P&jvUc8Iuy|Zw7{Nf$wJI)j#P*|wnPL@hhVu^dWMWyN;87eA0QlxZ?4xe>WE^K43G{w}q~U&GAlE?bI(}ttU2q2_pe&XRl!C zE5+Ct<0=0BKx=|?XJ-ER52+J770F=qa(F5>88&aZ+I<2Vjp6}9vQCt6pkqZ3E+=3) zyldmqhW>xdB9H(wt0V%mr@!C9NC5g1!8pTZuZm?7XMVVLB9$+|8mZf@yBQSwA~X2T z%awc0eD}t^MtUb`aD-moa~ou2L`yX_8&m?*mol%(0|NeeA+=ANk)5|Ow0nCUeks8_ znRDG4BELRSc%l%)O3rIn4_%bdL+@Q*%N1$y3lMU=_jMPWj?IHNIp{r43-)1Wz0OZE zcnMR2P?x|svvG(YAi{>mde8V2c9#XAq&`&D7ZRr_A!PWv!qdi;5~x zM0axYC3c0|Jak3N#V{)zs^=yvh1{Zxyj1u?!I~pL7MMyMgAz?HGD1QyNNZAH6ZKc8 z{H#rLt;Zo%Tm7cOm+%5#x1hh^?C{DAKfQz7!sW>S(obbXNvXzv9(*pW7p^N4V9m8o zFQ##1Wx25oEm~b;Ujg+xu_@ZN*G4>db83yhu)@;mnE&69o{}3^~P4u)cxOhHVR}CI&RmwSRB$g6kY1>12@* zT~ws6n@}wX^G|9tz|>8*XJ2vAU)=Ue5rwGW4Gc6q7PV_}w$&;GUwKC=8YR<$V z=)_(n1j=EL_VFD*u!~T+Imlq_+w>V4woy&3?1T>3@&x{mcIqb=05o5t&u$juBO`gU z?Ojz)HOIp9+BJ5tB{gIptHE;y(=t&xXI+g2{9PP{)y*DB0keiK;ipuI*qNx3l`^lf z7LS$-v8%tsJA}Y$+wxJZaM0co1MMH+&s=TfdkUj!7%vPw&^ugD!?~?vwExFT@QVVJ zKRu05^)PX8pHA%Bup%Hg}7^9{IZIa?H!(+K;9>wTpIaW1C`FB?ta-H#t!Mo#@f<3=c- zd2iTmT2W74A3j_>UgT!BVqyvNRemNt*P4(U;UUD}HTp_u{fZnl%q!qSW}Zi(!*N37 za%&3nDYSnqYI9a*lstVk5 zE2{3%2wReM24do|yM_Pahh1=YM0kkzHiAW+7l@LG$i3gqA~+(7VuGRC%K|sj-C@TK zu8&NjIRrqDZBF6-ZkP{o$k1ynM~Wk7gMkt2i>xDXP_e8m7phda%Zn@(Lc)1rgKlp! z1vpN0v%Si+tL@L|yS`tfAluBFJ*q%0*U2 z0)gFov!xct+r|1B`jWChr(3R*{m$%5FI_DIvJC5-U@oZjL2126dxOz7>sBedJ6Y+$;>Q^Wl6r&wAWlC?RK0XSI1{1|Z+^|x{A zpAr#uAX@QdYRZGCjX=QBAYkB%Hc-L^A)CVyQN~-Lod&M94mP5Z7kc7tqwOX(fY)t_n*!* z3g_B4L6~_GSQ3XO83w823(zFH?N{n7<*qsWg7UcKBp@i!WcDc&XpE zBuW5ZO5^D%+e;}_{HNfKjhuJf_xHJ{IUkH{S|;h@ONymM4$}Cf&er50ItVv`D2GK4 z#;3jEILd9_bc{AZFUcAI4x=RkbLC_K!Ld0iLV}iq5%$O`ID5L^_MIHEWiy|Gmz4)+ zq$v5_^$y@Zx7S0VjzC{R%kOG2J~()%@xYmAL#BlE#BBJ+Sth4Y&bTwAg5M$;!}MqF z@#eXvcj^gZ_xti1@CEUmcp5Q0BQv zQX%)UKAryoZbHy5vHs|$de=B{a)hnwO|y`0jNH*FFi1$|L~oX0sgC?BU8R*2GXZ~j zq}G3yD>ZF`5Q9akEfn=fsznVb0f&tl)tflo{zS}w5Jy{)J^ks|$`yuNmDcxfZEBq* zN6i|0D&0iQ1P~KoyC|M6N};)$gMTZ$FT?NsAs8H+s`%ZZo&XyI_;J*|!x0-Uvu`B> zNdE@G-R@5y16b#!edqNYZ+)X2CgP!CB>9GHWKZ^va{Z@sW{W$sZ?N_DZO8kr8=U|A zSp33xhfrAkmAWsx{@Oj$d3n)(ZNDwCG330+ml>oB+inYbdKJOyiM>$_Yo*`!xPCuj z(cHQ{*nhAkm8qS{i1rqH`?x>Q`e9S>3%AGE83Uz|sHPlgK8kFxa`gHs_-UZ97<~~Mob@lKi zwo|#(ROxv3;0m*d%x2nZ_j?-S7kMu=*H6s9*M&LNsXv(_6JaPB@7+WZEiI||St0k# zF^vrDRp-@N(U{9h?)q|Ng~-JQ)O9k8naL_wg6ul!ZCks{gE|jNdv^;9?oBm%sW~wg z5i`(!F?rprNr%R=Il5(1nE30_$C`XXHuUXaj}B|_T-dpyIC!r}MQPVU?(5=YV`DM? zfV%-%m0f*RyZt-d-^sCJx%3_EWh}KvkRbGeZ-^+av0HeI|t#GvzWP#NLV? zo_NUNo_{qOY;&7Ej$;q;E%1rTk>7nr=4$tc88x1ZPD)2IO@`wHDkkroC>yYxm?~8& z|1d8fhC%U*1&<123ih5qH8`n82qx?3dS96XWTle3lK-<4k*TpPnmjVx#VWhOx0Gm? za@Pn>drgq^oDS(O{lcrr`H51$1~vw|#kkF_t`z_*L!j2Q8MeXVs|5Q=EgQoe5`7BMD2b4{Eu&?xh(O`RXNn? zM0OM0GuseVsdxNYItq0rL!SkS{pykoy8S1|f>jmQ?F)AzqueAN8HZd`w8or)X;9A> zKI1%%-zDcZGWYQWEnOL)X{oBs2rn1vUIn=w%rlo<`2&QVs;%v5Qep%VnX!J~o^_T- zj#PUb5Lvq5@8{3`A5;o1)mIf&k6VIBCKieQP+BuO#YkY%EMN~yzxT@4tM2EC-U4eJ z@09^vq;}#g%Xfg?kV+rf8R{ztid6q_qev?((|M+HxLM&xOZunQPdc1IKdjWX6D0YU zTEIv?G5M$RK$>0Q4-(|^`2;o%?_xc{Xq|re547BP0y`CEC`Ge$OEbgZ zZmh#^_fA?f8uSFNujLxro;o|_ec$=(*5L;&)P!ebi8nc{iH{n*TnAX-)gdKc8>$!W!}wUb)jGFMZaCx07_4-;rz7i3@AF zn6Fe)V?K=bwysG24Zgo6mUXa2-fSr>6>>||;Qk7+0};s!9rJVFKEW(1iWj7>Xe@Vc z_5yXUsT)T#3S4l9z!MtR!>vF<}PsEqrbiU5Bz^hU2!}ZU5Jo>wn z8*?Q8=P*3#vL((%{gEk`)x4`IF~vNM9gkOXXRlCSDqjv;`5HT$D=nUvX9+eFiE~aR z!>kT&!J+T#iWQ#@o|p(?*Ng0aCwE8NVcqxC^J`C4jhAzoJ}n^4BnHX7;Y8jK?)m#C zxia<;443crJ#s+`u|+E6zPj4udPr&guRum!V;(%Sd# zJ|Bm>nmJ1(0TeeDDG)Gvc3Jq!KwWJ00G0-s($dq0+ImaG$zGl7`bTxUx$n67+gA;v9lKT^HNi+{yA*inBU*^ z1p7{iH1%hCdU|+znK3f5vKQ9^Glzzv3#Cy?w^t-?B{$v8O;E>(2%xCFDlkgF(nC}@ zjAOAroh?*;DtUXfBPdBvjM94MgJeDtrX2T2Ix+Wta#QPlgME*X?<10q5#C4nu#3sV zQ>P2s;88DtddltW;xb%N_RS&7{E&8lHDTOYHZxr&I_5x}B2PS-vTJ7#kyG~QY*Ya8 z2QARN182u=SqzgHxz>D~*Ht-%IM2voAZL3lkfZ8i1Z-u6c+IcJ~=Q)lsMSt zSTK~+ZG7t}jz1VEyq0}|7!#^+|GsAlbo633t^9T@j(4hhWhZQr9FkmERyNKYB=SxF zJ{~`&^M@uJ+8iHL6oY-#)^ydQJw2kd@37^^&4M7R111$Gj{ptwV(?s88`_PFB1$K; zh2D%2oqCOepuKzx;O^JaQR|@>6g1)ul;ChllTpj#c34p5NENhYDmGnyfz=CC6J8Yr zkKx?p9L4M4Gf7 zFskp`*&5*QgfI7Uox35ZzZK3r7ye>UR@(S{o#(5LYckx}mNLkHF8Z3T)qhZ}f*M8Zv%EaeCczfn-0O8GezzLH~44dDZ5v`>y($x;c*+bJD#HHa7H{P=Lepj&nKSlBtzm0IYV zHS$jhEp*^-q=Sx~MN#eDTaX-;5~H}f+}X>=r_?e_p_#6i(b28DMeyxI3RJT#C()QF zOlvZc4~ienzhnKV(9?TQdv6X_81FrA~?~0xAjWf3!0`%C8e~(#8snp zcWo2{A5Y4()8oVX56lpMtn|mnK-tD?KjK{mfpN(tbv9RLaR#G_5*M)|;I1WluFMEz zaE>XwWx!bDq$+b9AwiX;6YB zbQ(I(C~6jgne<&HPWQjWc*);)ZacT;639F`H2h73fgX`>W^cDsfrYDbGGGMN# z$e!7T3?{qno0m*V@Hq&LUal=+cjoPvK7OmWQ1J?d2CG!P0ycBew-(~l>G_ZNU>zu{!)_U9Rh9VoCJ@zr zx7xx{5B;)%Pozr_(o45vCE707_x7zA*M-u7t10Gu3!*R87UCgH^!zBF*k}*@CPI6u z3Qv3x;Ti=2Kb}9wsZ*yXUZ?O%v>Lt4-GFO5cP7+oCvlPR18cys5$Dp%Zx0Yx*oJO= zkDND|s<&iMrbU4kwba51K zyg}8f0FVIUeWs|NnOb=cht0Ld>-DpAwABV=Wn|u~OO3&t(%Jd0^j%H96T$t)Riy(l zDMYa6o51HwiOOzLMOX}oB}kW9m3l=@CtV}yA5L!^>3UXCbr?&rsnVH=FWqkf33b*v zmARMn;1(R*Ur7vWp>k(BShF8)1rpC4ppx7;{;XGH8~blww+b|TY_F|tP9nWBjYbhF z3pt$lKG#s`_GQdlXc>p&md@Pi*Z1ikeQi%g;<#qazHF2ZOb_}>HCyA)i19Db6wm>f znR{EHqTg6oRJ}&~n|qkJpVOid!_{B^`c!h3&CBTW!6|!&BLs~UokKYo@RTCD;HwC$ z@$5|8C{_!kH%xp}@KKQpnC`8tyOf9r61i-{+YzojIEoxrvrLonNKo(V&KiioHVLtM zVaR>xPl_r{w@}bAGNnOZKi2V_jV@ZXH;-bV=Fvm=2W}3&KsQgpvMhyKkNQq;Jt`?H z>Q)|^Ao)~I+>5(`RD)VgFjk9=q!T3}Yw8{_w>twdCeNwr?(ti-Q#;z*qn91 zTrF;(=Z7Q6qgUyu;jN?7Dfdv`a8|AN+W+;!rxLD@j36`%8cp2XUCdM?HNBlBeAk^t zqL!+uh1}wOWeN1vbuy>8!C2}guGFTNrEeMFaK@tI%0J0pR21}|P&a-w_f)cxiFTZt zcYpfBxO)4$4ec*;-gOa2+7r*+b2CjERaj$;DzxyM7%K7Q%U~}s#-I9L*C<)Z4e^>K zq@ZGiKO7!4dfExT1t`e+tZKLYBDpKn`=?O8A)OOeU+wki%r-mu(8Rhsr2`BI(N8-& zU+*n+Q=j|`v7`C@CyzguFa5J2P&POLKVsA)lb!OIJ?>bprN@*IYo&ik@3EW@2~ux& zvgV=-|AquEdrLfx|L&MW1|@pRGSAdb(rB4MAHGT~y-TK7deO(8rp~l`UfwTLLr*On z+BW?4UNJT7_Q8V>|< z8tR~+pl|)NEZ=$OW_FYs?KYPg;r>ocHY4FhUkj#-jOY)GL|6l#FA^3*A#K|yzY#{^IKVG_-vtj#r{w$agU=aozx5*-sk8eKfp5d)x9=J^HVO zzFKx2%A(kjV-u^1?P#-Wzj<6r(F0aW2#V`L(IsWD##^8%7YZ8E9;a6Y#FAsePP4aQ7}@2h)%W9P~#hE+bens1TNfYH+a*NQ*IN|CViF{kW~CAE4~FN#INl)0mqoMZyCo?fLM^* zXu$F5Y|kPhP)qDpyp`ESp@GXdH}@BOqhOKoDez!u_r1#=qguWv2vWvl(nCZHjd>3Q zcCB63SW+m+sD zM&Ph&XruzFWm_8NyBG}1*A35lP1FC_WZGf=2jfvBN7 zAqa&arbQSi*+!Y@TJd``2*rIE(yhOj+PY!mf!V9KnZ`~rybUlq=1VMb7v z3B=wW{%hKKKTGuES0gkILn9+eD}>c7CO69-)Jcu00beI|^(xZ~)CrR1-`r&dXNv6I zo0xA!zYImelyl~Q@7wj4dj`AO(j&wY*l=>E!xP@2O$8g9?~9IQQC^Dwrr=epvgWXz zQf9=IrlPm<7fpfd{ccs9=IY#db*(pXP53I7b!eN?JmTGXIfyWMk*We(5hj7##okWu65%;{vbSnl-x?y+`PvC?kcMBNa3JXoA5U{6iBKoN%pO^D*`7#~K}@ zYWFweH2|;}meXg=kbDC6Nh-R{Qfali;nD$xoFZBCn17J3 z*L}9O`)%`*TtjV>^qYizNF`$VL`(6et~9*NPL08&$yf1Zq)R*SslCV~oft?5Z~sD( zds0ndN@ZqdT|Qkxw$2= zL`pb!kFCQ!pW{{$2rKnjm*w>Q)y=Hj*kxIlx=q*jFmV?`lN(ljZ8{u9`pssY*ZkSu z`NKmdwR2sUITw7koT0K0rWR2@ecj>FfAO;aU_4D77WRuTJgM_vzO73?I!VcC`d&|lSn(PNaE}JSTb@T>@%c*wQ zt2Xy7wjCr>f(Ax77woru+Pf#@bI9uF{OF`7CM0G1^@|dk3$obvj5_DvBaKn~LT1_5*y~oPfG{^G?~LbctbqGT=Mp#0EV?b@jf1X9*_&%bkb@ zp`_I?QCir~={%_9LCU>jDZ!iLVsTG{lBoN1Yd(1uQP&Hw$0`yuzo@thsf)HW+Ut}J z)W^of`CCuyX3%Tdy>}RH3`&iw!96Ntw)dFVv2(8X=m*=s7Ba_J7u7pk&MpnOE2G-H zVbtq>*-qeZ)aVFXScb^&-n9|Z0O2>*LP#k^vCT#ku_(73$p5S_0D5M^S(W#~6H2;T z4XXEvV4Oa#7BeF(LqM#j0cvMTSHTiy@vA%xfy%^LBX$~#M&euPvw%ToMr0+MTQtuV z=y>_}aA(D^VsS=Do#w!|0A7y9qdiqCG&Tvkm}NDqhP7zKp4jhI#Ad>LU^}O}ob8=E zr0=sw_8X?|)SuZRrpfm~^)*YB*NL_62J5|$XbQF{XFC8ZIlb;sC~+%$Kd|V+6DP~^ zD|GIB-$@EX04-jx@>(AzjjdQxAq1k`Mu#0EviD&q8arK6+rE}-uM$x-27a9g3^cTV zq5}B4RZf)e@7D%DgNM1jF3|cBJox}6!%75>5ClqKE#$Q;h8L#~VJlVUJ*|ivfHer} zG!eSobXI@bo6!$Oi8#5`=bLIDd7T&pPzY}{1l5mv1vz`#VD1w02I0Noc+1vIK*tk? z4~d2ah`28J1Ey?PBvN=8+dmWH+;Akee*(%)KUwz~EDOTDDM9irr~UkY9s#WIfDgvX zoNX)^Q4JQ0V~=9b*Q@CaFYAjz6LQoAqtYe$O&`;G0886FlL@hl=Z&vZFFS6wUQ*1W z8J6Y4&Ye3l&tt>-J(GRZ!=0=r6}<2{!D+9P_13leXfBozlheC>%Mt>l*z=F&1pP|# zckxi0r7H=+r~CWvQcw8qu0J_->aET3E3XZeM9qjhd^Y~m8;)BBy5(uSA66Z$u5pUn z&1jHUMDHH=bF)a*7cw@k!BV~ZVnP>d;}xkYupa^>Rx?vVgo)EivDf(vP2DRxpp_PB z8|Cug0nL47d5T6>A0_qhQ9(3g#d#s>JWO#i{utL(`%7rty|eoFn{w4`TFRbQKZ|Nl z_)-PGAPBhj$KbF2-bl)?PQ7O9Vip1XbdHzyoXKserXL6@9y%44a^FxXPDOaZ`Q6uk zbPa-YBH9C`C6y|@65ErhX*&|9>a*M$I~Xicey722rRs39@VAakxnCN)yD4xLch~x@ zivhJ@snHVnU0Re@eU$R;D*`f_TE)p<>%5DWW+kgoq%#?%6obwLiVTpMvWHFfjD`r0 zbzZt#y^9;TQL^c?epCOc)9>4)=-|fj*`M9i<)qzF=3i{hZZ92z` z{xv=vG{q>UM%T*~p`>c;*l}sEfR06TNH@04W3N8>%W}=v_;V@ubz98haMk(@Mxv$1 zBiw=EOWq^H|GThO|6qG=hV8+0TNY_3%(1k;lA_DqQ2);TGqaf#Vqk^lPe7-%`;_XR zOLhNUpAePYc=~bsOWlc-MSB^s77@0stLzE0*qA-us3(_vlYWk9<@;uR>gUC_+T||2 zZY`8IQ(32Q|dJP1?!j>EiEg*mFgyfg~4!0|I*401w-q1#5qOS zy4+qKPWQ~DjCp6}j-VesuC~Fl3#V6)brIHA(vI%8r%gPi{ARdVcAbQ(Yx#9K9>4>! z$Dcdxh~;7aD{6q+@6<5c{RR0hB_LgZ&c($R}5 z0cnhKC@lY`JA{@6+~tigZTNT0duDRDcNUxmWtZdpV)q6_UTMxcw$y8KE1GFQHr7I) z-JtnIbg=z>lo%VFe?KaA7I5Lt1-C=;LMv2$$j4z4R2bp z_c2du_>$4UzycWVL@O$m2yW~Z`DUnl=eK$~EA0am6|qa|*IQPNc%~(PRo#*;f+}C^ zGIM%BOFP!ZM}CLhcno{@EHC}L5l0C(@7z!1_73KT{jF8Zn|yfI7K>F zY8nd$%Xl#Zo`JTx;00G3@t&_Luh>8-piN&N_N^<{`^EK{!P@R42&+gaXa7 zXgcU_rS336I}8ln}itP?Z)^XB2>cXF*?-QuBNBwYiozyyAGe82RH zzCotJpK^UqjJ{oR6Z>D6`8g(?^=B0dO;*HgGyPw5VN&rj`*cUXL!8U^X;0s)A{o`? zpT2VK62*=$)6xTxp8t8&BOo#g59bK7y0%V(_QP%Pj6qUns(& z*Qpcb&LdsnHk&T_N2)*g@OwchV5J?|98SMEOlT@Jqu+7~U;doNFXK8wvUXZH7qXEph zjTBOw>gC~4f2M}pclhL={urh74`zk{YDtI0x^?CqOW!HKX^JML9bsG4bVTD*9>IV^ z5e9zohlx>#j5*s}<2@U(Lf?uFr zOIh*zaKt7ue_YN+S)d*st(L6u9jhX4J)zL9d|{7K7!7XsCPObBe(wA=hBzz2#J7no zDeJ*qE=i%t_^HQEoGlqUB_@_c=x~A2FG|Ee@ukcFOuUvWM~eHxlYvEXpLrHvSW6hN zBBGLWd=Y^S-V^l39A3o0YVsvf?K8gtydZ#`(g8SU4{zsXzH)jwwkm?r2;UZ|DxdF@ zINP|v=zZmuN0i-TX76KBorx~|aPufY;@iEg?>$LC){t8U#V%3yV_kqyR1F__oSkZ3 z`|UJJGk~?p-uQ2wPyUj@Qc|iaL2|?}Y>B9WHmW$SAIS}9!HMgyzVuU29NYTsTS<^M z+!|h6Uxm?J+3OWcq1xGt)r@}FG1W)9mH`g{7w6yWxTJ%tJ5{?9k=n0b(>#@gZ1Q%% zFDQj-ry{;R^SqG&+&jfQztpRg8VM|FJbfKxd~I=_T@D}PN|Rf#UD`bc11ZDZ&$Q4? zqg(auJUy~-CRNs=86&|mQC`oyg_uw8SMS@Bs$RgwD?wal$Bu{w;-Balk}y=ZnPg3u zj_dXke5%@+BWloQME6`fyUQ%X<1SO%b${~b^NpeRus&X_&w4oRYUE`AlYONz`@a0K zbnsKKd$N0~lm!6S(5-XalifrL;S~{lO6)PN$P33|FFTQU(q0K|L3*P-QH;^EMWF;) z<qlP_OOZJ?FG&*K$fIk*!6R#+s#s8bT_Su~kwH zA%@D{DUnEJ8HH4`lr?)~sg#ls6GBLgF(muGy`S%>bDrPtec%3io=%-JX1;UZ*Y#P` z5vlE2?2Gx@$<#W9qm;_qGui(ugHVk5LfuLKi5U`aEbj??XBK`Q*%_M3U(j6ZgB?k^ z!Y}GmDC7P3d7RN2ZllyEGaRTQF~tMLw!1ZBTc zl?7ouq6&rG3dF94r04|2veCqa!?_^~8wGJVQ&l2F9}0~78S&tISlL!}i7m=RLWM}< zWb_`wCq&z@b^(y;<3`pml4<2mrt-Sk7$48@S36MMG)ScxhK{_dH@`KN-PH+;9Y23E zsoEzfxeN0J^Gngf2e!mh)U?B+VOF$p`4GbpH|~ywdXp`rjXF#IEvj3qAC0I zL@&Ed*@kQTjVm6_F?}zdx##K@#nrJUa;BPSADP`&PjwB(e>#>b5)TiM#-8`svdDor zq1{#ENLF@-0ix`CS*NSk*yN#5G7$0W#$Gog#QBWoynJeEZhouvc|-R&yhA^eOqUfs zBO(gG`4<#K_C+Xk7Wphc!9yop7mmu2n1PNbt@nOJ0L(D+D&TBJjblPJH1F~8{?e{3 zi=lTqN~po$*d&7 zE3!);6Jfg+OZZaPigR62u86BX7aN~g?beUwW37v^8`*)9O!Kb)ap{Qnct`* zpT7n=&%B53X*6SJ5M5Lwgi?H8J6PY)NMk#o>;|iExyxNUdpi zPWD`!dJ&-5L<32hrLf5iJSOmiK=B3D2mgeXhI_7)X{e zxNr{RJmbW{U(YWYK}djzN8AOxA6+ozfxrKgM;L+9tX!cawdP6umV6LQ^7%?EK#5c9 zJOs}*kEjM8<9cu?H>8P@(85S{7Lo~gd?C2AtUmW<&gdm-=IRwUL-pjBTzLp@G7p+T z7c5&Wz4U>1v0|L;A+=G*KcbdtB*x#+t@BH3=pIy8`|O6lF_p)VMy*D^(S)}2S^;7U ztnTk9Ledq5Beegv{(IY)0F*NyAt9h9Uah?z64Uo0Y&`|=_|&Z%B0Shz`- zQEioJmNFD`>&M{fZC(ProfhypA+UwKOB8w$%A6_9NLE6%HjB5jV(Qx-oXiDt#(PD` zX&fc<1G&x}cX}mmUZ^e=)~cz;zlxINc1Etnc$vT-4?y;(QIZCkgDqZ{{x>JbnVQX} zE;MJW=r*4`-c-eJYgn^viP{Tmmx`9MyR|1YhST)9nosUecyQ}lacQ>7yxqI<)^tgc zJY<-BBgZi!(j?7ZETF;pdnz|Fau!fNA)-P&RdeR(AxhY^aH|mEcqIJ&Sd712+kRoPmXGGUOE_URYlioQh&izSvOWaQdr3w@U##?sx}yHT=*!8IO!Mj34% z&`Js`gGY)0WdW(g@pTqop5>u5#L8w#5v;Mq8P9t_V0ZJH{keqlrXmfdJOP0r%AYKO zqagmONYzP$HT91P@^4mOwCf*jC1dLiVhP4VTyAOOh4d62$hIcs$35|v-6St-!1)tX)_!dxi>WXs{1n?!>7mQ zVxr#R{zqlgxcy0`!^W3Pj4rd|8XA_1QNzad%!zmElFz>oEDqbUNKPYM;+*y*R!t_j$V#(6AB;S^1Dl zqtku8U22JRp|nQZ7s&{nL#lVI#diT{SGc`TnAWBc7|TQU@PAFn|5BE*haMs?Fx0N^ zmkt^s+)>wktrwpnoWWg6?m25!Z7M(AGXq#o2q{ z)SxIqDWc{L`V>j=SRi%@IzTY+J3E-Q)m7OuMBHpQ6p4gV8F{>kU6d5}I}t~8R#3yd zdnNwPJTk+tZeB2a9{H`O)9(#M6YsRtj(;x`$UKVgB1kc<-7s_;X2QjLf`lstuM@Lv zSS)hWs9`s*(`<7$8SmMQXIN^9=j5m~R;CKYi>|J)lU%6iXfiAOZUQqSnK3v!6ytmV zMci_YBH^CrhN`(Qitv|65omSK1Y8}|-1SLNGI>r6+x#s0etq_w?p}J|RuRJSg~Sk# z-?ID}gkAvzbBz0F*(pbGv>m?(=aO>w%j-s47QFm17^-de%`^FB!=Su-BrPEEKTWaC zq6O$~4dlAiV778;(XN^~cB5sU{kJuG>L9<9S~4EvVQA>u6VQqY?-KcQxp};!`n-l`zwaCdi@xG(#YhxoMhu$rfj_7+f zt}jMJbdFcjpeuPW($nAo9myd0E@AhMnEzf8Ltiw8Ho`c4arNC&G&xHxF<3osH!|-= zn%2W|C^T~(of#f!SM!Mut)5=LKfc-c6pD{NXo6tSr!cLZwqT~qQTuh^JUjWNlVb`j zo^!-!k57LS>udAO^u_$-E{gGX4J>e;C;TffR7ovqwkhg3IW;*@FGKz`pKTFr@dXP!3}WEsuR%XvlyrunQB2P@zB-fi~ESYbXOm&7Z<|Z zRVy)i>gPjukXYLV<`S76ovJP~=f6h`Jg_b1VMXX?7fv!IJrmV@h##kSLE7y?F84oY z_ zTVAcTOeweis&5INKZOdHH51qczu(c-h~C3vt{O3`nf=x%Lz_*;1oczO$7k2nAQPeX zq(~}%g+iEn=q+69)bYv4!$OVpTUKKWzHf54)TcJi|AxwcntN7sw6|}BM*Of?dpBEm zJ3dJJxdb-Rm~qvf85Y`X3*ypjUj*2l@Sz$;S{4lPI9>$^%t9ITEG!=y$o zNXF4_ltID8_4wA-B_sD?Sj7&}))I{l_1@|#wTRol2K#@)bvw z=bnp&Ck=4%_-*70@UDY&pSEEj%>c{iIIC- zsk|-cP(Vzcq2V-C#W-MhL@qd1fFW$X9u2DduA%W@)_gE z_VyMp#h>19;gXFym|HWWx8mb78pws^BR!pG#R-6OreAXA`%by0@Yy~hHKX^Eivasf z51G$o#>W@*BxNc|R1`w;7clf;U{ca^tduyMA&*oBp1cUySTWZ&Gf45)Vqh$#XO8Gn@GrS+v6U1 zg!SCzUZJ>i=R}wJ48_o})~Rspe1GAD(X$c1D=Hj|&&=By+RFzOfZ$^nmP#(VoV|WJ z>UhQJ^cKlGm*q2TCI$!F%%@j)8qAq2{3pXt&xVi!A;moJhe?f`EP(RFwRf^?aKvUe zM(L~}xQyHoGjN4Viq1=-X=>12KfB`(_C>*h1P5LS2SMni#>cCfWOqC`NYva=bLU~_ zQc0v!bed^Ln@?UN^uKO1G3Byfb5==%q^EMjQ+C9TZ5j<(hK6IW z)SwdLPr=|{P+QDvv&YT#qf|S%RF=G@eo@>`H;fgi3WI#+jEbm+1}AcG?_5PztSfzL zQaLGx*h`9}lvPy53f+)R6lPnnlrV^^c@S17+?rhpF_M7{t95f>Z^EsTzG0ORm{1@v z98?#SmvuLmnnX?$+2wox3ObQj{MQ{q+3J24 zBxti*05^CYtsE7i0@U89k4Eq!jdiF~=Ye}ciPlkx^bR*O)kcz8|H{p35mj-MbbN2;Q;9WfSLoH(e0|{mf#p+vF zY|AehW%2J2wusM;i$dkRJ2i@k4gIM{Xb+!OLsnxr`&!)?SLfW6ja=Uqn$F2#`PjKE z?&@G?ZX|w!*L&ZbLB>7GVdeOm%i34n?k%(C@lNiV%xnh~0IB=CgCC;RT>0U@IkR&s znj1m1$Fk+_8X#3+86;3-c+?`NKT#$yVI!z8NAKEZi~V%VX`LwyDBDAuyW)3-{wrrsUi!GE9?{gV zx=3yX)(Gxa`a*|-35IGc-%2dEZ+Qvts?=eCIO?(Z;-tLAu}fM4|1$u8b3hjXmOI8I&$pva`uOQ~bemPuUmnS8o_0 z)tAt__D1$iY$A@DIlZhtTqU)I(@um92qHva7&F7!h3m7lPOPcVLsSv6>k`y&N*fxo z56jiNt=)IED$B;u(5Gebm4`q%>NmO(7NyudTQ9ya<(})h0)`X*ca65J2!tpMPL%5f zA*3=ldHKZdo6?}f{v3f~kz;lu;^HA$HThEHh${$Yr-&xSS`Jo)V!tyffvX3g@t@2xU#psc84IU&xfsRHwR4|=?sdi;-C zgoT3fgv1A-^TgJGoMdaAC;MNoo%?qR@~9Aehw!5u{Y5Zj`1o7pf-#U;^2<`+r1;Mx z^-3XNW~zB6sg_VJfuA&@!(7GzmfWphG~qh@R&-n?^<{1URZCzKs(- zZ)`opG#kw@DB`j3SL7e@6G27|sLmAk&#^7507~JEW$oNF{fJ2THrJ7#g6F9mt;wvN zq5-sWlzA0Sj-SP~#;v)6owXl2N1y5{#khM020@zcMw z=9ks30-S9&!u;059TGZSSl5GF^mg!-Y* z0d1Dzp5fsd z#Suy_b{0*8NY-xdUU1Ohg>4$((YLJ2cza;XadFY@UWo&ywfJq|5`UK9-C37PoBjH4<|O)PMBR*)_Rd&rq+|3wTZ*I{VM$K;>u-GrR)=7%rbrEzn>jar*a zmnT$ZnKhne71uw^1J&GDIC(Cif+R)IEfBVe}L=Q}vohwsy-z=2dVRBTW z0uV%%t|%WpuFs*IniqTVq@Y{w*mAgS0 z0Q7V0j;LpI@vVk*khg#%y9ZU%?$16Y>A7PKOiuGL(@gcYU>C3KWeaEJhfDk6)qhdH zAC$DJf4Hi<_w=?mX1VJuqQrBbKR=dITmLS0B5i2H>=6nIJ?HuJ-s*#*x3+rOU6}59 z<(41rE`*N{Kp!-*63| z;OTs$eQ&Og{Ec#_!~C%1l=sO%x>@Z6kfo=(*VtTBIG`1_q{kp*s!PEA*8Q09$ZpVm zamG!auO&PbqWo=1w}lQ86YDfXcjROjQnZM*=SRZw2lNlrpeOqBGcDJz^)6(pRRRvR zVsCoy)9CQVK5>WpRFUtr@vcMqvtG8#ze|De#X`>{_-Uli)nMCKy}F>j&~|9>{jUZ?&>b(3YL!GMgW6? zIi1(FP0y+lQhg5>k!lBoKXs)udz=+oZoMPU<-9YK)3YSkN+ zHn0d3tJ86PXuGj#c-&Xz8zKY=rE_OdOE%i=cWdM(?+mlu%{}VK*kxgmF`rlpnU#El z60EOQnNiIbFNA5B*2?PANR1h{Kj@r1X@H0O%En8rEgH=$@8BS2N4ji#<&qx|)o~L7 zc%}2Os3D!yS&qL7O86;j!h+T}ON0Hk-H+1t5rYlKc*Q-phGOBL9J!?E0O57D;RN5$ ziagm71J-3u-D$--7OaQ_C~2aGTsRU>7=S9ANIwWoM15BG#57Jd0-Sm+g&xwTZutGd z3dJ$0MPi>>&7*??s{sFriGjzsWp0e1CaSJ^wPF+ShR_kTcNNC*8!` z=R-tTRlWLhhN1f+qg7%Rt0YulI*sDe!)$X&B;2WCu?{K~=@Hr~Yx`Y^c>hCrvfq)` zm)zxHDq%_M_q)T%rSIMF+r!&Lbm(T;$cN(@EL~eveAhXWVDD|^_MW)JWE;-SdxqAP37F ze9yyhT5s_sDyZbzN>P;+#%F&ByY26$2rm2p4E5Vl3;*bbfq@1 z1&>(~eKR+ro^(-!o=EmLWZh>OEl+vJdv;X|Nw?k-i*7~>xjmWuxjqZ;dAmd3nK%S_ zLDA3sy5+o-Bu$IS-5pCshr&l@fgOKyD_!qySshw@Hu6k9eINPrN1l&OC&X|O0qFtC%R>% zV_hARh8~b~V<;PJ^yp<)VYXg&HW?JF(O9Zg*y)^nVK<_e&tI|D3f0ES73cJb_vPDf zG3qyoC-K^PG5Ulb}^$LJu!Z^UpaF zfli0HD4=WP8BmsNs2x0P$>JB=mV(}60*B}6$tNYRA7VsP<0WK;k3)90VcCL#{`~9a z(ZJ3@ofA)N|Toat9S@8V%!x+(A7*>gd+4`AiffA?Yk^TU4 zAwR>MygX9zS-txNAW&tn<>E<0VR24qFnRQ&j-V_GB*{9ujtBqDjF~1iqC9!p0J*HB zM&US*R7F7d=k#i{F8CuXFNxm&*o`fs%V@M+dnV+PAii+1nCKU?namhDD^4)NPK{sS z%%#OQqR?pNWU9{)9@xwbZemWxaZIjLBh40)YubS#D@nCG)8~-$kURC|8h2+dr?f^L zVjJ-rxygID$bn}^>1@%s)1Kpln}<)@e{}Vv(P&u|Z4%MZE3Z4CHZ!1>x^^)%R_uJc zuy*mrHpF!$W&(>zUF&CoKV0RsK0N5Jv>K1;$(&?s)DNH>A@y+)1hP{po>N*Ojh3awVQba7T=Wt1X3S*|Npi)2jG4oM z9vL%oApf=HTUV&xwp}u2KfPltX32Q<Q4pzU~Te`VJGZ0^@2 z-8(hc&DXuVQ&!@cg5@HC9(EZ)eN^A)r(Wj7hTCqtB`1b5uMbOzC$wkHFWu)iiAw+h z37QbkxSdw>Qk~i`03FJ4X{XpY%+=7}`fni+H z+^;XZa4N@>L((O7t;9^or2JkSj&Sktz!eA_GSd-Z))GVoph5sz4~WYG9x{W`ws(Y! zt}s8Ji8CL;-LT)*ox}6=H2wpaI^r$<*Q#On3MK<-t#a3p$Lf~ewRR#X$g9N(h!ekI(^0GFD3hkUIdr3HCkz)ablky(HW4rsQX9U zUI}^KRrXJ%JUwzHu8Pc5UuBmG5ye+t`B{p0SSYce@_PFx6Pj3)ZAE9+RLhV9NxCMbApGCLm68D0JVN zpc?dn*?WLx5*F(miI$PLE!YN$jztTzqx-HB<}|b@_qei)YaXYvoPQ$1r1Y%yTVDhv z1E$#GwNaqtp?UYS6ylm_mM__uL%&4!JHd%q7KC6$d=YHb^CN8&`U~qLhyXaFkIe5C zh|fI`B!%$giu5B;w1}`dwYz<5{AL6s>x{KoX9=U^KKWsVfB|KlTDyj<|HqB+g#BhC z0z&n|mR;Mh|Ec_@8I| zPLTTNPP#f`MwG*}tv}y9g0K9UaOZVPEzR_dwYJrt7EG^+ey3hspv_$-bj;<6c+H+o zF)cw>s+qZd+R-(rdI$aGJycn8CT65OZOCWlAP4n6pKe z7*j&atT@#%8RtHn{o))cd&SF6rET}=X%mUE@5bA`If8=A(%!%1e7$l=;}kQ9rNVIH zs0x=PpGDhYe8S4h-UpyFu_r&TaHI)sJwCY~T;18SpAUtE(jGlq>F_eana#gc(7#n& z*C5bVNx6ceGq)BxcnG)CpU?%pEHi@_UU#8=%zTZNvyClkIe-#tsr2BQyLcMF2IR_l zHbv~4`dsFF;aRGp5udvU`80WSna@?{g%GU-1@vmd?~3n>GxakX4dpm`l8rnS#CZX% zc2+pbwOdq;9icqn5bMmfyJ;ON%PCe-FLHBbz|#P}tGk2=jPXb~?bu&Lr8?3AyHTfy znQeF?U;1?9nWywpi(mwqBjMCJl5ud={llfyuxR7KbGay9KxBWQZHkTFsRJR8y?Q*`(C-CTv73$5z7gXJQY1lx(pysU;N&t;y=i8 zHmwDu7aLB~yRtK&6`q5Wl50?{^rD~uY-m97aFg{P+CXMaYcp*oCVC3rnQi+xG?Yox ztJ3}O_=t}0Q7$;4oFfr5K>WS<`0=;x8db1=BzJv@NIVcI3^i9^BmQ9e7h{U`L;-G> z>}HS0|B=p}@<9AB9`ecI20Pq6#E&NZ&rf!pDg4O%+s$dK^_rh3t|YzXGfw-mhr-R@ zm~l<7)k}!Ep1EO?_t997)9M%SerpA-%-!%Sc5UT92fYISGR)kDhR*1@WROZ0TPW^0 zyi8uQRHihI2+JkzJH#@=Nryv=8kQk_xSSQT+XcJBmXIaxl47%M z0o6`ZC^QWX4^pncfWJr(&D(|-ZaF;6x$s3NGlHd90e3TThp1oAZyF)IWrVD3puSxr zK4xSZ3WERZ?YY7UDGwAz3~y!7_??ee9Li&;R{oHb(F4RaP@8Rs3eQsCWTg}xRvQ$s zXNEr9Klazc4=@m)8RE5o_~miZ%9PtUFhhFRiyRLWUTI{pzt%~Y@y2AU*>{m!&k#Pz zSSoVi;J&5R4k5zgMD~w<+{+Krb!m!<{L3)Lv||nPde~wt`Yny3&6>iF{k8ggt>@xn z*0PPz*z#x)`tolo1F4)u0z9<>u)3Roez3bnSgLm`Nu4UcoyWFofTp0>zd(QXyu}3Dp!QEMdiJ?>$3o3*Hi4(iKGD{;<$W3 z*=u9r9rC&UiCF3>7m<^djzMwZwC&`;bhc>Wopyu7HyBqkwv;-oLmi6p0yJ@SUs!R} zZ&T?H+_-mdMB#GjQnK(zE7*oNu>_g;U1H6d={3DgYc(rJ@-+^~KNwKXwkc&0!2mB` zy!}0quj$x%+~z)7+H@K5@q-&wBo2o~ar+hTD|ZS3CPLJkn|ORa&ZZ6>TVA$tDK=6d z&OO)oXSURS{Ae6*xiiINUuTHr)BAN^b|QoOEYrC@pmy5zdTl+*zuhpynz>$;AbF=2h^h|JHiET)` zjkA7iXZWfrn@p0B3*;VX3(^?7>3u6-+p)Ae#$+E#?vM05;-vLmZrL~M>f)U8Jy-J) z&Gr5cynm&BEyCoyk@4-GidI}R%8Kr0r*}H{FrB7Jx;72dlz)iqRj(BltI8eML=pDNI8k3)8`zIp?_Hrb0w)6l=hla1R z;SrhL>CU(@XUl5y<`KEYI|$pp;9Qlcqsvqt#BN3<-3@@34eoCc0CK|r&hvfGK)CUZ zz0cEFlhA*$N;ftI=@4gW^N*+(iRBNK{#hpSALb^47AN^@iB%umaAGg4QznIlg^HU? z54w7$u0&eZh7(l@?i7hVTn8nBgz+p&*WOTzYmhNJBQLh!>lbgbcJ@VGTFl|>iMqGj z!oD=UhR>%=n1Bn|c7;=Gh;h|za@0UbMmLD|v*U{;>nkDs-bwfyTDSidhsd7vZ9Dmw zp+eld!c{>1NtX-%J1`4xO}FTQ1$A;l%yRR{nS>Z=E!C;Xu^m$dl~9rik^?O>Ki?8| zW02M_^MQfTW0J@Iz5?g~)Nth{1I2HQ0O_EJQTPL~NHDUJ_U{^LLi8+UD>8isedoXF zI7Jg$nE4gktrN{bfj^ddl14~TzTLNom^H{;+7#WVp3Ho5AjhoW^>RU}SJq3TH`}aB zagH4FvK)(<)Vft%?6R-tt&Cggtv2=7??}x~4&^2LwQ=w7&3^D#$v(}GWg@D%GHBr!z^b+QUVskZPpI7pJI$|%_DyZzp82tVKVIbk$_3ubMUrt zfC%!+rFAlpUT7L95aktXaBHA29z-}w;|wxC50u@MHlm}l({rY0<|eLVSd*dix?@WY z+$RC=g)4EJaFW>#4e#6PksAAzE7E=tQY7LZaJAs1HXesLm+TZ)&H9k?=Ajq*t<(~ifE<3|E$eyUQcD5djQ-&7 zR?VpIzy)BvknXr{yQie&PHoUeL%6Ok*z;^aUD776{(w^yS(?@ynQV@Gt@lDL0MW!6h>`7_IsRz)hi z@Zu&QA)_NY@bHu?hQ>bK&lhqlmKxZT{n<%(^gHE9sW4f%73_xN&iaVn*~kdn-;oh{ z^XkuvFC`HX&?xW%d;TN2pl7Cqd4g>IrSws<1BMAB`gp(D)fioa*-IgkWocxUE3qjd z$2a8IuwuzI{-=3~bY9hXOOw(+o~#Wl;(0gxTMJ-|gQ&;p@CJ64TwHk2V=L;Kd;3Of zPS=@>uPs+BQSCZO*2n%zHM`UC!6%HdCw!5u3%=Qbz^(;f-V)8zr{&frHqdv z2kRqJ{VOZi6Oa2({5)ZT*Ds*!I^t!cU&f5pVKFS-7iKfNW@c9AriVRr^~b7#E9_ zthfx?P*~-=#JRs|#9gg|#vnP+ktT)-_FFa2q1EUmwLU~=f*6-Bc1_9mu9DcoZqKiM zV&B$Pe|9uFpSmu zWr1Zt!#yXuv#)n~jSjL85fiyR|9x8Nx+vm_Cu%X3$bnD~YM6+X=N1$UH=$r>WU9_F zJeGZ40gyT@bOeA+=vrQ2OUnvzWZZJ3G_{;Z_6?AW!3ixf1Kb@v-nCUp#ITPc7P>7< zqYv#!dB>08yn1E9U$8KbkLPyf#!~4;8f7|}8PE}+zqzdJX8E}0HsEZ9O%Yz)r)d4q zEnM#+&fm)&ql?!NZ}ptK6}bOf#SzzZ%z6)(!~B@ZgY$RWZ4pKb$-`yDt?#ie;heN=cy0SVyM)Y_y64gZsNs7su z0rNvx21JBuk1vtMpa-FbbrRde4IKV*WdjlDB-Dq`Y|$ULq=pC>zKl=?>i< zx94XbM#WG=7E|iO^;jx0&XeES2fs2Upk!}w08|(`lE-yPt zJLwN)`BnB&O+tH**(@)JKlrEFItzAwXt*Nm!Z@jumI_|#$^6S$5)ztRy)7K50oJ_M z-$P!;e+*db+nvn}s}cL%^jLshcKsyJ{G8h~b*4*t9qQi~_=agd8@x_Sd}qxD)QZFS z)H;J4Io=gE_sNWm_;@Cl$`oLv%x#xZ#0M1zqAjh%BJN1kzOl9;36)yq)SaV;uhNxw zS2!u62mc&|)ObpEraOO0dRNKNEv~kcf?a&lA^}O`*}QiW*ueHwc|f6jZP

RCPiJ1=dX`&meWs(Vhc@X&$iouUS!9oo~O}zYGQ%U@#$}D83xmL8d6$WT& zr0pNqKx<=}&SSZ12SZ0%lq;;5^;s$}6a_iuGfg`R)E97mkfuLWY^x}I>bEW2nAIL! zyH77JiGUvtq*6}J#R>}M<(tw~JCp)iWy}~P_E=sqPtK}@sNJbGh*TwV)A_C>#GfSA zJ&1a@CB$eP2t#c=IqgtyJ?BQyGDtAS# zZ#qXEV_IA7XJ?DNdE`K3Nh)R^^$0%t*5!o%LP4P7%{`BkR~N$v6Y|kBP$1@} zR;x%M+zO~Yl{)g?^?~KRC0#ONEeu?Hz9=rqXhxDkP*-}jLnN!9CnY&KYWu2Uo=uj$ zwFLWVEzx@XDDD~HFkNN75rYiYWJz%U?(V2Nio$pMd%IS+A(eJsV_>|FU|4JSS z{Wo&OZO%+;xBYXY8NcJ79wQ)FH); z6%b0lnZ9}7^`qx&=MsC=`D|@Iy`H7m^1w+kY1C0n}YMiY8Vg}Ry{d^Q`pf| ztnu7+AuqH+nSf903uD!}ss%ho*f2^f__b2*ymi^e&@FeBm1K(=#oE{uNu3o>U0Gj^ zmFVSqn32OyMVXn_@@Mkb%9u5|4)p)URU%{Etq@RU1{D?8?mv7&6!0Xh&NX@eM!OF5 z!q&3K$9ye^*IAr;A+&jo`t7sYwJBfskA8RQW{W0$IVdsYUC?7Gw}W`s|NA~bQ_kY< zM=)3;6Xe3qv3!2Av*V7ajtR5v?anoqY>4088uS1L@og%atGn#OY&8vjTzJuaA)#dx zr)gQbzp3ZK3$&l*?=|+2HD2)+BzjBq?#-o0>Vc#|g=rG*evj*gT-ff?vXZyNuWMcv z+hovaA-8w=P9nZwm|i8EJ9)iV^CEAGa)pRlplxa4yi2om(?9W@pux?=sSg!Z0{efI zUDvb_yb~oqSooScpZty9!f*v-yEBOnG(2E@v86 zy4{=fNpcp>YT6MHJ$ta)?MCC$ za!-@E5L6s#-}60fXtP14mruMFCqBA4m-vt=WI_zDjKw(|IR2hgTRtns!=#3SC=px! zy*Go4^_n}NfVi~vtuwDGdqias)B$MljZ8^Q@oR?#LvSwnrR6BSRTI2;_CcNj`6}Is z>iGDR#Vz%dmPk@6chz6eP`_;i4Ni^8XGcGtd?wxy(m`hr11PpV{tICF?X}}D+fB%; z42w0=lV9E6K6+lkiyLugXP^51#7sY+OzZ&pG~0D6)=6%8lu_dW;DN1=f4f2Eu!rPH(V9vAro;T$o z86E_fB44rPM7Fx65wIhBe#DSK!C6i(gEw|>_^N^ar7=Y1{2g})xF>XIT0yNc8jYM6|@%{2_< zrD;8`WA^uK>!SpV@^O(wC9ghn%sM3{B|P?yfC#(ox!FQYC4@%gDc$-2Jtk7SFp-W2 zA?Mi=1(QdNGGC2uN1FPA1|@fhKB>I-?j@1M)*|gDGCcN?sq0eMP|wNXWNLD4jPP%L z&w0WBIw>wKF1F7rEUax;SG;_%KC;+;i6GBx>D0`$N~iV-e`&}XYAEZ>6e`l+Kr+IX z2`)#_+IT^2mRzFGe$r>E)n2wJirrj$Jf|m#E5{;|g+RQnK4zF>;AH|Z+ZjfBZ1t9cnCWO6D&;kSz4gwI(C*GnC66dZI?ZvEwdbHCsOQE zk1pC2ls;45PB^y>j&fj_JOA)6R{&ITtJ5tF4NJOOm~n!0SrMdt=s}&|A74OF=W$eu zhj7ZUU)1eod}f^~pDle0^IyEW;$Y`$tuoNCk4p0ac2(3OSWQ|gxafGYaQ~Fq78uW5&Ko6OT$1^`j z2wW&d!k6fOLeRtmtUmAU_b+u;o1yD`@9D%xQ{ew%T%742I#;t_Z-ic-fv=#R?e8SA zgkL-U?ph~@M@c(mPVCcXhXlDXr=*uYwjXkrl>8wgUgaRjK+|E+0V~3b(A4|cN@?Rh44vChXD)vfySVmhT|3#SUKAJ03Gs~*F=SmK(p^t!`g6(JC= z!d}Ods+W?(Vk7nv^YJ$o3uVsxIp@-1oPUAB>%4&o36lfDP6rC#BQT$j1Cua1fXSZd zZMg~&2gLdM3$BZjVYxuKh1d~hXXgh>!-zYBbf!q`o;Z7r<+agkm?qXyHe0ys6HA?w zsSh{k1@_2Iy}*6i-|HNKsK!Hquj@6`63VFxfLtO|SvQ;e$~isI5$ode(HImfzNl_j zSkNAph?!53px4HW#YQ4#=wIQpFlzu=fJMD*;cv@@+AiXez%%jE6_dT?v)hQbW<>;9 zbU^A%v_rZ>%fvZQ0WA^9Mc4@M>7(+qFEG-d*yt@@wk-Nf6N&GGPx9Abjd^DuEoN~o zPo09TmFY1vH3F8A^h3stU~rsFR~5)YCX04(d9gUp#qZm_?9z$X{a>1#-CQlm1l4c9 zA4^{LcnP6rxXJ6_*aHCPbI5BR3nYG(l{#*xhAtG`mp6F%Tn}5tph?m3vN99#1 z9};&fEf81K=Ch_T;=WeaSCRNDZ-z-yOT0O*@ES^>$^61tKE5fx@I9TDZ6_LJ-A2&y%1oY z*u+33EIGRxeoL!{BgG@$+|ewuF5?vBIZ!129gwNV_4IE;Lu7f#;pW11T0?IA36c^%MUJCUQ z9Zd&4s7ciVXy1NkASTbz`nmq2@?6vLirK0V7Rq2@BLx#3y~#>(A42}lF1`i{2Gu8s zf0tbn-Z2C}fH>&#Z~Ew8lv%kXP^zSli7x`;?HJ-EQw>FVaZ@EKAx!70_q^*l==9p@=k<4zqOe&k%0-tn!gqDWZ z%T6A-J)=h~>b9q(-o8Z5l{gasdRcL4nZamz)78w%PaR9zE&teHx^c}c{?sdP|7~`K zyRwx&hk2@v?86ZLhnB86LfW=5yFmS1;sN4%$a}eRhf1?7`_KB@tZZhzjxR?0O zzahYuf9oeMEr!k5!$S^a9kltCg6)KKA|^&l?}>l9Hat@HD3ukI9Lfi{v9I-Q|4k26 zxPui+bowrfA&FNjA76c#A&cTRx97*rv$BbgNBzbQ+z6rXPApcGF*dd$ty-aDXjt`7 zlub1Iy#?~KGkV<$L}k=Pyf6Cch>`CeM^RjPeP7X&jL9vEkD4abn$l8DeUsz2)EVQO ziv@=_oRh92*dW6q{a2j|xb7$>C=PmEO z5276DYmrojjVrIJb&}gD|1ng36Nf*PPfL;#yXq;fysrqvX+RkT-?(ama76&DLz&9h z`vVe3*`1x*7dD<@lu>r-2Dw?|feZwJxNm82;8}n4{S@CVYT;HFzj4L8vg1^#^pZUc z68MAJV(L8F3Wy;6HphBmqA%pL1tOB3FDNPdN-rR^9Zjtkz}>;zvkeLgMX~rigkP8veR}v*%2Hvh_VSKy2*+6_B-2 z;(%-G%6z9KJ`wH1zhR1h;h{*7xeQW>z#c9^FVNqwc{WMjVxB+tMx;!?>f8zcd$Hu! zn7tA^S;h7U!fukWZz3)~Do&)>79FBx7w?nZy-U@tt&anig*>5-W>8KWLAk{3bWf^1 zCZAnPXfmB6Egd!-v5W+Bd`2a6GSg89qz@a{r+pLjZ%0avh*RJY*0^Ldnl>HwluCA_p#Jz*!KRGc=qe#>O;kG(KOQX0q<5!or zhH=KVHiV;7!=~}^@V`6O<#k*9uwe*m%sPA(IU6w=KthSjTI077{?cMp*km5jdk}0P zJ|wK2BUKE*NbJ!jp?d>c4)qOw{PftujCtI}J2~l-Ok>;KTFbeX&qJddTFyUgJ#Rw~ z>J3~wd~L4Y^iJJF3{vHqMHU}*mIk|A;!R{S&@!f8s3-6Ig-xzQX@RkLd1Zw58v4Q~ zb!W`v~+vvP&sXsfvWLGAEdPA>>v9tc{6B@UosH+XV zx{7C$N&(J#_<+E4TwTuG0KQppu8j~1zaxPqnV6cQ3>fj-)(X0-%zcjW!TOHd0T)c5 zEp~OtYoPWutJfLcUve|)$`N-pudr7GlRzkdBL$+df{9gOz* z*4F2tH~LFUB@zH_^op|iWnCPXxA^_cbZoWbXgUkdEz{ zV17$x?lq!M4Q%zQQWaa5Eh??VzpTl1VU!Vx(ZMa5xEETH_wYraS@Lw4=zYiM$}tz~ zG;hcP+dQvuSCb4}+C#9ga&9!Gn7A~MUUkp%SS?<9n5~SWeli(XEjGRyr$&-4)~8s$ z7Gu7f@6%KccgAVmw#wN6jo#M-NpzbAbetSI4&~ARY68le2O@RrBuTd+E2KQma)J`c zsyb+q1dUrerCEg)F%0X-&?o2aH6cfA*2CpCn+vcbjR_6=v934P0G_;%`i}v>agfwR zaG0UitOzp;Xrl6FuMU>;GC_XBQuH9j#6l{KNuu~}d_2a^o6^*I3 z*1=Y!<{^kwK$&rDe1V5Kcj8X&x}f)ex0hn3lVx+6!-Jt+^dvUi=x`}>`T^&2Mh0mg zM`jO}6cD~l@qWf<(#^~Z&i*Mp?+luRdPZCc)oek5TrpB|bfflSSGxtxYzVSh2Lcbp zvBAp|RUY?3cUc&6?hm&l%7?wgs{~x7XZ5iCGpu|ue~05cgtyp;-zSNX6s3V;(c|qJ z;#;AE@^I*DiGZ+~$wjHc>{!0(LzI1%e4I7tzr_FIH%=CU=~%CR`<}jowq2kw*r3<9 zlfz)1CWNhU5CfWCeB@+?|It9~0IeSiZng4cDgu>DoALB@*a|r^N*;X+CzdrD#=eYlqXZyl&}BtoFs`06T- z8g6e3t$NT`|3z>z2tXXnbp{o0=`$ZBgM`tkQ?c@`ix&dAJ{>BRZ4|!Jud~i{^VQ|4 za`4J$Myw?f28*wCk6cE5ZnpBMA1m$x*iupeU*6Fn_rk9cfW$Yw$MR#AKv(zZLCl&G z`0@ptuR?|b;Y2ZywZ!Z^@lT5bY!hc^(^8#E0Z?H*7 zW93p{1$_TY{ch}LT}IjIRqCT-17`^M5Gk`KcrZ#yG)Bld|hw;_W&@yRixZC)R)AvLKHRL8I#0NSW z%lUS;ds*dB(DOSpolk@qvYb`p=`zufH${n~!BS8S9oa+%In00@5(4aUdC;uXr~F@t z42FpTnLURCA~P0`BVxEA%m0KQ6aue!f`ok|f5r!{mGM0MlS7O1S_E8y+TJl}g*oIV zj{M0t@v2+%%_E;Bt_TjJngvh-a*suj<;VKOTR+bFEAFfIkS^pZp6G0;f8T`T`h|9x zY@;#po#4LG7fMF$PDa)YQa+|5vU*KD^NC=& zQ9weE>&;Gg@j z?3ec^{jq6gdKu4SyAcNIW~$cYs|mGfvUa;#$>Ql)YTk&;#+3Ow%l~@o0&f}++n}eW zVYVxca%#?7h>(PM9}`*sf^)m0A5oIM_P-5!jua7ns9c@yKKZ(dAmy=nvclSfC!e3& z9=szBGHZ9e1n662Mol(>NnhTmWtE9afE-0>ze{(1y-m}Is=x{w zWc(k#zC0Yt{f)cRsiP87Lb8+;l_jN2LJ>(qDwRD+h3xxYWM3+ZLX^ejm|Exj- zCxSRnod!rkUU~A!rjnMv7ug%U<|S5DNt-(Me{m%vD2yb;WiOM(M`SIkeiGUlv z`uvu^x^vLIX*K6T7ZGtD^3Thfm$Z_vR~)-z>`dZ*A15hTZD)kf7TB#+;=6N&O}=OpLUkcf+A<8nB>48<$Dmm$>Chk2x*}FbGv5mLKC}svxMrN zx@Wd(p{LnLjR>}tgeukx(Bf51&be!_g;|6dD50i-*+!ALZL#xC@&L9fgiJ%DH^6i$ z@xf-Aw_#F{0f-N5>;c@<{MLjv)DZX<;b>4)1o98}&gxM-HIjmtDReo-(Sr5I!oE&* zcv?nXLP`j#aYi1owV#J5V{FL3pUx9r9523z{W+!l*SxH6n@!LE784)SnEZJ)tcI;?Q z3D`!^b}C)wf8?2__BC$d-_SCLUZ!Y>PnXW{f5QAnci}`Av}tN4nQ-A;SDrHgFwb9( zm?%|3VuwpepAXJx!tcP&N3?q{xXWNE-B<&j(FPEh96UWcrl6wxJV&t$f2*&lx&L2g zEm|zpX+l_cb%U%?aLgyOU`R{rY}0zUeuBMx<7vy)7~9L~#$f_&LrwJQfcSRUSNVBg zJy=UXL}8FRuR`FZt1JApWBX3>-b@3Qsi=VsI#QF%I@VI*5e4_JPcfWE=&Sxe;)~$C zeX6JSyPVv%dO-P(GG<~^*q<=3_6k(%+S<20u2QAzo6Z;_iyc_+=SSg zRw~}x*?B$Hk2opqo3fxexOm5OyOM~K{%~=@aY^Th0j0GE_HS#$h^!2Ym!A6Xhx=kI z)Cl9V&9ysz1fuGg)XTQ&L`C{N@D;l;GCs~`pFK^XsDkY}n>hCQK;L_ni(5q36Hi>% z=zsEy4-z4|Z%RZpB6?u>)3MP=e#Pcx18F8vmkQcmLw~Uk(JyJl%G-Z zlFxT@^=?8HQr-P5`=2Na)Pr?L2p@fwitzV(&zfq-+U?=_qtP66aDQ4vgUl9j)3&CP z)kfhEl){R% zZPmMJ^Eszf1$lNGN{EJFs^q#8FH|z+99w-;YDT%vpwi{aKPLBbgy9SZx~&R1BV^k{ zU-ZqOwFy&dug)K}Ji=DJ!KvErKw1Q}Z4g93bVupw#ZW2|;;;WEQs?V!!Sc;+gW2u+ z@324lJZEh5*hAs>8RyoV2!^@_lr4*|{e-ru1hUh|SRkWl5%v(XYl#l4s<%#B1ThnDS_Ge9WgI(yh&V zC`(;J83f$%DQW5%D5ZTg4ue*`Yc)Dy4~0D4jl`>KcQMN#cIkdt+zV*0EzTr}uY9ax z#A~8$_~o$(mwfgDkHhH%t(5zMY~2_kycp1f;jY2ANaGE*88rQ<o4^_XWGTc`%4t(DK)CZaMg_)|Oj|PS1b|7KyGpS~7CvXmsnSn3zUq{ zW)M!o2bZ||$tF;^CGwU<04e$ET-$rmM}7rf#P;glsuaoyp=k$q>7>ZbS+*Z_u7uhg z6i%!Xv(Z%zlwSV7h#K$>sk|qk92ifEs@fJ~>m0k$2z!e}#lKl$p0m-2NN67a{wfd1 zvwmcIfadLoq&|e5FvSrSh>1@|!fXqiFxV9hYeS^($eRY!xf?=3H^K-Boa(8uJ`?A) z2WX|MQxdf^Z!J@_ITqMiUwCYLV&y%IMAqEIf_?trMBQr*Q1vu`P-g5()HV*W0v!PViW<%K-K2NI)Yg3a>lO0v zDezhgc{m&)$Rap6(b{cl{haz;qFSP;ixiuz?5JXX;9Ka<8+BRU&=EdMniGZ!6u??; z-nYHPome7oM>n@yvZU|1=KI3oN7mee%JJSVcbl5toYG)(vwqRA`H>4eVZ#J6C2Hn9 zxRo43e5^Lu-LlA>yuhpF(koI^5_49}F3~2!IFoNDjaO>KZC-z36V`=-$M2o)RdEV!A?2_IS{W7P=#c{LNKZEudum4WnW zt~14ZmQnHVedW5ry?^URCvT{#e_dUwv>gq%LOAB;+mvrcake;KI(^VIXE8a?| za;tf)xA?oUOWr(o9<;;q)fKx|EIkY5V@Y%ewakUoIZPbkU-owIyt()$xZyj=3h+Jp zpoyw)14HF(7!eVw9O4MfbX3AZpXXIIlU9@C1r79xCHE}2PO&0KvvE!|#8*9*E2!)# z)Xvm)+v%8letb%Pft(F3|~PW-sC1qot(oO0*s=mLbVv=)m?g)x)_>t zwlTeP9V^ptu_NvA)Wk5TyQ?eaJvyf5t;r^B^@svDahV!^P-WkhNVk;NiU2*gT_nY% zm4=m7wvH$q_bfk`)HC--S&UIndN!7h_xAd-_I<`re{HQBk>tTnawgS>3oe@7-8B-B zp_2$5O#bE4UxjDwL__N-ZE67`SVt~hR~(1c3S6-e%C%?JEg#u0QFzAI^I z!qv#?)Tha{NrN^5MJl88e>d?EdzTdH;CIey+y!;m)phiq-MJ$&a(IpRb zenlz6%Ol=`tj4ZIWnJwHd~+C50u)j6V+a;+ErXDgd?azC2XE!|bZ?(k&N)=Wo*kpW`ba`(osa?6kDsg77w*wdu!v@W69jjS}ilpT80@@rh?_~dG>~sKe-)qx{TIaEm0UzJI zv>h+|BHR8h&fHVkkIYW@4zrbaR0_zMeuh@G7i-=2Qt>7_O0+YiGuat*Cru)>%u-Bj zs7DkP=1d1ISHwArQpc~RI%bC#;}tI6E+v=#s|4#enJ)K5E+NL6pPi+yZ%a4mBaM$k zO7OJUnRM)BGJ77G;p!d~TwnN0eH%C9*LS;SA6u^|D{EdK-EA5Q5r<4y?(zp z3wsmJvk}*LNzC6jyrRNG%jCXf<_TAj5=M)m-Pibp!e5 z#+EfQia0f>`PG#&=)eCpcMwgj+Q=%KPp zn0JNoF8(lYBGiVJm6#YQ5)i1lx)N!@H`K>#v?6A72h$@3lsSF1vC$lugA9w16RnOd zOnqk(HF|=GW1^&vH)&_=hOm6y3ACQwrn?&?CW_8*|1JubV5)|#9+mp`)WD-7Cpz9+ z44mckh0BSJ7Q`G6l2Zvzc+YmK9d|x%_Ab(7kuJXUw6}4Fy?7M{La8>md<4A< zR=x`h`mrx14`x2qagi)99^iCgrY{1m)_R&Ra*+GZm+BY8so5?#OSYA-O2d`W#OFeo zz@0{?lphTazS_IKdBLQhQpMmw-Oy`!H&=2^-{ghOy3@LqJOU3lwweW7+ty({b)D;B zUqc9XkyStX zwCR`CiWxg+!W$U5O3vk?NP~E;4Vw;+a)c&Oiye8JS55%n4ncNqQ>%A&b?ebAVT5CJ zlsI=ovOO?6+sX-GkRl;S7((X=S6L$*@JgOGcu|BJZLF!9zl+?1T<)p)Xh}=r*sqC} zlv{(cU{5WPiIq-*{R@EKsASX_7hOR$ml>-I*hmLdyuI+++RffRi6P8+k4DnWxd`L7 zeB?Z7u+3--HbU~3H(68>Anv=E)FiaBWQy?+UmBanZ`E+|&vU$$>B>~e!@n@fG1&Hbjqi60iJtc@-TJTXX#7_h&; zh82d*K~E>D@I;bA<<{(Cb-j*+slW?mI^+?a#I_RKJrPFFT5`?Po3-tnq}xjfSB-AV zkm<->tHTAH_fvEC3J;wpc84W4Y{7KO$u-*#_EdN{5!S9(3?FY?pSESYq5wMcP>A6B zU9)dt$RLcb*;yZ~OPlan2KL~oj^fdmFbXxNxjHAEhax~O%j$x0{5%l^IJ>xsE zI7zx@=z+R42dkNRRI=yKAAYpg@*rvzXR3s~qEdT{laixDcf;aof~XQ?h%PKVNY`Dod)i}NB9Kw&_x!9_6XYJ$V z4G$GG?)1%A!}SgR!_~?F?z#-!o$4Km!K(?139S(1M=@}31L?plgTX)|07L}J_%xA9 z6DGhGEZRgLohtA3IjFdAUjZ_)E3=?Vg6l(z02{mf(~27K=WVvvia6+geR?DH?{1Q8 zi$x2M8g_cWM+L2pMG4cA>A%`-q3iY9o+Y5caOAqzc3llGrOM0%0I)b~8^g{`^|!P&lm<7BEZvj2Wx+LKQK^aFyrlySGH; zobaxLF>C0UP}YX!|8_csQi4i+E9)3ac*_~|3;%H%^S_d)*5tdkFlh$X71I&DMI$vS zBJ0Y0?iDaXsC=|w(+dCQ3p{?k)0dQ{BkFvPOucocZbqoo;+r1{;ruNCuayfEXx;fn zJDt)8IYHDmr}%{P6DS7Gdf&}Z4Av~uwnxg!q!T`^s?i-hBWaeGUXC_ko8oO?|8!JB zRh4pOsVRzGCfi{@W25~b3Jy8&$5-^*CypW=Qrf4kCY8fMrQ_wUV7Nv~vDUwMN0HFf z)Qsq{eoBO(MgS6|ZX|kPRZ62h)fRO!wJxvAUqy%m%bDKJ=yHYW5*3PFc}Mk_U-+)o z)PIApYNpK&(9d2HgGKwrHOnfH&+yP^Z#Rj#0$C2y6F!0Q{$X4+yL)(zaPWQK&x6GthyRRR8K8lPyIcsj?noH&-WLWl;k!w!I9`=NwMPm zB>r}h3-G9+@+wYg?kb$pv)TeNzXt+Pv>ARhOvd9nvQ$f2exBCZrdC{3w6fx9<{&xq zCI~+Rb7gRlt(%oQWOH5+H=TvA-m6W(dD#{og+9^M1P zYY<1!taM)dOg&+8)7+6{cw`bE8(BYV@9W%yJwG+)t;>PndqNpsm7QYTWq=h&#jYo5 z-=>jS>O!iw>%K~mL%!VYrn%Fv^B3+LhK2fBctrU^#I^4e{?=#WHrym)oIZZM+k994 zYbs;ouGOQb$G&#;Bo|M@&3h$JGy5BDkh$L4*>2@(tr-MrH+amt6%-h~W|yJ(eJpWm zqot6#laKooVbO}W2aTt7$v%ch{py#ms<1-Jykm7Y#sSdWm<6lHduy=8&l5=siaJo> z|3*U9UazCQeOiC}D}pTFY(Lv=8@Id?#gllw|647l<{gS_a*lh(unc`D838EfE}kH3{|tSRx&b4!77ZjXllhmV@_X~87DAu#HH)> zG9GPv5FIJPPgqDGQtJz94u&xM2m8dNKZ)S9p`M&-fCj=jgVZoJk6%BnY<7b~+hc_n zu`qKvwoiNGx0flBvQtTs(seB&kq=Fxpux!ERSOpX-Lw8z>#QKN3pHXxNI`#h=S(_9 zf=E$a;q?W?+b^0w-DV%lR_9=rW-Uv&Ir&VOqO<^z>&G(%X?UPmL?I0t-ZE;EH3}I@ z0&euM4EqO&1h&m^iz=5=J;mwEMWoBnOU&9NqUCyl`K)3W3JYP7o7lD#=$2Wq8m}5* zZSv&IPMH|^5_=3yx$;|bZ8zkvpq zLK??#LXGlu!E((qDev7Yyzr%DhoQ2OF{A?G#3uOR^=W$voPY~%k$IP6gM=e0mcK^M zk*;{irTb;@+(J}M&&^wmT`yB~;`5q@BESMjS~#NcE~owKKH12*Z#6VxvaJwQ*EE|| z;~)vYLbYdnN1nkq@aURl zs1Bw2m$iB;FAlnrGZO|{8@N-jUjb2M?rVU5)8#=Z?vnPeh(msYS2tBJ+mIDv?w|!$}b8Y2+VMMzZ7;|U@{1$ z!KVg1lnIv_dOFCG-hZK{EM}%p?EU9$gd)C^&Q+CLYaJnrFtN_~{G^;`ZGSx*@nKCF zst0Q)XE*g=Ajjgwzt@OsaV#M*pl!DVV{_67t-HC7WSH!Vr9A4XmXk$IXT=be@g`la zUOCHHi);|+&v=Hr%J7Y2Y$Uu=)6x_a(0SlIBM0DWAo1qpYK$nz#u9H4g@mfZqQJ%d z*0tm3CU>qrY?kr45$Ee?CnA!yyP;Y`98^dgBtuR|%#YSNefEj!-yZ*w^IR67Gr8^Uh(#E}LBl)HAYA@UE*02QLG zE%KWk)+$TbQj5yIibdsB(3$j)CFjQrGoly`!UUQ|Io=pUxrNDo^ryuJ#oOsqsLB?3 z+IR|r{Kb2nd`C-;<_fI>ItYgaZG*=XWdJ8Lhi?T|Bv}it$=Kc4Ftpz+W9Ol-gwxHU(G3n}@GTPK!DL0dN zGo_lCSq$^EHE4rWL=z&nP96ZK$yHnSFe&ZwA1xAt&N#Hvd?w ztE+pQl2}8=NY82V>#SLZY`0|_;<3572}^TW!p9izKL(y+2OP+tDRI@?u7<;`w>LR$ z$50s}DOWxw<^+2^$Q3?MUD!A8{OOnSnH4-eVIx|xE~1UKfroIK~wlj;F-bVFz%udz~#5s$l;3>3Y;xF$opb7jUXz$V|poj z-$MIbLPBn~5SVSBKa)>hWr|Zd#B-l#89FNhQX-%9_s7tYpAjAV-D_`XLUhrSkn@hk z59)ln?f^P(%NUfIdD)2#W-`jmWv%2qU(o@)4OAA-h3~FOYldQEaPw1bJV@D1FiUXO z+fKX-rz0;GMXe+T1ac5-%&@*9S>D)ksnyU52_XXDp!=-d$PSM(d{+iJJQVRlQvQ*$ ztuXbi&avhuh6Q5y#I4>vJ zbh0&3BvdJhKN?z37zOL!FeIslGrQUwZy0~C^ALj-hjw7bP!n#tuGLIfXG3_@VK#SI z_(t`1ku#K|MK8IiyI`ZHsVUyyjtOFD6IHkQushPfha=CeD9|BS1oRTyDn3Pp1E#hl zEjA9>=9mT_^|~Fq+obVP4cfAZVf@QGQx_q6Ty9Mv@8rK_`afuiNwnF+Np6jThMl!_ zcFWcAM`aEdC{rJnzZ0A4Fo^33!dZy;HpmfGPr2vPykJ8tr!MBy*PvPf_$?|Kfc4;n zw#viaka40sFynkj%o?aA>56C&jEH=u_B`pDa`;||U za?+OeqQNSk&d>RKwJvdMV&$?4X%rPOOxTuS-bQ9V%)fTobyp+-WoOyTU-~tlrxoeY z2SggRq4SaGxhCz{aWUvfTcfId5XGBs-nU*u)HJwXFG@h!t~MtKC9%@8DxHOf-pEx<*V9RMKE7j4=oFh3HKw%%V^6WYMlB(^q3;HCIn2d)yKe?Z z2?{-Re8zjEC@f04&OKw@j=C{C2uOB9gj0+~=5Yi%eKSGc)2a-yuU4ZwZ8knU<74`k z*8cN=$oGiPJv;n`X3SZ2Yhf_;u8KvXE>s70O&eV#bk zYSI-I6KQh*Qhvt$8uJVt%%^`EVj~QT8x||(cp-90Nn_P>seb9zhk0ZMW)DudcjOOY z83HuL#@$^;^;BCvakEvvd9A`X23PDVah@X_sHGoGleRvp!pw)EiZ(~gStuYrhSMmw zfbw5)ChVz!Pr4Z^M3`x5Abn9$d(uDd2;>)e=qXCI69YqYyyOgbc9XuIo{93~h5iO} z4-$|XESs?dSO>kKqsYp;<$iTT5mKaRs?AFDFBJhE>`t9lqxf(DGObjl{4D=9^-EV7 z`2~R9)h78*Hc$MTFaLFRjF9&{pL+NQ2^#wKHL4RUY9hk5n?z;^nH_N|rn=~DS3sY8 zCuKtxKVosE^=DPgy*}ALDA4TM;NEc-G}@1REH6_A*s)9X1)NWeT5vO`IO#Q_o*?CE zc(_Cqp?!!iasM@HVM3@@%nGxGx=F~$3?FEkDpf%O?0%36AbJcFaFJPE;Z|U$X-1b7 z&gyJgfb%FhlY04jxZk?@lP!Rin(uby{+iAD)sP#NoSHd^XDvq2_mqbt1Ph2n*56!#qK zzDs06A&hb1XG^z~bpt(5mY&Q+`zfG~l{(6m?`D<>jw=Oi&?=t%{_s@uuGLY|mG@Bg zC{@+P_)VR12fXI0s$wK@5y672%l^WA42A#iK&X;eCzvY0y4GO(9#IWSd_;4fbEduD z*x5Wz4fWlqu5RV8i!mt@dR3LMuU}hE9%Q^_QJsr8@xhD8^|_nA=5ETY##A&o(}gq@ zyxk?!9gqHen9Vz{$cBB!nMG3sHR{0-qXEiom6>e!#}H@xn==DT^A2TN;-28z%OM-` za6um*ablO1N$>uo9}O$Wn*#lZBcx1Q+T=I$tN&>5FFaqQODT>n3->K!lqhc*pyEEP zugtbM33iBVbKn+HH;dJ!Z6XtoQ#odN*M2C*N#iIJr*u$VGUTkL=4s?kRX+q;c6zo5 zx#k{K^pRoOqiJfXG-*cp?~$(bo5!d7R+W6;6p)+eoAr80`3+}JpYW_Oh35y6Os4gB z$(MAN3!Yck!V=e!jO-V~r<3pml8f8^P5PKfH4+dkO2jQ@GECAkVLQtbHs{9IMuz)HTRK59u!K zp!E#cUe7zD0HPU!={bJhjA=1wtF*T3u(BFpSJa3~#-LHWx4Gvm&Cz0Zf5aCOl~}w; zdvIMpqQ|9lvZ(#6r3dMDilxF=XOB@U*miric3$MJ zIvcIfF?_y&ja3!-(HMH+dr+wTv-n5zzAwfdqs{rvGlFbiHi}GUnUe%nrtN;^BxTY3 zz|dJ(_&l}an&s<*XTR_bkdfzHrqq@{c3XW(S(>nll+Kcl!+Z<#LI6TL=5z<%V}Huq z=x$7qE8aReIXxVFq=c>hhr)jDS6GHhQYRJ`VpDibH}g5`ZY+tUs3s(@yDyW$CU}K4 z|NXlh?@b>%3XesBX_iE_a8&D=C~xQU>pRf-^M1rX{hQ_#VB8t&Rj-&jsLdxsrk~*B_7+WdU&&2*?@p?Y3cwBa#SgtM(xeK zy$2Eu1 zx?er3Lhcd4AS3FQ*+!A3>NW<8H(nHm0HL+utu{z7qf;YVW_qgs6el^36-N&i@4Fcp zq`_Tv2dPtzD`&atOXc0Z_0r{RcF_f5cM ze3wjn6@TS~uOVsw1x>+8Q$-UEwu7$L(@}6_RI$rzWoTDX4m*Jv&!v2!~qCRH6KQSm}hQwoZ)FqF+(y=<|$KK^&>Sr$Qx zM3Tv|QUb3YdGM#F+!PoeFEqaY0)77Xh?i*pe;*J-JA3<{+6b}?c^SU^hULmI0q0?> z-5nx+hK0zZLp@(vG4i!jA-pz8hrStGT+9C){r7!bjyK_wOtpgEOd)lP0@7Ju?sCht zWb#OMPA_o|P8J+(WIWc_XoS!Nn+(Ig&Cv!#mtVK{Bd~EjKD^-FbqZ!fwyF~&dzdP) z#dvE68p~JO+zxj6a;`@M4o?r;kY={R-o(Cilr3jwUd_`oW2>9WE}|w@4LJPNx&|6V zp1JF2Li^8FZ5_?Kb(+LYaQV8I22o@HB7mF#NKJ^PVprB9*4x(HiUP#fVx~;l+vN%U zCk|lN`hL=^ZU^)(AlRUfE@Kbq1MS|Bvq2)SiTBQvx2Hh!UF+Kkv>sms=}x0PPn9*B zqM)P7gDKNs2yq#*y82w5oIdzVM_L$iB1~i%kzbOf*tOqSE8jd?K$%T(Z0+Hsr02?E zoJOBSIIeK|A}~i0x4qyqO9Fz-$V0IuiYSsmWf^0FBa?O3EOTQ&_b}hQI;XMXt?fW^ zanfgYw8nT-B$j`X9NRBZHT}V7o8u~L-Z+Fa!7LJKuaMyhOIaw;eoD@&xC^qsUf$!R zkfkD7^Mah|{J2~~)NPDvBYUyM$CC4()?Q~x+L+5O7}VL!=uR_-@{dJ7NXD{s++Qzh zrl!`%(j#RZYja&##QV=hbxRps6XrssU#DjddRy*%Q9RRmG1hE1qYxd){G#+wHvZfR^qYRuC-Lx=H#OX9z>7o!^GYp#(Cdsmir2LiGK9&CRW6ISc@3~R*8>Pl1=V#OtN2+a$;BKf6H~d4cvkc z^8@x)7IqYl)O*)tInTbQs44(I@Ca}csrjMS-!SAOX|y@iQKebFEicnfBf+)Qv1%Z> z!;4g;Lo7-#2R!)B^0~r-SRuFx&P^1=L~dFE4i-&w$uHP9S3lcBG#O7a2WO@N2$qbi zF3VH6a}4_&OglnA&vm*iBh~wlBBHmKC2k2fr>|joNBM{^G7Ni+JGR%^K2X@d+IydK zgFeJlMJd4;xF+E0hcoV*C)Y3VPSAKZVvwA8VbyHk)LKT{d!&+czK_+n6K6@)M;E&o z1;&}fauLQ+#$3BuL9ji*L$(V-urPg%|0C}-H>}&Z_BOX#aVwekr04DBkEiZbL>i#* zR|Be~)b!yO*Eg-euDedRZi+Bx@qNpgz`-R;uo(N*5&^ym?quz(2BoJ~%fW9QRZyK* z4G6Aj-e{q={Vj#885S667ngr7b~({pbvA*$Dtj9a;)Ohi>M`UqR#x+@%9uP@!x zd}p8+%kt-paICs%^6l);!+%B8x&Nc}q}l0{4d05tXk}7c13fdJS2O#{46vyf1pVc) zQjAYsng2^%PE*+4=Zs~uxBIHL)nm=+_li#M{JWpZl^a_*|JvOw*Ok>eeY7s+j}MQO$@&!DJ(JHkqn@puv6xVqxV0P_z}NY{>Q&`|M>&0ewzy+o z4do%*ZBl4-^8QaE-dG&Jkx4YjYG#}{I~7tUwSKmF)>BCV5u|-DthpnNolA7cOA(oA zU~brPA>&LsNF>oLf+~-1?iVWZsPPm+;3)XHqjqOD_;#Kz$Zaz9HfMz&O4j7TMtLkP zs2lfE?FwR2+J0K)XlHnQS*M$^)N}Y_bBscVMXCN^C%6O2CZQB`(wnKZyq@NN>rZ~X zDcz*)!oB3ziYcBF`QYD{cYR-o8M)HB@m;WYNMN;T0c&aPPh;z8}!gkd-o4m%tuPxmP+pEV7H27fzBl1J6kG3thPvu7dT6(+1lB8-WM zy)FE$rbpvs&uHf9XSs_`*$rHI; zh=3P_$&2tH2qo?Hu=g`dCH2}Ib5sFgixfH=HmI|mpKwtc%wezpmkTg#Ta*=j>6U&m zb$4Jq!N{vuh_*}tWG%zQ-h}|;fqknh-c~4cSII^OmD_ew!UKi_U6i7g&X^rZPeZ`+ z$g>mvZ@v#V**};QzSZa4mXEGhH9X>0lYI@~)~ZV-F7%156|>s#RX!o(NZ&xO z{)J;SV)w?WWtNfGN*VmJ^<`i4i=)P+pqk9M78Z-tSd%ep8Qij>S&Lae(~0VSmbCAD zlW)T8Mu+O2dwgOO{GlL~gL8;~XU$5QiKtj9Nf0=`D0Q|~60Z*!(K)lcmPg`8;z$m9 z9KM}Dou9grvq~R+37YH=OW7ViJC31TC@{A>>b+M_Wx$2~K!{2eCyL7Qy>04fea{pI z91A5x|I!P#E4ZVz{hv;q73N1%t*sq%^Ub|CS#?+2kLKuOqY92yqOMw=`9|N)lGeAS zUv1VgcCLNr1GOfAX9Huy0$pafHTIk@kiKsLYJGdk9;0C1-N?jhb67}P@se2M{S@L( zC7{VA&-cF>(^cA_ZH7V;V`mOe&*YXz$(A?s*AtCgb3nMZSwHW_ z%UVZX^f&a6J3FUwe;hHZ~3C zewiaoFx<*$EDaDvoRv(_Ne4>?0tA<5>uysm1fNv|?7V*A&?M&H6MIzZBF08G80j`- z>$pVr%@9m{`JwKL05c=LWq;2ox`Ybky~l#=U46eHw$e8yI7b77sty97areE#^NN*umlF!1C1m@ z+;TKw)4LlQxW7kWRoO-ArROrc3I1th2}&0H0Ora78dOccJN5Uzp$K4GZTaQ%lhL5; zeJ*p~$#1L`+I=P1dduBBgGh0FxH-ZZd1%atl7xay*fHWdrxcGJ~lekA}wvcmdRrxlF>ix+^W2bR^W2&;EJLrTcVGvMa2fZy&WqOpU>6nDR|Kd?&dhZt5^UK0bk$tP zP4%b54YlOUaW|E$P41Py*0FnA{s`GTw{qu;@|B%B$(vT_c8i|9Wj$(s&|b@_^6cN% zA5>U^cB@NHMTc9?Y3+P@(8|if4x07*pH_OBRB1K~aN*mHSjzut1pvZ><)F|^&uO__ zDfQ}vU-V_fSJuaQE)1X(08$!sG{RVJ&FYFTy=vc{pD<^-+vnUdg_KL;smvj8QofEYc@m&wv}6?I^3d?L9!N@>Arc8K;|7Co2MYT zZgrWtNbbRY@x>zl(GQYD%$0UvP^!S^-)qyG9N|zSWEu~z`u8SYplK#v9wS<2(SI1P1he4%p^4k;r2J`E>e zpLk_?=IL;UpGKv+xYr*G?Nj(u)U5W7&>BY-)_N*ET(32MJ?qe`*7a z;FVK1Vut9_5WbOaYU3BaX$3rN`9KD0e1kcUE7HC7`v*;bkUAwo{IBpSWXL^9Gkw-F ztvj6FHw=kboOH|;ZUB}QSgz4aS#i=oDwLt33S|WTVdx{$J4VtI{*Y_NmMWC`cas9+ zXDZH{uiNXnr^M>ly#2dGbfR2}xA*ykX*~t>+k9?ChHaP@;v}O|+N5(5+fbO^SELx} z>+RY1vS5uxVh(pw^vnrD^vLmWqcW5AV3P_kUh32Avi~K2Ilha*dQz-HSEn zocgpmc|l_45e7Y9)RdtU9fM{=A(o8>W6tkHh4h+1M>6CLvk02NPiQdD)>UW+i=dUK zX?-RS?eU1Qhg~D1jLxVQa8$Q^yMbP2!5b`iA=4V1>WezOT1=_hPcCJAWSG%*f2__9 zGdHNTZqZd*Mn=K=*5owho2NgMOHW%BTUb>YT%rF^LKQ1(=_EwhYTxQ?fJIR$vlkY! zb=9vsdYl)gr-dLNf%xKJ50*onr)DoXsL%ykjZ~^#Y>tX#&$mlY@}#&nR^K+hANsZ_ zn#V8PASlTH(*5BGz(-O|y5%3b2;m)krulez6$AqLiIwW9VJm)au}DEx3QW&E55@p| zde0&_?6H`A+YykpNVdIZYh`V{nSb``Ilp^ml3WjDQ_CBF_|O4N>ZNC_tRfHU`wN|r z0uwpPrX~EYATgSK8IIYgOp%aFasF4#=LxoR19kMg)xHwq;OGL~{07zLwggooMPD}N zqE=<+MU$q%JpC&f`M#F1*9egVL4zhsRz!mFZT^T`jUDqfabtH9v_YS`Jfayamz8Cu zSM+PPPxZ5qrCOb1t}}F~+hv8xuN1^#5wa|-`aB|6u{uu;LvTvpXgYiD9YVYhvHDao zf-O-BuH4NMlS-&Tz z^Z+U5{g#)V7iSs>6B)=gOrj!Le&0hL|BkJf`2+dQ6}Rw9xisk2b+A|csMFsN+Hc$8 zTmp1^kN!j?#z7?`qy4(~qZayK3O=&~cT21E+#O)jf=SZlI?P0>o!{$DTJDugykd^l zPjyaaQ4BavIG%# zbS03-%=W|h~b>YPn0dQS~d-+$P( z`kC+`d6-zWT(G8Z`;rEFaJZVJV}|R1gepOj1dAW4-(u<|Ee9*il{l5c1VGPB!N>`U6`!ozo1Ek69xNaQ zhw>;Q{Qv+m>^rm~TpV3ztVUtYOAIxbraXS0V|&f$7fx?V7Aqd{2>1LEcU_NI?`wE3 zIn}HuDOWKh@66mm6qRP-RiO2wlZo$l>a{0Sv}U&Nii;1h3|0hLSXwH+0&=iyFYXE6 zPMwFCpv;fnH@?s9qwbk7RGbFYdTYg6@dV|sHl}JuDH~I7Sp+4@i6fdq)Kguu)M4X5 zclQ>wdd^Nx;9NRZhwCIk7|HcNIxk(a`-D~el$==5D_h_+lb$l4MeZIbu%ZvwWqf-c z;Vlpiu2A(!vGMw{TJh%46WZ4iv?=S$cAKvHDr`NAReHWT)qeVw_JLoevWn{+#4FsdcXqX@*m6rH5nQ%%EW z{PE_@is*?9IXRD)3uUIInzuQVi+r8Oh-#7k@m-(I567`*N&fv)=Wy~Trw&Smw1SW| zmm|C~&VZpfNnc50yuI^Aaa(+$9p!6-E6%H^Yh?3pG$KZWcrQ~A{}dX%<^dnswd|1n zjY`LH_>%ixW$s|rFC5*Lp+cdjg4(Nl_OVP*T_IWa*1Z>oz~AH1@^3q~3=-o4Kgg$l z_n%F_Yu5kTqG(NKt@0&DN$QTg`lyA^dGEGRBPxwQ{Im)K@3{i48<(T5btlwpHEKZ$ zJ|iM;-_|X4ais8J&))I_XHYaDF&nn(dii@7tM+HS{vx%q=yD(mHRI#%sSnp`#5fW* zt!U4aowa8P(0lr|@$|9jp51SJl-HTZTHrxEabace%Euh7-Bz6c5Sm%`E+?-d>Gj!k zk#IZlqHY!A$h_-s^KA)~49p=-RxA}(ZUjGQn4}+dMU_%GW#y>z1d|)D3W?s9{$l?3 z2grO zAt>h^G=gAZn~iwDFauRdvy33FfqV(A2(UUqfqly!&uVI+L@NiQ; z(mJp&eQ3)RF=%%sI3WH_pN%yR5vGXVJ03TCim(^Umk{NTf@%uUhg6H6?QRxU`D@CS zAEls<5iBQtmGI;Nj8yL(ROlT2=jALNFBS*?zVpvo`h5m}CZ2McuujvT=j&@ z!Yo=d!$4#SWf82BJV4zOjz09&;05b9J$Hf{Z7-{^5*o8=IdZ8LX?vho#oLBLJ6E)@ zauRr2hwZb8J5%hYx&raIVFm`17Y>CvSEDX{&QejxO+w84+c&|J~GP#>?c z1sL~z3b7NIlvE&=h9Y>S7uLd=gTdkqhri|B{!Emi0ANKmm%@!(82#2c?gV?BO|c%# zeL}ub6CDufKc`{o16pckvzS{EnT%sB-7nmb6EcN&V{WDTX#L)tYSSoPZ}a;^Q8J~! zLo4(m5PWZ}^9K|RuHdx%)Nzdi6gI_9%lp$DJg0_dZ5{-J!ZBu2eU91aICqtSYJoNP zfO^q!MU8QHF);E?zA(QO1k_q&VLtLk8xp>OWX%%{70wXAdR^;nVNCQxf|m0SD|yd% z#xT^xqn^heKpyy%=~8U2Gdm{=c^iWG_QD-I{$S5;9&R;Va!t8#y**FyR=mQI`G1#x zePHE-^&wpSa#sxGyob*d6S#o#!t9_}N01MZtqMYP`GL3t1KWfd%N}bkVjv!_kC zDe~gCz|6F564+axLAezvpnJOR;IDDiD-iS{MivT`4|=xuqPBJa%gZoV@){A5(~2M* zLB=+%h&>SV%KB=?Jhl=<9ow~Q<(_av9yem^vpj~4Ojr0 zU0rD)p^q}C49e>ZXbrF#RJ?s+Y2Hz;J3@gC5;C=*u3%BbbbOlq=+q&j_qHNUc=o9_ z1#O6dwms{2SQLF&=vL+UQbpy0i>8a6rxjjl@8r*%e{>+TpI(1F zYFGrvs0~Tc(PyB#p-9wec2)#=Qya9?i<5Tpe!P@DY$ZR9w{wm5f^X5=;Q4+l^O4++ zP6<_$D0W3`Q^o_zTul}(Idv|~4JH_r5;-2Ln!RgqIJgq+vDx=T!&P2~DCVX5X5<=p zCyA&w+q-n`uGT)l((!X^l+#R4@5no0A*~1~)ZLkSQoBwV@S`dyDpaJ%Fhf`Es(W!I z^usX(9S-b0_iD02vH4Vu%&EqG z@?+YEr^1S_8OW_EStI7>>kOeAD^tuMb!%dq7mr`%UUnG|mKI!4cjmI6UmU7ujv#3b z$v5$x2ku*(gOA3^!Do3)W3~|6Rt;2ke&rZ#Z)w=;zkU&VBmGyAR8I{ZHwqpgL*|k> zi1yA)P%65iv}N#u0Zip^TV7x^I^F@sA|W?R3W{WQ`Y1Ve+Q|gWytj`mL>-9HpqRkP z7R@UV;uPTT@FqGrl{SYq%zf|b!;&fbE8;8-IV-K7WHdg>GjD@~16`487hT>m=wdCT zO2H;-rsA!%S7y~dc78(21|1?{e(~`vu4SUhw_yvHe31N2qQIH!%9AjOl9iQx_x+M& zXg40WvUiJngY4;-;`Cejx0X$+;_SwTU}AAF$=|I@{WI!~1!N zu5c!nOoA1XtG$!kP|XO-3*2ME)ltdFyZY>+wZRCXrZh0wq3PPy)m{varvFi*lxdsY zq+|?|32%$8;rv5D@9;=>e!WPBW{B|9xM6vno_;{sX}At)9`w}Q$vidZ-fRyA+&IM2 zSlO`%f{($irtpfhn^_QR6#QW6x{054i#W2Nk_P83UZh4xGGd z$LSE)L!R$TVFVFEpaJ)xxdU=M7+#!&<(Mrp{h)j1AZ#_q zD&D>YOBp$)P7p{G|NQlxs%5+JY}nJzC+-#UCleEg@BR9fa!FKb8`)f>{m{}pu@1$+ z{acqL%53q>+%h$%OA1^fsz%zPzV&o~GzW)e3c!Fx!js>>9*RHL!+w2w8bIDcs-VU< z@jKAmI%l=^OhV$ONND4*!>Jo1@G_Gqi6iV{GS&cz^37TNDjMLfM9!?vfu~E|OW9R% zNzt@9gK`f&7kaGr&=6jKs|RjH@MQ={FPPeZ%yzUe0?J<}s3$iL^6~L;=?nSG z-;4>FXT2b%J#Bn_H@0G05d)-(W(U;Bm2r&U$e(FbV_jdbV!HrCz~XUwbP|Y`KV$9Y z;PVkl&%zs_{F|utb3H2RakLW}fE$nR@pR-?a(^Yn4-jznJtrdy(mJ4LU@|aOkwSq6 zdEfC^t5#HA&Vf}lgmUlpvTmpn$FO{h-;Eg|r|unCc{%{remgZEFC<+DOmANrlS(~d z!KzAm2H<)tf9|3E{X}YBRdYj4;JUi8@o*KGH6ivurd_uxK2DR(hc;)dg*EBrOs162 zqH5!2ULG6|N!A}qNUXOhU9ZNZMbzLVB}7=8T;pRCT`X!#t{pstNfYxHLFzJV3(q&` z_mMRNh2DfKS~2h-oPe6nJ{sCRd-~H9v^RE7Z^bH!@gL{3zqLGRP)deJhoXAwxPsl9 zJ01@QrFgb7Dt)p@9q28+m;83$TWjvU>#B3w;jo`M)$t%nr(+778Ez$2$>@XH&3Vh2 zLrJY7d#&WwoSU}05!VN`vW7PJI!gi3dHC$bz1aG4mfuqT{lJuEa;&BzfSsR&)-}dviC#D zj}5|RysYjw)GhnfJM&KSQ$0>{6*^C{$}(u3kT}^Sneg`o4jpz6zMy&&>!njXKI*lK zwHUtRqYI z7F$F`XVloroExitP!=JhkLf*#d22480V5d@=ye@rv(~Khwh)?2_zfweGH0E4cuKsXyaMyhv ziW!CrL&HBgEa-Uyx*=>|M^G64+L+t9B>lacnDxmXRJa^9s$>BsVM0 zx8w`Bs5V@tJFgkGtj^W)**d5~zP$u4%Z+u6|3; zzn#ANNMe-~M)I^45n~^!`D?Ca7APrw_JBAe--1j0TvE0B;-Ws`wj7SB=F@L654l$pQ`ez4$00it$EsIOcV9eXmzd(MmjsZnEiZ3oZjN;Cy^3q%y)9yj zye7jt-^j7MFn3vQ1*&_dp9p7A$xu_joZ2CiFVIqNypy$2e1P(SE%$aabH@S1FHXza zoktuIU$d_L@3!Px_WD9@-3^OzeV@i}1Z8sOBLpw`_8x}^u48ufh|}$(R#wN2xSK_7 zTg}rX#9K)wV%WdOqakSMWu|mJgb0z}O!5Pw2kHauJXXhxG(6!aEG7&MG1-L@VgaPI zlb@zOD9tzh-mM({e4YDL2`qZYkJ))x6*P2eDBb9w!dyK)-9;*SJHwmU0A|{{>F`4a z^><8+FaO8R?(g3()&0}Cww8tW$C~N(-1I|eB&J!JVk6>mQvVBenA!#M1Cv=r$QdII%M{;Jt~CO3Phd2ixU1 z*mN)24NgswWb`2U+6Y}8EgkNf&aJw*mu-k_EA>$JLSd0Ql9i# zfNuM-W*M?9J>sJJJa{#cyWCzME)gw#WPR8TTuh1$(s%KDhULol_*)wB2K0F(Mc+UP zdHx$Y&m@*$Ma-0xnq+vlmm=bD?<=D_I}9jRxVW&Wwkdx`y*5yMM_zHNLyKtg?DymB zNcn%Pz?=d;@HTI{aK_qzSDg!TZQu5s7Z`wvxDI%`g>}A}^zl{heTaAxNC#%2mrE^7 z?(=|3X4Q3ugBF>Uxz=CLJ5xJP{a1Xk3tlxyi6;P#ee+Hxvd z0NCIIV&u9XQ7M?a9%nUD;C9Y$Dq&7035_KTL6|S)Jws|o07YneKW)g1sA5J__)LP4 z47WbM1XTVDxyE)G_Xn@F3?|h*NR1xN;*1EU z ze7UQii+xE`yPmz)Yf((B9d~^grFymDcvb>wd@5YSHK*Yx*JmP&f=;6mb2w4)D4<7pQHuEaHQYc+f;a z*YSPq2VW(bVnxA{x`mOE*$=uK3vZmHf}g9-vsZu z8)xiw2528rdTf>rN>`thg1yR~wc{y3USr?bF)zHXH!kJKr_so-6v^hC`Ie#LT?jdp7ZEk_rDd+&ARUTBzxtO)ibe8cC%| ztg%1FQT_~h=PtP^ZBo_u-}GYHKE4O@&69L0zj(_iTrl!-$RfaKes9<>XFnawQU1|Q z=ih%SFwP?~q_u9XflBA;tVD^Urzc5?6FdM({vrp_vnIj~2i0LNic*?a(m#B4h{{)pI#S}%(BJ97ySk2e56SWxDQ+CR%73Z3BJ|g5P`=Bp#t7BxHv+RGjz)9|cFS=6P~(7bXX| zs*u7lz>UrB)}!P8q-E;UYbNLN?ei|8`?#}_$OmG8osahTqyaDb^IP5B7wzUw5P%tT z(ky0&0q_~)73xlGcL)-`=c8wFc*3`^&hyk1!Z-^a5EJFwh+A+$UUtzfYFG{DeL|ux zyh*T))r!V^@N=d=OGj#5>6W$Sh)awWPg)skYaKW=>zR>zsU;tDkh%KM0Jf05!8Nw% zy?4$P&?4901Xm=&|Bt^okI-H6Ol)qqG`sLXJAqeg*`OZRhh+87V|k*ho@ZYWDIwJG zh%oHJ&jF!PBBUk%pGcQn#_@KmRkRzu6*s-(9rni@rw@YGfD&Qt{d3B|tD*aRK|^+8 z7l~q}J#`uzH{AnKr|NY>c?1s$chAlbN$RDiCoFOwg?`z%d!J|;$HHsOBxp6-k@R%V zpmN{Rg8VudVC6_fneO<2M3U+0<_}Rw#}TTup}r+Q-Y#8xU)rt@wLV`< zwbJb# zY|&;d1#+ZNnk5*|=j7LxgL32{!ep1U^z=^B?vTGs_x28PmVfmyCu$&SaE)Vt5fOsY z=iw12uI)_2E|g32ZW{v|I)0>NVMa7-+O7@vc!*9@TAQ*gZnsr*ey92R`i3XK!VT4U zCiTM-UvKXQ^-`mcu!13lo5aL0q~#dskKhQ&Qs0W~^^8kxqRW1A%}71B?@hHjpQ=&>oNHB{oHFlB^K&yh)s$Bg zS|%oYQ+BtdfF4~|U$I*0fhOM%nEf|~qCvlNtVU)oYiO1a@xaeD&t>Oz`uE&(h*0Nx zpX=!RNR5JyKJ+QiC0}=}fKPpvW>^yq5NpT&_Q{NssM|JzAv~!ujg*Px1Gz)r%0Z{% zc)CHRccfls=|t*Aalt%V=4?qpRgKf@pM1Tu^FM#2WEoBUsyLPYi<%V;LI_0rkV)_X z$35-W4-Jk_2XzF~GROZC|M=~008R&({fa2IM8YJMZ|_jmk6CjK7vDC}`zcn9ikD|B zNoV66#5!j&65?wC*KBI(MU-v| zsJ4_N_?`E^G9%7m_E)tks(|nfR}J`Tu`%1t8ow5cV!0k>EZf)+>)N#5cm>5B>qB$D zeGXXhp-jA8i;II=>z%_d$FMW!XZGgM|E?dd5x*IivQ3CAcvl{ks^IDLkI5E>z3QU} zS6=qY%6djeuTR}}>4%bFzn7x<-@%E$>m7V(nLwI;Da07~@Po2Q6j2v?!M;bX68jX- zJ!!#HC0Q(;e{tm+M82|b|;pGqn&3RS{7UV&-D zQ`UDCtO8QD{fSbJ7-_xWC|fBpyq(Of>R&_mtzVV5q>ANT+8%nCuoC@Fm$a2{fM<)M zE`562{ui&x_ya8s4QK2=e^~wL;F-MSL$_(V%1ta8xe*CGK&{c(%NZEO{VK0Oi`_pV_#RlMz93po@ z`6lbl>U{G)G;;dGYOT*J1Ogug3%SmGUp+oU3C0iU%i@9wxT(Ey(>T-pwk2-jq=G2({B{`8#`2LZK;q^v8g0W`^%#-g{c5U!9z(0 z*&Fnr`&Y z_2_^DGEE6}e@2t-j1RvxaYLudXL*pFJv?5%ni<})?nwJ&R&q3-_-Mp^zloXQlmv-R zQls=pUM-S0$U>3Z9u@nNX{IFxG2nSttS(F@=3K62REM~}*h3#fB0pWKU_Zg=@zyVP z!`?_db``B5y7&GqeX_mO&w`Sy zXQ5PRdWkjHK0i^A%+CRZ2bzRPx&f^wl;=@#n>K#0xp_&xsRfX~vkQ&-;b9fA5#NSlZtD?IVyxFn`C!#-4u>9KqTK zJO8X(MdmRVBj=o}-*}Yfl2%{8+WAJewzhVE^|9MkaVb^1$HqzF?u86z+c)wiF`pf# zO~{?I^Bqn`4v3j#u~?3L;{U&Z?^VYV-?{XlFPa9jeru($M;-S8Zeze3*XJ`mYV{i7 zTMUOLSzTgMyrdRZoLmcQ1(^`BRZGkIuA}B&0>n2_q3VivV^Tw2I zRW{g*>C;{!j1QY-qAb%-uJzK%)z=t1nO0EIa}t0uyezq~t?cZ!mPKP~W;+^zn~Rw- zj5(PjlgAnxM0kELziEH_5X<0phToMdUniwQ=@PKeB+4sVEM9Skoz=&Qa@qbF&djvp z;@DCGUi`Xn^}kcY1C@?Lcs!|VWK2|9g+qTK#&5$9(wcUIWv(rEgc+^*gAukBIz_UN zdSB<<%60#P)+@R$B%n55ODV0%O-IRu_s9Jq3WbawXW?E{B84CO{m`Z&!AGQN$0;tWT6E=x36B})nue+^R-vLFp=R*-Lb)moNCcCaP+c|rg;g+Ju7V-As#DG{`rnP zV)tzGt2*iz?J{41O=`sRD16nZk6H*6Zor!g>|C&^HEU|V>)~`wxZ;Ur{mSwupVEiC zd{WYKFO8`Kk8yh?G4HKQ|9sgqR-oI%oapAjBXf-{$=saQ-?DV27Mpmpqn3qXomFIS zTB8wLm|~9=SN}63Qs>2jhJ1KM13u~9uhM^deI2~7B|?^;nsszQ;F}mkq?eDRmdC;S z1-jyDMvWvMA{z77LE9^sJ;0#T&LQT==lN^PodCi**z6nV+x+&p-jIVj7bco~7_;|M z6I+feX}}wk6plKA(F2ja87DE4;RBj#9?>6Um#N@jq1cgh{uzxU3s16IO>ZTW!^Zhb z_)4Zt{T+?@f<5$XA|oq81zx_duPM`@&1p!9@og23woV-NA6DoB1mTx!CSPe*Z-`YnaC!W}c8} zpB$I`+pG!iIM3s0*3P$~v>oB+VvpJ+O2FT+N`K-Huh8G@s&mHbGC6$q6txe5b!p(y z81g76WOt5U5x!Q~USQd^z^wFi^t#?|c4^N{X_bWWh(k0%8wY>6C{fbKKd(>&lU%s$3iGr$n0BL&2&&{CqwG6h462zuoP8V}%B# zebU7IgHrzZ^=M(dfx|a`oka&U-mr?$Hohv92!XG5Q0Pq25e@J5g3EtFkA0&C_@eO? zZmgTOtOX7`9x zx&MIh-;cv=S;O#mC_l?mwm5%xk1@ptag?of?$ zuWAYHHzCW6my1I*xvA_}q*KTWD}liDbUUMg(?FTcLf^R+CMRDY3(8bKRtUq6V&={i z43BCpMA|Me8)a*NyZr7uC}D*O5t7e74;<3BhoBE~)P)&{!dyuxeH&bK@;a0H6&Z({ zrG;VIv<1G07neIz9VQwtsS8`;_#!f5wh{wtW=s z4UV$s&6D4LKUsjjp_Gjm-MFI2F8Z(Jv4O;-zi%gQHz6aH!ed$E*RuOOz{oKrs$B}x ztx&oeo0nP^w$;NmeQJP5{wrMFFv`(z;TtfZ*$lvmvii^Pu0c2U`YX@G%J>3-qr%Zg zH!}ZciQj@Rv!c^TAP|_Xl`&_z6L{&%G+~>Uo<2W6Sqh-_9Z0DHfi3qY+{k~Gr`-To z6l+Rd`Bv$kWYTnN`+PpuYVRlK5O+hddR%%&p+!0`e}J$ZEk(-8en~zZVSXSNk%`BN5SK7K-4O2X^)Y+4%+1zl=r zP`-}0LqbNXKg@;xdlZ5067w@k7D?YaxI|c$dqi2k?^YR1oIbzIq)!g)13?I1uH&v# zSZEOQ)1@U}MYkZ40prM~9q-N>!zC`?^nqX}Qc^5A(P_O99`RF`MS(PKcKwWyNG| z<0+^*cS66iq`0^Tbr7pZvnJ5DO~_}NZy7b}&~=d`QXcn2mAGP{6fs(lYyIjM@V`3f z>A8VhDesv6Yx=2P>(Y>Sn6j^AkRGYm4ciorxpKtEUNAB=Y;x7f+$h6LQLkHqD6Nu& zc>fc?S9dfidru?;E32uojc%BNrhf)W<=Y9-f}{rnnbVE!K@~%#a2oGc?Ho3$(VMg|EB|?ln&;g*Aa)RuEaX z{A5hg#HR!D$N%2~3HZ|Tp`zH~%^lX*oc_ZpmtAg-HR!DQX5-h~Zi?_qoDeOQ2!Z{K zw6I)~nVg}aror=W=Y`@td)pf?Tm*@33W*aK5x}<5jtGXpl~vx~u~bJswkdi2XlTO4 z)|2wbRWwW!Qxg56PVX+U))F_Ja``d@J}HIMCZE%*tl%M8==KlPw~OTCO?mTEj|i}V zP;g}SzbI7b$#e0_059uGRZpiEYZ%6Kmi5<4Q1{GxZ<$OXOZ@ti3Ou=97b#XqLXe** z!jVBOj6Tte@DAN42@()c6v#5hIIa+{T&iGk6Y_sX{^X1@Htk&S&Ktg-u|(g zXDH@Rmx6}V(fq%dzBv76u#+X_+d z@Q>?`<-VWvDK5;jSJLIdV)FG5Tb2t;*|BX;|E+y`bR-UAY+A=^XFcND`}U`2mw-7xd0%-o*UFAyROca1`9*1JfUs6HO-Lb>zH zC1vwT)Yr(J+Qw5B#fJqQ% zn9dnxHeA1?9jIh5F(FDTs;xY^KsZ*KFvUA~*ZqqScb_YQ03OF4jCdBOuuEgjFpJW3e5g(s#&>#fak!8m#Q%cw9ezUFZ_>EXg?p%A2Azhmi{evQgk^%lJ zE|U*?F>GJ4Q1fnI816U-7_`6{jNcoMt@-%bKd0(;RGgLUA6Kl-kq_bFuIuz4TFMFc z{m{tFe&8Rv_)Fp-zFj6yJkv{-l$>K-aLKIlrrj)hpQ_-=9gdx|eC2YFIQh+70n3^D z&Uk3=Qb4XCA4*1U>(}PP+^X`-Df96bpD;!}ck1QQZYU|*Z>#w$g}*&MA9wq;FdhNh zYMZy_D6S=s&#G&UM4XBUcezYg_IC7U?qGBBZvSG#Ty?~{@Gbd03-%yrDNpF48W_uY ze(45INzBHBle6U=&=11}IxBG)>qaYMUQI-?VHUpwip>@5A7ADhzb8^D*y=o%H<1)I zOT6tsgLTmnjU1xc{2AfEd5Ma=%tsO-q;R>e-VQJkh($Z}e~SzqSW;m*T|f+On%xr< zZuoFMcR0Z-Ow#~+Vj9%hGVDF`QJMm7Ea(tzuZ|tKY-^FL20WO(N0rT%b|`5565Cm zzFFUhZBUf24CK6CZ~fNLFr%rTnD=0^)!&?lg@!<7HsN|SQ&gJSPyhW;wv?A%yDLMP zA(cazpYH%bfXvqvCJGsMtF)_QgL%1fEun%wX})6ad%u01D`#$Za)k9d_UQFgvm^6FE zDw5T$_2s`v4I~O=#ZB1Vsd)(mrr2OfmxLu^262>sT?kyANIXzWf`i{zzBf7tNYPTj zJ6-=1c6ebTQ`Js$z9K3-D5$!5rN@zE4=l@{jYDAzk-f zW{r)OnqU~NkB)V{&}#Z+fFjqvqz|r%k2p<~X4Yaf$;DJsR}>bAO<||rXX#j16VprN1eVY3wnb&h`p%}ei!ZKd?YbP>X!19YI8Hh4yVDBKSheNL z(e#dq;%@RbYYMO=`8~YYac&6~G(Ij@@2D0fO&oaj9~U62UlC*IiygU<5`ETFW!w~F zU~A=QIj)O7g9ng<40s1%KN-_Z_2}ngWheLwvBWNnXE2_V9t=^wFk&_aK05SWg3((O zfPW*t*3B|^r}TCIT46LYx@S$#w&s@%vCO`vp5ewf81UBk@v5@}>il?176ovkqt53a z#mPJ_J_Z*x?kh9r>n44?!joBgl+(NQx;-+n%S;2c)7#V2Ga@P+sSAUWTdj}n*4cMB zzTI|T4G~-0=E@KbdwGBHJ*QxZnt4PWwzl^q06>}Jo+tf zYc3|R4i9t0i60v>Ad6x9us+E0Fd!6J-SNLY3!8!O6*u2?_>dEP(Y*!FPXwTS6ao9b zSZqeKGYYMEHBDl^O_l^ig$}`!s&$Z1CGG-$qo;_}q3nr|=IhG6af<>!N5YlnVi#34 zv7Wrc^O3ZmV!+rv99>|TyfpWCRZ@eKqAt3 zQ|7Y&x}uMLA;Y9kLg-O5cHauRkv}L};?u~%-6%e~0nYVu4B5S?${{JOwuQ<0FEFr` z-n+V$V40P*rAgZt%>nRq&X^KzUydJN7>yOp$4(86=LK<{#IruN5c0o1o-kYie~`2M z;nt&et5AkL_2xR9?x!$&doK{@=%u`!1c-!mYjdp*Y$)637T1nNehcPXF*MpTPg1P7 zmSIica%BqmDL))1o zG*jZ&Rk)<$W^}|hEQz69v2O+1`96ea#s{AVR?`0!%DNqEg)d2nu~r(mA+Sf)<@6b! zDQOTxBm}2buV0|u?%+jy2uV&0c>ylQZ<8_u{k=>7>^yu;oE!|xWGbLtjELZTeA*#1` z@%{L6kfI%N-gpA5dEn$f^$9%J7RO;S-uCqV87A|w#2RUsv7bK~gCs`6E)QJ_em`RF z;`$7Dfi?ON%iPp+3s`Sk&+?8~d;0ojrW4ddKuKte=4SFFLgYgtN#QKzh5wg3d({zv zsTz>0lfrw>2ZMS9S1k=5#m_=X>UAX#60Ii$RdI&pU`7TooO`6`;}sZgY1Y+!6P??K zQ)>Z@`eA}!i9^!ols@MtvaNruI^mwIOpu`lxM2A%mxB_yROijD9R^&>JUNtLU!Z%G zqQ)DH>=w`>2ub<&IH110AwS(3 zprMi4@Qq$c%LHh7{mGm>JPMjz-R8g`TOWoeGA;dxj1)uGo8r(oAsc> zmj?II%6Nk+Zqct=!{--4}INv_i2Cm(z=Ny?XJTJ<{&ORD| zeq)E%j707`Bug9L>Rnm1U-#TTfAiV3LS(9g;s8i4TNpwY43yTy|9CJH5^&qNrJB01 z5MOEQ>mKbGkrZwFA*I!T>^$=a>8yFkw}9}#yy=p^rcOHxX33XuaLF{q=*q|L^fZZa z$|YtfU#?0z{)383?2utPKFAwr*_z+-Gb!t$e4sE(FmQ`j32g_V?9jxs0Grk6PB8$&GjrvJ)1gKL*#^!`c7Eg zgz&6HTP&-K4C>ZKNKYpFm?;(7#uOAb=oyjR=V}I9?bgJ4H54}luu|QJ+Q?I{I?)IC zT4Tqn00mI{iJ0g1UY9Q){006_tzbW)ujDSC&W{9BK*CxBh} zbDNts6!Fh^wqtOT%GW4bg?QZS2vikkB4C4S8D2H0N#N|LwjhMa`b=DOxSNjjsqWcT zIi`wblc1iow@JI6-i~4n$~4@Z>E7%TTq|xi63|GZ za{#Bs+xtE1bbQaGkE7Nf-?xm5Z2*E=xhUM2qG-&#!g5g7Ev^r*RJI0iBOvblc38Z< zhpBTB3ZH}=`ezufF4AHvXG#`EdvpwVwIKb4V}7#D%wpktho{Yr=MveOS7sNYgs|iz zgeCZqU0vrWR*p%ggs2}F1&(znD?xsvuj@;VX|)_9G*9#WS*5#+ji4I}D(@I8d}Tm} zS`7>-qQijz6VxEx0?eU)bNv>$C_F6xqvpPn2MHe9HUp3kRW9O4vX|#2;-Qu|2Fcq@ zAz0$K1g%Pme(ifLLs(OuDGz$a8+IyU8}$V17X5QFVNY_$L9c$8?Tj<=MA%0({M_IQ zyk%%(uFxF{po5&8Bi6j2XAIs9Dt}}{-QF0yuvbQ}`!q}d>cjp<5Bg1H%7mQYXj3}m zP>`El8&@ zBt7G}##q7mxW0cNMjekY{Ri;u>|iATRLOJLogA=z zoZNXYAj{sgmL&_QfV2Ee2VHA+#*%Zr*)fDx2H@T!bSV8de&RqJhnUi`L5#y4Y#D$; zTgIslSXleHwNKi&Iv>wJfilZsk8%xQ$v<qqy=PtE#%<>YOXEM+>MlAScM|*WI`F z#>PEPua!|2i6>XY=&G^X zwysKZ7YT_t0c(Wzu7@Fr2^KvNX?kvcnjW&K+PE&h7)c)-{4Lwv)1KdkdV#1^^ES6P z_4F9wY0!);2X!ab8flCws~wRqJR|nh_Gx=l**$`d(70>g zZ7F82V4Bb#aZ!@iTh!wICsDWxdeP}`bq6JF5olc7cD5)D z(_2=6<2+x7DP{TDxD$dhUK@_yI_*Yvpk7RB)$bTfIyFd&nH2sIIi_zWR3g8yu+ZXw z&Nin#*EG&|ML3DE+BF{ko?}Yu${SjmZ@Om0`7?7)hi*R~s_Wo}TjSN{fUQjSP{aj> zwpxgo($XyZR)TX(n1}0PlcCi`L^ydG?f(KV7(EqSSU-(0t%4gc7iNT?{J2B*o<13| z4HBhXO-NbV3#6*cJH8e_Yc`wd&}<3?C55S8j4jTMpZWH3zsWH$$Og>_UHk!l%>?8n z4v<)>K@q9b|LD+1)uL{bg~92P_-!|LL=ir`>FIzM&PMOz~ z;=m%nYg(a`dvsQ#4|5)D3{Ibhe8rvKGCJ7lk7cVa9h{?SA8=XNy6ziOO~ge5k~7X~ z5=+>66dl;*Gvm#}q;N%!BkiB`%OqJ3VI#!dFl-ZaR;beDnY5mM*C+q_Km#4PSNcS_ zT>dx&q|U*Bcfw_J__JZ-w>9Od!mo&~7&}gv?5ROQ%ms7`^2xzY44@_tPbcPu1YdmD z_F0-(m;3sWBdq=aoJt5*3K6D&Q=GO4{r?}f`le|DcquD|i zOth8)$75bdX-5pYAqdQv0uY&9$=L!+A=PIus;klUKP5e=)UnmsrKjpW_3W!6!QTbb zME5edDH0aadQdt_E;j2Li_rWld8jxOHReuimKBNhgDSMoM>5NUdudIW#{2&9rP<+w;LBN@rVJ{2Op&a|uodoKk0d=Vr{X6dT`0oxeMhP+gso>t-*Y&Zqa zh;7=~+~L?KYF7RrA`NnmuJ4Nt(yx`}#jV>#n*TY?0xOs;@8GY@4mJv5dSu}+zJ`jh zUpKdXhyZ2@#d1$G2*c=YBtpP7CH^w3>k7O-`(AQ>tH10u_{z%u=-To<)j1Zv(^eoe zLAp|yNw-KZ!hss4s;n$kbTZ}}?MFw4y5H8lYV@CJB+&Apu0+|h_MRDgj7iWZ$=4K4tbsi)G9H(Ll_KOyO{XbaZB_X6FkjK2&K^F+G zx971$0aI30#hyISGOjOmNROU$E=akSFb?8;A{7`Ty zR=A_=YQNK?K`0ngLoy`8Vktr=YxwZw`;w zkM|WO3&%5DV*@sXKa2T3Yrg(u;|_zt+K;-Zld);1DBH!YWUA{kpx%5inFd%D>0+Su z#00{{2r8E04g>OW!%xj`HKZ!sbT;is@2d-iFYJCf*!pryf&l198BTq`FOK(82_rLn zdB%gZo%{pzyOJ$>Txy9(3lH+5#lYs*Y9j2*6cwwVEY3Uq8O&Pv>xi`VAM`1{ka-h@ zXaB=p;ayOVG}}GRYia|!Uu&`D*4#pq9!K%+kh6Iv##^(N+r~vZ`D=a@%mM8q<0QhX zESiF5v^EEBwJUi3J|qDW&RTaJuh3!XCqrKSPB{;|JxbWF0>ygd&Zmh86tXLT^c5T) zyEi$Ef$O3mAA|X;nESH%Wf%AXYLa@V-DV8+LL&#=yi8)AnG%D<|1_E5%?Bk1Up-4b zx!>^O{2woRCA?X`uUj3zwf7pybA`93e;Sv}WXz%Niv_&(HI}K5JkAxIKMkyOVd1u$ zPJc9pln0u_X)0p_OqPGGF&4Nom^UfTg4gLT=L%dJZ99}^KM}R!)%wm~_Lv$N-`18N z>m#(7wKp&f^qbsX^Xc(lGnVa>3d?H=MDy7L(N(le7zo&#`c!yX`fSpUkb2qZ=LOn) zRm7wc1Cy=}plg(qk1z5#s-dWtN)*%s)p?4vy z1<0=rRfKaTk)=$Chg>4ke7FgDMZ`8d^nX@AE*Y}eg%6>NEwuKWg|NByvQjRw?G68> z6u;_-j6^i$Xk8t}Uwts%ykfnw(BHfPDrKn4E^cUoTjIF`x9I;7)kDzcTXI1CW zG0$>zbnL0=)R2+TJB{37~Z|6Mw+%qe7KE%E6t@rLGJ8djm` zM>pRV7gJn-=M>>H0FzE*kWz+_*0#1h#U?$Sx}NK};>r;x(ygw;Q>PJmvQL-Z;e_)w z?a?uU5@WC3@W%fH>a2Hr(;x4((C5R|WD+vL-2KrA2eEI3#FNf|tfHpIQUIzLtjnj(%(2RAA)f%5h9`Id)$Vac@n+P#O$2+vEq8Q^~A^=T@&c>K9uft(yYnQ z5ESJ*4i0#fY^dLbp`J-}pAeyp?Q|t0_(Zy-x}X(^I1q|!Vm*b1Y9jC z^uOb~DhFW%vC`?f0y7t3N8r|?u zApcifUArPaUK+Oc!#?pI?>V6oN+T&Szz(r%ofsW;hETHz0D+33v4#{=&t0b_&kT7? zaeayrV37O%1@PL?kU4HZW8SlYjm>M-Zldc2kIfPH}|*E;96gyH6wr zp&|J3lQ1Q{y~x)^oh4uK zZ0cl8jBbHM2pR%UPr}^*uFmD<2O(p4isWNLS$Zty1ry^iYZxw^b9FGnRbs13Ck`fJ z1x1Le0kW`lrTG#exy=1Cda6D%&w(4iMf_VjG+B?+)5|*`sQ0z{sNOP@?KjVgH=*H8 zIAi=D=_yQA32I5*6JAM{ZxKIEf{Pb5@6FN?3bMM0YWOef^yc-o?XfA6tCsq#@Njpp zJeOW!v%$(3p#=G-1qOrv%{jVx`m)=j8vw`Q=oO*iUY+PKSZR>zjc88Xw@`y-_9sZ- zc2vx=o&O=L8`rl{vtxE1BX4a$nb=dJ?XaWSU}rG9GiDS7-wJqvT9;c_-1K#R4ALGz2Or>6o({)1ZH`BED*(f9pQoNMBtXS9CfZ$!@gmafG8{Twlh?T_B<5*%u;$ zi)JIJ6mVc&`I+2vNC>Gcz~%2=6=jb9;7{f=RviRD2eT{5V?Gv}k9ovd+uLJzsYB>L zZW6hXo_}T?(n4NsT%S#1;9J67Au~v=T~>F$yo*4fM2OT;iZSk*p9Y~)Uo6$@9K?Mx zu{zna)~zhZ_o01j$x!(nKYy2C#(=E3XK7^ANdu*ELm74!akVsGJA)y`z>Yeo{2IZO zbOE0R)*hWnnf=PO(3X~5evZJ1i@J8yz)|PT4eL*s?zRO>hy177R#O>t51aL*a*xGa z#$Gu(cm22L1~r9jRce&6#D{E0H-f4A1Q-p*G!L}T+Zi2B4~ZB?BO#u}C~_`HZQDe| zT2S5bOozYCtqfzW+~TA`m-T$q0gFpQe^ZP&aPOIW25RT_={;M;LE+^2Wd49%_g(bj zycdqe6BY{VJ`(;iI`a0{a?Bl6kqM5sDEOsDD^K2)he0oZYS~ zSaqg^tmW16|L)&(`L`~6U-w&+_aDbLp=H>`WyyA5K0#9bpv;Xlg-*XstCmil*y{bm zEAhyqt7I;V9^Xsd4Hj#)VKMoYSMLTJd^|ubHPAwZpTaC_K=>iJy?P>YOYz&hNp=d1GOTXPo{1bK!3^dt%OYSo)Q152pk##WTty~Tp6+-&8W z?Iuv<6AsZ{?$F+#GW973+Z^b5TcxesO1u1ftfosGD{hJ$l<5oMDgMa(ry2_ge7nIV zXs;pe&sq18$asNM>xFiMmt_twU(ksgBgF;>-WrJ3C%qo@K(fe|t=5MP6O69CI0_`Z z8z{K1^%n6}V7ap)Q|68`NUs|V)DUl07rkz^W@@PhC|5nYAF!e$Yu;__E$ zaBQcXt_>LE25#EjR=i;~ z{l^s}Au#k=>*3>5{CVd{2w1`PDpJ*>65hb>=h=ho|D{Vs_#@@?6*osiw2GP|sAkREaQ zGFpT@5TWxGRUJ;CPG%EpG&vj~#wp8_-oNdVoMSnWQ1DDLz7fjQI`FmHC#en%6i%4V zf!^V>04%SP8%MlkNCE_~%ex_%xA*}~tq>;>BXE|HjO#Vx`k$1OS5sh@d`i@RT!28& zr!VuLG82JH4?a5A{+JlfECm3r+V8y=CAmXTHF`mo;KeC#b3?A;xUznbE8$lG zvRCbMBr~o4ol_V*NNj$vI)Cq8jfbEByxt)%Z1uW5+Q!FS4Gpo%2ER!{6Y+PnOz3P% z$B5KrEdyLPs=5o^z#LC{M_#7}*D~nsSe@rZN-#*!UNWIwZ8<9;mai=`2;t5KRsJ{R zB9n~XimIQ5S2v2AH36f2$0~w3L}I6g{Cf`?sE&)@wf}JI{2W}zEMR4jp8mbJH_$>0 zZ^euMi8vnj)A|)R86o466i$~7>$+Geh;#CC;8)}&V+AsBvB^?E_EHyV!pBj62D9pw zD@HEKT-+YM^L_&i+sI8X@9zF8wZv7t*YC)_pGVm9Q9EAdZV!qGzK6CA38o&xl3XhM;#zdw5FXW6?xpQs!jeLJ zb%Fn04vp-wtEyOCFMSmKf=3){V#kARjAqRD%C%@&eQxsxN1xcCUFIiJ%>U7(l6J*`*EAyhihx*8CZ#SQ-`D17qmBN4yuO!3h`bHS^L zl9~ZmP^;hNr^+s$K`o_zs1KX8bULAuWO^TK6M4YJxtX8DHL?Zv-H1dW*TmS^8?{3_t4A-=w8=RP2ZI=YxcI}9>fGAR z@}+B0p{JlE1LFZ_r7=h2;H4hQddy9}MrQjZ^L6wZFfExP(&S=}$T zH71)hxfk|@h~4bnv(~=#$nTq`MxN%?r?^vhs9Hs|_wgStc%^;pN)WTW_Pb9um0l(Zk$8&3Hu9Nk%ZpJrLM+3Q z*)GcEu)J*LuG*a1xzP@%J129#R!qL99FG~kZCZpc{W7dgtJ18ARnEx6m6mT@rP5wg zWhd$0>9A~aR%K`xn`?Xf<9{FO)nKsVECr_ICZ#$if>KjcH4TOX_cN^^Im59KxJFA( zw_JvVAqtt?&d#W#9*^n<4R7o|=9_1~D>S%hrxcUYr;r-mjZ-9dx7^p*^LO4;a2qju z_t!^$@jq}_W1IKe`)IKuBYBMLqWXm|=#;)C($LN6tm&rHF-|n?XHSV&nj0e>xlKVu zg<-cp#}Bv2(;mCWdA-fYef!0F*6em`lkWN_g~?<}PM%5W+aHuGb5N9$o4mJoVBi*A zSL|K;89UN~44qN$l>=0b$@IXDr;l8xrn(APuuU{NIMuqK~Ci=hGDInw}RHR;7HbOmj zSlE79=8bF2Zl&%hS-=8axTc zv=MibywAFg;YaBAlvYb7lh8_VmW!Gu-aCG{;0!(!lF+-VoRT4&Twj`x=eKP2_Wk4B z`G|W@kWy~eRE4*Y(z$G84aP*2esi)Ai{k+{Yu?`8F105q!yS#U;AZ%Obk`==hFUUY zm48pz&i_h)mY5h3660G6PmU9Jf?u>Aw9ZZTU*G)y_hwFk8iYzM_UGGocblDE1UK8h z%jyv_TBT*c3!+8vt-ZKi-^$5*Bk@4*4Hkc#8}A**;baqG0>?}Waod#c4k^Q@wjK9e z+$~agYra`Zv|SF;w#^TUqR(|Gz?*ls>zQ>&ogur(x9sH=~lm`+aU`?j~YvSeR7AP&(My5ez;>!3_=!m4lBdx;)qU2*> z%lCW!p=vJPyYBTWi>rEidM{>M>Y5{hQ*0E4I2&8WJ;UZo+F<6i0bPTunM^28GH*!a zo!GdzoyjG+Bz2|1kMMes)%7@%RG~fg)0*%*#1TC>-bS{cR;gI+$8#M{W4HGHH{|cS zS?3H<-ZuhNxOfX<){?hu9@5hFqU>V~n~JYi>G}3IB|^khS4G$EzIQO&<8mtjIKM7C zEmVnvps4@)dd0pK;zuMiU{pw^fkFwt8%1FGftxa zgAWmnHj3{#NFL3dg*7@grK9ng(4Wcol)zy8+wc?Yj7R9Y?9cSfFAY6DQ~TENE(vj+ za18B{d2ZAl3cR;#-*xrMa`D;@;yCr)CnU$Yx$5ZPep5bzIL_64nEA$ZKt8_X(F`&{}~@TQ7Y8czAlctgb@E7u?2I)}J-t zeS05ey*YKbi_zA$!N7o*EVMZm!5CJ?hYb8Xw;d>CWZJh%Rh#eBd)^3qErYvc346*; z5;gun@$LdT;#N2~+tx(7#%M<{#_$nxLf#=QU?%{y`wpIC-Rt~Wjw11uPCNxXLA5q>ftHH*$m7e^=m0$3m2;$vf{1$TaIV)nMZ&?f&?d-;N)VNq*aHOiMUx%1GS zk`lSEku~_P9w*Z9Zu2e)@|H}9LZKzqBp?l>e;D~{$;k155<3GE> zCW46tkwexiViw_`OF#TolqOu=d+0zsLqFd5vi4(w!VHtn%Na>e)ttX>f{7 z=LyebT`9jmy#7>n4&}MYU+@HewDzXX7j)+T42gVrc(WX5{P82UW<=6ojDrKzPICBb zsq)I2xjdf#U?WTU$TG_sX``$;C@rpCk ztNH|HdM3O*B^g|acWOAPNt#pN`Xv^gU3)!g6nMzCMrXD@b3?9`XgHrp?vrSxyJF^# zjQPZsO=&(+QSH|bNLlN&z3JW0r#TToG-f4w@^5w-X<6&YH?8X6_&hqZJv(yQn+#&- zap2hStOENJS+Yb-?A)#6NA!+&4IcYq`gi`Jm(^ipA+JBgi!ciRI4W5U>wR+9?&)xE z{}pz=+B3t)#VS!vv{jtz!!FZtD{Qx+I@=yxZQPpQMRH!h- zl)QtOKU6q3K5xwF`Y5nX^rVOeEdxm$8R#mOe zZ@5x9@|_mGNoY5EOU*D>06_)%A{0IH{92P!U&FIU=iTXjsQlDFI?whHk_%(}zV}AyA7& z)n^QO>B+yR{MNZiHuJzYBaAJ_d6!Sj2JWcNfz~+>uKB(zC8o9}H(bb_eqBy9Fju!L zUtPSOB~zVaV}IM$a2TK;x&3->&s1I>#a+vCrRi0;t}7^X1OTy_61u#4vwRYQ675^n z=BLUh&s>9Z$jvkxsuhhq@HCIm>0g(tSOWGBucld3R??>U-)DPkHnrafP{i*w+Tn4#SP| z0X;KsirYq-$FRBZndK`DC$4zaZ_=_l2{-cK;ixubav%cfDbM!*?3xhI-GR z@`Y`GoP(iU>E1H_|BtITkB55y;>WvE5y?)-E)-cJBU?m5h^}OvBvhD;CEK7Pd-g^l zvX`=C--WD`Y+bT7jWyYq82k6Ub?@i<{r&vYeRRXj`#ta1Ip=wvOVQ}~-O8oxVLN7! z#Xrj!>Rx1E2#vi3=DhBu%tZsvb;K=B0h|;vM-c{M#+n{1A6EZ<=XfgcUoaC;1V>Sq zE1ym~p*~?h=Z}1p^5tPeA`2fm{XZogCUW(^@tIP@#l{qP{ zhZ-sF!?CXY{#}B!6QI&^vzYSS?QwwXdcQ=vnHTpL$liB%m36PfD9fe!lF_DgynSVU zp04h}(!4?#Q?4wu4Q>{|$pI$2&C7ANSe39eu%49&+r4~L^J=fFiwiu^2F&WkN#eOB z=AJ-io&AQmr2M}p(9-IvdZ)$GIIXM~Mq{jYg-rhG`M%(zs;3gp*;Qh&z_V;dkn zuov^Vo-a7Kd|PCg^WR^7n@~`^WBD*|I8IHlcHGjG>n4Xq7eM`hU+97@wDVd zXe^ei&IBBIB#tzwQQ?uhPjF@rtjwF<`08*L95tZVVvb;tCkgN;Gae5*sO0`7cCcsY z;^Sb}bqez&2+l4Q*UuQ9j0$5iA5jzVzBn?Pf%x!cphyB#!EjK(5P&U~6e!BPbArer zk_k4L?wk|JKj-6-BJxq-zl2aAM<={8ZIuA@*2iJF7B|ivdxS44_=?CgDQ!{rg{QcH z#SNjyPA;dl80AJHe2-A@aefuN3gvh@a6tMd#(9YbLunHp{c2$O8}3qk?x}AXiUJ-p>FhsQ}YM( zv1&?wC+d%0GhnV7iGXRo`rK9~QZw`U=slBF6cy>Cr2@;8I&5|3sf5sL=dbYsov730 z`=u2_EPn?$#nhh)?NDi~pa@0`YTCi4`3`>v;DpjD=>c|0>iNvViqVWc;#crjFw|q|sqpUQtXASsTXE3# z&OSHfvPa&*A`R!CO&Uz%C>51{(|$K4xS3KR$yiM$7*-0ZA&D1;TLQu){o6=3LSP*S z-L?=80VIY>{kE5a7V0SgFlcY!I}+^Q^tMG)a)s~rHwqRcS7*u-jJ)BAY0gdkRmmMl zg3!0xBQ!4i-dXU&Xd7V;SxZy@>IUW}3&gs0rJJuoM`ZoE5EcEAOCE@;t8>@bt@3FqUPSRb<@@ zw7OV%sFi(XvLi7*lnEK|>vPTbt9HNaLfgX!$2>~MOVeRpW?@0fPDCyU-^YIm1aNc9 za}&1PYNUq!dR86>&iC_j`49>BYjzTFnxaD4V~;hH)G^hqAslsW6{WL=2ft&D72RDv zcZY-Z0+*(~bwEF^6TuFZ41ch(2@{jVr#&s7c2&n==G~!L1j0~e?fdl9Qd;7BR4N;0 zf<9jo*xO3T^LW*wUyJ;6!tCH39(YCnALtvVP9*$D`z@BsCOZLXQs<4X<1Cv_QQ@wZSSnvs119J~G3?L~d5ei{-RLYcRj35=7YTuw4YPP+PYw1^0 zHVsvEnBI{ai_GGu&#FLIQSPc*c?cj~fa<{!S!M#Q{n=IrNqsQETcFWnM;O1?{GGJu z(3S`}y>L>#aU22)hZvzp#wQc?M-EMvH@W-11eDs~@ko&7ADuQ(9{nYRU;^;#%V|WB zn?-*5?`8@5W|&DCqYVMek*|+ZiD~>=?$`{;Se=g>q_~*rc$DPm)26;HRe0b$L{i*- zx)&D=%>@VRQ%wlaZ1_aP2ZTpqR7V#;4nMY7+;=bGp+(CKPa&aT0lYpv+Ky6upyhF&;|P3Q^}@-X zY4=SY#1711i|Z=#W-=Jq){T2jIjwtS91{XnK>4G4-IZH}0|@{(jE1UluZj-lIsHf&^(%z495p1#2)+ z@jiEncNm(~1(aCmZ7$8TdgTT}=rJTBr3X5P%k%x^vSR43g zlm8u5!Ejk)`U{_nYcYQRbcz^_kwLjj%M@Be)1k~3sYULx`YNFX5p0w~1nJz8)nshl zSe9_WMd>SQOf6Cm2vG~InlHpJ38Y4|HM3h^jS=kWpdrx&n0Z{e)*~~)Q!G~J|IX~L zpg$z?$tOSKNm2BzajntLeru1+DsG9}>sZqgIj&%zgjp2e zK{*`!pxIML$qJz<9H650b^OD^0&wJ$qvVUegm|gJ(vrS*>eTsekDotSIIL+kwHx4> zHEf4^E&{lD+j$!0*HQ7uXDTDcUJTX8Fo~^i+fW5a1+oPS;gT@(p6!gP)N+(+r!IyV zfN_?+JCVQJ{ewbe=l)ucJ#P$M-7e1i&C`W8yt4GL`32bVGYtVMqO<@w@6EnQY(pV>82zk&LCCV2+MgA{ z*w2Rt!bTk&3;09F$``yX2~)ps>B&tq6M`hRxXy?HZ4Dkspum1nwx9E@%br@q>PzfO zH%u8bYnb5M{?QGMO)nDC&s7ehp+Ug=>LkptvGd7#9zI(~|0GSM9H=%Ouf$9GUWoe(1<~Hk_0-vMD0L+~ zPZOy=w%>v!{}0f4B%!CT9}>*QHez{d6(_PLNjt0`43(Pn`lfxw?*#8Y`8w{FXu0C& zHX#V$Ufqnv35|I4FSNCVlo>S8phS9QU=5}jgQ@0YC(+O!d8(iSA@rws?U2I(dXr?@ zh1xn49F?uQauIByu_>)yHIv8gYc@`OfioVSVwd+nK7-~Jd{wZ=;~&w3p^2AgsjFWi zbBokNuD~oY9c8cDnacE%%;Ah)m-qV}uEg*kl{>&BSS&U*4uJhJ6o>VAxG^TAzU8-b z;v3)?z`R_6EFvMxnEh}>zZgy(QlI+W{;TH}77Rcl>6O8@yf%S1rN~9s`~qyGk?)F) zjYY&{94$)_plZL-TlRps$u0I7wABwE-Y_x(kZw^cfvmlkjfgfqA$Gh!nu4JloS>M6 zO=oNXF=$vhO_?c1_~-s_B}xT8wg0#P|10dpeUQ~hI)Gibc_}{8S?c(|%I@y$40)4h z_B&Rs7;uS!HO!7W`m~tzI3~9h!#a+Q?ATlEZ+BBRtfwNJ73B0Bt0-yrPOPn^TGBg6MQs2{7=B z5Qt;nXiL$|6b5rAJ00abIRe~tP%r#|#RpIxxLS-une>3Z2NFf3r^?9zTL1XiBp{&b zu#AW801)zheD)g(MKkS+2H47<*NRc>ggjW-TP!T?&ckXuF^e>?{2U;8C<~yZf_DTy zYB9i9wKZ8=8qg2oFril6VS;Tbc;Gp^C5jsBxWd6I_BF2! zFp_%I-w^}2*PUY@XDrble^%0IQ7%@RFoOLz=x*#K7Z(;Gzo~X1&_T_x%7*War+t8@GCu020 zh^nd0A)s!>|H+Oou~eL4>E2|~q87!n!v^H+?pmB6g9%UvqWq|%?|J^R_u2Yidm&A2 zGx|dyw62`*+}ztVQc_l~ESZoV5yZinu(?XzUj<3n*Ns@@nbH%PxpZMeMqcpS+X8RD z9f{9pl>kjC_c=f|R#Z~j;HLQ4Ic|r$c7UXypg>cdyfJq^yr*n__`s7Vd**-biV~Q_ z|N4>gM391PmukAzbkp8b>qT&&Rn#$kESHN8E&r(U33YJ8m!w7M&!JbRPJ!hx*DDip zxrLC@y7Kt?P-#cutp2uNkl#`Frr7=@ZP?e9WB`+~nVtWB!r_%%s&OQpYfjo!4A|sgGn##R}T?%G7;3E=Zx3w$NWXCpJ?4mLxsm!Kq87K&N_zT+a5M zS-58*%8#Rd!DY&}?x5x7D<0k4mh9lW22~xA5=}^eRLn9q%dmy;hS5h#HNh^lk`i^Y3MRAndZK?oZ%HIi>YA&x?8W-RSn2OIxtYQVT z8L7*qStobsC~v>SRG*%me;!RW`oa6|@c1a3=?p4jey7>oY#pakCO1~xOl4lVdYxa2joxqdi1lxnttJ7 zkLk+y5-gWzNOWgY>{I$&*&9zU#b${f(TR{P>$_pplmaW&Lo`S3Y}o)o0qcGuq+e`g z{53>Te6W*|(Te%%rmJph|6R^HcY?)d9p@5w?$V{Pz(_#C1{+BqQ!X21#Kn~0KI46{ zezFw+z-&yHmw=nZyu&oBFh<{%>hY?@bqKrQqjMJ+)i66cLog$<| zzMxDsyxFwzSusHMN<6%Lv0jz7;SDmoW8 zLzIa~7h6908=fI%4c*?wp0CUFF1xYup^(m|q_k7C>qpw_92gkDl#RJ2{v$juH30aU zx%qbKbm`T!i@QeQV`NBK{T}ooNqpl_wwVcDSXdY^fR-lg=b=j*fnM@v?Rn_j-%U+T zoh8;=a6%a{Ll_{Be6rsN{2lP1%9wp>PykXKyAyhV#45b%R@nh4Pbf$yh9km}^GUH2 zh#VPyYu$q}fVjYKx3I8kDTP2TFb7+@3%f#NIZ+_CcBGK~l)SG=t|$n1uj|A>&_eGz zi!d01su*LJ2|z+D8#>nb(X1Fv&BIXRxnf%}!KOcSU{{og8@$1MsGaeVF>T{V6`9*A zWBwFWX!7r03pX7|?v?Zr01yx*Ly@aI#jSNoU0Za&6!=9vg3~DrYJhUX`DR{wUnxKU zpo#$k42ik98_bHk!DY9RL8;?@$tG;#yV%DP1FbxEdYD?4QoeD6S`uV7-rfok>3v>( zUjtH}BeU`bdUu&kFy9^U2R|I{{mdZ5?V2DIY&VOPq@-%dpf9ud^gQ{ZNAjO9!MEBCj285aR@1B8c^@8T4Qa1ych)SN`aC~lHAC$3?#|Z5-7zqqe;DA-dvI$B zoJ=b#H@Ap;-`!5O5a753PPVE2UgzG13dBKhFDyX%<9+b{DjVtt)ptwH$63|-@V?D5 z-LwVJglueVfL{OruAmLsZqYYR+NJ~k#8!XZZpl3kWzi>ojapwE2Hakitbxakrr&VG z(9@=rt=9*B^cUf-Ny5;>ZAwwiAIk6ED6$i9{OEyQx4Nl`< zRne#llWf9P!+F5-tmS=)2NgSo9)DTgp!CT55|owvRRiXV=~L&X#BhD4V%MLF>h=!E zr!Je;o{JDTe<$E0`%1@X01PHiMYUoknj&h?f-)X>2Vk;hnIJw=b?`Hu?}y`k!e~H} z>)33g!-*_N3qkOmr=p#(GmuU5XSwJg3c0PZuDzxZN zlI#dJ5Dyt=^HOROl134zXCGWi6A71+U=fBAUAe(6#>VW&m4scKy0N#JyEhHV^||FP5t1{w|!MU6+j>;|1on z3>O7jaHL1ZjkB}M@h^Y!F39v>?~nX-sP` z)94iH5!aO@s8_JxFc0_!-WeEyHemU}cOv9!!B%6Yc0v9*>OLTU?j8npIj7NM0r6L^ zL0>cw)A{)MKnxMm;2h18lus~I^K|05RFk2n2u=&m_ey$UWW~h(br;I zxdm*+fHVR=sc2V=meiLl!U+Dczkg(2zuhvo6nv%f86!h{{5IWvodrS57z`}%ZY2G< zv+}ytVZ#tuXUz-!ZqF7EX%t4^DM!jdMpY}C_TU5xx{DPGhl{Lk+f4h@B-T!_;{|j<`W9X!^c!63e*PtsYp>f zwa9Y^NID^A&s8AImF5|AJS}$BcpFjgV-o@ao%!j={@XLz#s8)+`m9S#B0W_|>luXm zdy_C|Xm0_#cjjel>HrBYf(L+hNMz-t3J|Frpl>L;S%!*UB;AIN256GNhYfvF_LXV= z6LQ}u{QqxL6Ly_uT|LY$uAfO+ zCpaQ_l?w%?0jm6?ma`ehR%Ve`3FD2H9J4TAY;Y@$o}7EBIqY$uY#O~4 zhDDb_o4qM3l@4dH9kQ6%l=DJLt{P^K@U%KqPV<;nm_fIUxxiEVC4A8aiF2;oZ7 zeItG_3bE}G=2s2`&q`QQ?2g|$VV!|etyY6X5N05|Ab~4a)Rx2#tSdtegwhq~eCS`A z<-dkI@I-}m*k0-ks~^7Ds+^b=qM(NLhrkR3o}c2DYkQR<_@w7YfV+sT$v*Y48kOo{ zK-87PXf&p1-{Ip@H0yDx6t~myQg-iAy24B$rI6$<4}V7v2VT}D*BMli(1I*36IJhU z;`M;T25>78_`njT+nDP;!V8%I%?4B*T)0yjr!%Bu47U{cP-7nfbJczeunisSBpk6x zo0AS&BF4xqYj~u7J7Y3ZkEnFv#V!N?VRrr4v%byc<-&!noSdJYUal(7(f|i8b%e;x3;VR0fCECZe=f;K zHuwk|^6#|`-L;(}A{M6%di6Bdm^D0;d5-bay`DB0|)W`f%xLM6mV1h8JS0v?wSamBv2xvfc$mAq9OKN3(12tawD~y$|P@OAzGvHSG2lW7mOd=C-e2B5e;vml( zKGcw24&()Ik2hQ_r-9%Np%Y-%1ckn9Yz(3WOz`4}{^6_zSVjH8S>OeDCZEZ)1pT7# z_D}c$cDdkEXq`M&EpG-iG!4q2Nd1;wDDki^1CQ5^Q3zK?Mdat_13v|de`Rg$S;F$~ zQ9#P!y>EgmFW~VyDs(4=Un`h_=g-E9-9{5Ha{oO3p9`^gz6+v##ftjAD3|nQ-3vXI zUO)Owx|torQLK2`#J2e-nGO!7oKZc1P z0{n=TV1fg+5T5d!)1tg~DbC8Q5c0zhf?Gg!`^|n?zh5rpi?Sx!3tP#@>x%l8RXn?+tGhvoe-s(t&Vb8{6Tja6zP5YTjCW0~#8`xR6zd7~e?4xkT}b=|P9mxQtkbLlVQ( zQD~>I65s)Je2c=Q0s$80;mWp!2sn;(Y<09Q?#20oH>i06BsA z%mO3BnBI!FwW$MRfB+}-C(@XJ09A<)+`Egn{-@V@^mB&kvz-pPu$1I`mad+B&{8X=OtwyWBeR_SC_#id*dcnS0rTv~rx zz{Q20(mAl!0?rF7sP_{)4j*sv&n$uciURe$-0XX!MXK*|LX)-5@$DA&FEyCsZH9Bz z?MK#?co;Vq7cX`u-Xl9`ZxnWZ*j?+9d4A|t?r%xjzCk34&_9EdXYn+8?SkbCLSZ=2 zd}1wgA>hK9qTNB%;8NvN7yx&C_0@3(E_OQnqrLbEub{<^%sAjWa=L3lf)jXk!$4Cv z>sBqf4%5#J({ADFx4?_7lp;kFGP=@cU)ouKMrgC&9f;~x=8bJIHEEIYO>L62Lvwf) z4QQ$1-B(q^O0eo=o%|VN`r6l5dm&_LAI(SjYo(U?3_vJ+MEoCna(e>|H5W<#?@txN z43zsD_UT_bJAIDPTEgnw!vLfNR_x@!MQS#Yd?U*WJ5bdN=mWOAw8(uK%8&o&C)2 zQj8)EGOknbfiOYC00{h$cf7pJ*ratgTngF<^S$2wp-a;hs$#~{8U~O%^_aXm-HYUm zP0U;JgM5E;VQ+V#GS6=t;dTEAs{eP)f20yyvgWt9?zeH%g&*zI%QLals(r(?i@CBJasAI*rJ9a~(| zss()}hz`_2sQ^=Y$0+5={)P;MP!9G@)01ED7X6@A0l5U1yRWZuqWHvJhwojsxsF4u zB{o#yQqbUt>y7^cH+@tD=*4HQkjg<4W&?B8Br9mAB$pgSgEW9>%@6Ayy7dnkC8Y~n zP@D5&Ee9JVw}0pRS(Nqx_2&`#@PAa~?U%4Rxf7j!FJZ^GQ{MtuZocf>-GBqxOt3dV z)-$l_RxWM`mVk?RNv{l`VPQNtXOWb%M^#S*0x&V@`GqDFNOD$jT*}IQUF@-fZScJa zWtBwY14+!(e5R{TZ}H3p%-;u9?w8<}`^$b*OZo zc*(%f0y_$Q2$}^~tqBLwR6+jCzwtKvS7sWB&UQN64=+$QO5(_ikI^nO6P0-zW%G#9 zAIDjVty)dQWqZ5fzk~lrrz==3fXF}5k@^)9nQr-uHw{=GJW41sD;+u^%LK2L@kvH^ zn?e3@pwlpsXl4%tl$9jo>|y=f5>qf-NE3k^ha!Da%UC9;?!kiR;n|l!6OjJS`*cA1 zB3GP@ZdlsQFZjMe5RVP;t=*yg31-CXhphoh z6k@;(oZzmRrZyQ}1W-Mb`4v(zlnd#D_Z!JLLquOv{8<^H=QO{_n^_z)TPPh8kB{p! zT^AK{;j#TrBua$o!=pu(Wheft?IODsJD%A(ozW@6)6lfAa^imV7`@U8g&=%79!Gk< z%F?p$h-?Lk!Y*)>mhc>r=}%7}Ln0swU&U~RXRur?S@%4=k9pK{{@jqwKgJYYf=|DU zZlNi%c?7&NF`TpPz7!hcNA=hVVj`oZz+_t9>}C80klKw{BIbX;%Q@{^Ki!-ti5kf` z#_9JsetY7FF;zXZ$fa>&W2{~vH+vpkHh76wa0>;5LT8y$L0XEG)1msR6zLZxV-_t;UCz8w{$mz-{C=z*cJ&X5l=3j1S>A86tuJO zcehuwM<#@Yx$+U6EvXuewZ(KESVIr=$d6M|5vkyCsd`&a8I+}iU8#mat8<*#^|p9E zdQc2-9^C+dVdi(j)}8W&mG5W?1eMX#dI6%W{C;pWFJ0sR>mc8BV+->#5)f{gKN2gl z0exzBzn}~Oo+wu^g}8Bs4ivVGvcMl0c7BS6MtZ;j+8*F;4fu+47J}bhet%(6lsgw= zbP20&{~u*2$Yj4$$Zknf-aeshP1}htJZGj1)=@2y^yb8BHm5MA;r6GtthFMcqp0r= z=K+`}j8aas?gJej0PKCn%+o6`2vRb}p&|%{=D9bPPcjR``>a#^51AwPa?Qz!>X21% zs72u)AKQwY&s-_ySYg z3d6k*VacFV*aE>Be`qovTzKJO1_mCM`?*S7bn}DHDbGY$Clzpk9U@ue5;Yo>IYaFZ zu#LIPKcWWd3xG^ypE?oP9(CIDKP~{w09xeWD=~DW6&*yTwtnn+x*B4<4(&Lk9%a2n zy0nC>;RKz~&v`RsxQ3+I;49(4zVPrU=xevpQ&wB^jL#C~vH#LU%^;32g`a@)E-2Yx znI*{2C}0n+b&cr-lE5_AybW8K z^B_f8_OuhMSs;lnhfg#3sJqrTrCDkU&>)dTEBX@H*zC|zx@pdIVgc!51cd7{IyXqT z^cnbX!!pgcUbahQ0#zEEQj&We*Pe=m3SNF8ez4dy*Ov1#eB)x~z5BGu7XyJC0euX9|YiX^UJ4e=9^+*~-q{Sp|cS7NB6venloBi04l4G00wLI-S2 zDmgDhikNwOVRcPS<`h~JVCElQY#bp}3$jT{WrF;L7xvLLc7aUi!?@hLoJ|Ovn|$zS zaSvE3t3I7u?iI%LD!xYAZFn$ehe=`V8}uH*2zXz8&ijP&v^ZceUR1zTEgEnjJILCUSkA{GmCz!XcQP$1turD)x=>CSB;pdim49`YB7Q)csGj{zx%mDxE>6cLu0v? zW`ZSQQ@HqYa&>q`t1uE_5+`KU`x5ELJuSo(ITEa&Bf4%tG~_q2Q^ zabZK9Z*gXR{%nM`C$BPXql|9fAn^EU91^miqxQU|!l`6qK45SG z=|X#4K~Z@;$9Tu zKB;uY`vl$mdb}RCw<<^aO{?nDret@Kp6FE;HR12SU{O`lhp1Ujs7S>}qHtI)VC911 z8-4+-SdWR?kpzJ80-rWj?Mb7>pI}E~M-bGyqoOp{lp{tcFB8GD9CY>blaPuLw|~-` zE2fjl3=avo9|2mdUEFuJvE^BDNgwQ5@yUy0OI#v{#tXqiC?Fqv3Jw+n3}khsw^$@} z!a*KZs|j{G0MA02gA>XrJoxTImzIrk)7)?=z=<5q^cw>t;JRm^qEDs)`BPL6DsFHr zAfG_Ofc*w(EKwOYEa{uIL`<0}lx`M{?q!1)CHP2}dkKd@zoVC&1VTETGiVA8@0XZj zvC?6ukjGIvd;wV>fWSiza3$Yvw^xcyy{3dspP|y>R4}izbX}F!;{`1=nW|bO^nHo8 zsC;b{x;*j=m{I7tAAPoZ>}25M>o8PgGD}>;-rS%uGVVW4R`719wG|*8I&yUcqdXWeng#15IB{ z&5T&+F02!tv1KQkj{utz+Sfb4@w1%0Q_2+x-SciHC1nG+onR>|UfkhQt+hvS(e-Gv zR=@ZMKkpDSDu}~4ib5g7(t8fZZ4~9?bl8r$RWGu5DmGX-r$D^`KjKG&Jre7`vf^Td z@t6X#EYHNl8H6p0S!ZA`v2$mudYpbK=mLec)xT`R@`mjAW_1a3wX z!PjUE+u4YCL&(~NztTLR4es?pwWm@|vdj{);M}S@+U-J=-K7KL3Py%D7!>vO^gK$F zd;qqRjj$%JFDJk`7z1*24ZZH$xf+p;U7vfNg)!;L4NyFV(}|Hm-sd~J3z&X5J2#XF zK?~j{JyMPWe`7;LQ|eZX5E+yd6fR*QT47DYz!e5rXXo4Dut)&OV1==qm-3SJnhjh7 za?^j3wvQ>3KjmY#tBqLYo%-$+*xFSu)072u=^!dw0ck>QI`OZ%;b5_`L-lHvJGW6z z)mu?~I6kvJe6TTD@N&}K@^3rL!w(5Xk;Bw0nG28Huau!#;O%KXIA-aIr|=ce#}GW1 zpP%7{U%JiV^kcu3z4#LrLqr#X)T-kUWPt^VxwvrbO6%3H=y zszR{}Xx$-FB8&4uH-1wk!WwXEcq#Mq5wH#f;6W(#Gajhck)QFyH{<-8r+Z8Zht&f* zs}wukt4{h@BvF;2unX;QKK)?xpVEZuao|9zf{KbT97n(QcRjw$gc*K7HhcrABA}D9 zcQi6;loa!4(J-*+-(KZfI!d2yhQQWhW#%H8gQXKnhG5xli_#s=bc0v8IPtINfx5Al2B1Ja!? z@GJE~0kn#+gxK^S-hY8Q*sBIb;vO z4)<~)tkV$;IS|Tn7r2a+;N`kHdvqg=F+-5{B$G;g4R6zPCob9SJ&@o$>?A2QMBPAx z^aYPuTcZ1c{%8Ys+D8f6f7M%REklVJHGpa%QaTV6 zU%K_&Q2XtU?}A&#MfKIiMc%M=TntBxJrIxe#UsYRV^Oh}zS@2Wk_V6t+~3;Zh+^~{ zk<<3d%&mLN+sDL4G{QOa8Is{ZW9PB&KT>q|o}Q=7h{r*>1ybN^+Qu%Kz4#i184Rag zU!a9xy-A_ssgWIU=%3efXi5L%Nv4}`DPb^lE+qa|I`*j|-`_Gc^WghDqg&AjXgWHX zg;CmxxRuq_42is}y~T7qbm^Z+1>=42KMa^Zpq6?SJ0&C}RIZkxBH$2u6%iM)wKivl zw;{hbXgo5@f9we_K{~MWh=^YCdWMh0qiQAwhoIZoQ80`Vu6f?;+E~OKpsx-@91jmC zxyu)(0Zt=GI~@M!&Gb2`?NhqfzlUtyO2`7)Qc4Bet?J<5U}Z@RyAVHoEswy*qZte4 zvAWl{R4b~L0%V(^-0@O@Mfu5y*dHJ)rfn<~``}y`+%E%eJ`~J1@aEZh!&QmAXS64w|1AO@8nVbS}7Ild&$~+Ez&=X!TzKIxfgP5}5 z?`bQF=SCFaZasn_<2SdsUV9;JW7PCyD!fdv%9Ifgr8x6xt!xZ+SoIpHu@4))d52}Z zHG}~iE#`giu_ll#UzJlyMXB!i$v}Sdu)}#kZ*EV4W&fP7q$D4b7F?8Bw$E(Rih;v22c=4IWEJM-2n41Yz>uHuVF#uiz}ST3^wHaY zyo*54K|IG_RkC%BQbxAI)%$sAG|&LKdi=zD#4gX|IhR+fg4z~T-HpqwEHbhT3|vb2 zQx^s_74B7kW9Yjy<60zeH+yJi=3SLl5B4FsYw((N5G6B1vEuX=x7}9EnH5FrOnTT6 zpPNzjc$6&DFwmoO;fP+Z>-|#o%ISf)@#EgFEN7Ui%%jT&z*Ds{@71w5^>OhLNugh~ z@ChwH*m!AX^po;$mS@%_sCpmD4QqqP--6copR|5TSIP2AIr-$bL&!T$JqqwtZVGu& zTxzaJHYK)qtbC3btbLoK&GY;R`)1dZyT2mk%`Vtw4|RM0^(;$yT#%nXEi#DnatOTR zU|e?RWI+Z4rE2mNoZNR^g6n3A6qQ?DbmWYFob*w2074%8y;jT*hKjSgQa5W)v=}HH zOnn-X#cA3d%mRVa-!8Yxg$=-rC8z}y1%L|sRAwhnT)kK}So+V+yVam+DKBp=q+Q|& zRQ0R=$)@uqH;hSPB%mpTSZuC}C!uD+P8nM7*-OIbw*yHo_6W6O@dRRF2^u?d^VcEy zICRp_$Tp@KfS^i8Fm7h0m!r0de2QwnL7N295O9eaFnmvWhn!S21|2DU+$}$z)nk_+ z-X%LN9|(obeu%fxHvmIyS+Wk-l%C+`=M7?{RyvR^EYF;q{slGQz=}T z%{S#%ama;fb>EEA>px#`KAe>%EdQI;*Gs{1&0+P+eWPF1a3~gKE6SbpZh4m4^g2G_ z*^6SMPwkT=N4879@MaB3+&Rf1Hg3O0O<;NOZEuflonpahtGF4XJ9qNk*lZQ zT82Vstrx9cwp(JZ#(etc+VmS#gp}E@xNmN-FJB9Z-DGK;!s|UM58zt>p}FCMXbf!M z-!JLL2s#dh%9@orD$q89aCLf;Q`|UBM6GOgpL|l|+v(iI^x{CYi2-ve!{3NU+P&)8 zSj(4~+HN!XSBzL5yKGK7od*L&Ldw8KX^fM7Qq8mu)~a_CTSmu?GZ?zrk2Mw$7y2K> zQ#VefxIxf^myb`AC=Z#&UdQhfHhjR)o{%@wHEitH=qdpBX7PXbM#JFN^KSNZJMu5p z8YJK>uoE&W5?JM(Q)|ed2YN1P81TX@T8B6o0%z=nqx8VjHi)LPER*W$+Mt zyEAE=I`?A1gJ$I}^Y40Z`V$qt;J>hFJQlyEA_i7WqY!Kg5xr31h-|_~HEoMfOL!%- z!>R?}yjll(hwj1S3lOJy3p<(% z-Ch;SBykF!coY2a!b~E<*Xv>zuWdq0n!zSwXwE!5dbhu+=@55hk~TcY>gwus2lFEK zpNEY+Bmrybjo#4dACi!mSTIH1au%4Z<=kRz9Ubt1e7hce>L`bVHSL$T;22jluqf+u zeD0w_aUjdPur~gY0=L9>;oRCWSKaPjs>HCmo*~cYi z+6gX<;N{xypP88^(q6c2g@kg2F&&2^$j9fIjrS_9!QpL+24&U#-OU*Z_-A{}!dK)z zN38)G+h}PBRS1?eqoa^jp)2PNr#~?KS2|TJj^pu9c**czu!>kO0dVmAa6#!RoW(XK zx9bMGM~8ezf28Q1{xaa_%Dkk&hsJ zJAxi@JsU9wr=GYTYf&a*0#%6OgNNti%~<3NVc5VRUh%8X=Mn7?+$5ewO~nU3*-O+r z_BlBX=djx@TrKHKraW3&${)Ya@C53+S40~Z)Lo0LOw6Jd4jLpeK{^T+C06ltQa=H+ z_K)uIrm!@sM7ohzpM$BIYmA^J+i3DoPzvg z;(}im%Bpf>8h#iZar3q?KbEVgbhRD~KN?9vP1L>5po&`qwfj#M2jB?cXJ(BU!JB-2 z`IDa9fqclKJxv6VCO4GclYDgDeTa=M&>w3^&`iie!dn+tSI3=_T)#s5{(&f}*C09m&;Bm~ z(F@>U0}9i&;UtIYR3L8i@Bs5*g=?v>PD6QAd51)LyikS;5*hdO%|TH&(mxl5SLbF? zS6d5M-u+T$hQE^mxWjGq$w3cCB+kqYrJ1WDRxw%A;NNf2PZy-kzr48_Iy(L{mWf$d z!=PaQQ}XS9N32H*rzSSl1e~~+`#3K}dNM}CZdk*otQq^M=z+R==e5{{v8OymMNfk0 znLA_^M!L|d2iwnH<8E*WVe)>COYylI{7pu;-z@@k<3;%xlHQF)Mcc;NCu}`=jwrpspiP{-_(G)GAp>*!Gj~r z{gVaV`g&G@+0@{O^ zPEdO0({#is>tz=8v@IJL;X=I$4Lr`KFdUM;Q&Bq*Awcy>+sN4l%9;GR2sKkS7}X#! z*Qpq}R_F%0^!=+=+bb?RsKgxEI+v@r$pS0P%)Pz2i@cVV9{KgR6>bv6zIZepp`=s& z1OdL^FI+IYZQZdc7j{Ww8g1Jd5a!zJAs*4Z<$mOf%Igyu5clnoY^N}SGV`*x2xYe} z_;A_X_8cx5Wt#NfUS}uNSdRF9fiCKePa?o@`b zOGt_HRlT2keq65ukBkO2!n8nX@clwBmHz~f*Z~1TgXAacrOLc#QgGmTu?YO+d?hYR z=xXkj`O>tkZ$V*Qf)>Lj<*88bD%PkbGgNp68wg_X+zDJ0GmR zYl>_O0p5A9%um+{;!n}3lLsnJ-TN>mFic_S4r)2} z@2xr$I*R0)hD$-67AIQr_4(5Pd(mI9tWc~`*Fmr>)M&-|e?N z-@sDfIEb4+>B+qkpX(eC0h9avZs}a-%I#A1+_Zkwsn;$V2CzNxJfqjQPGP#2eXo7= z6EHyR$-t)gj8~9dJC68HO=-lI2KPOmFYDqDwR*e4vO%?+5pQP_ZO_k)R>Ngg7d zD}V-imZ7>`$BLMVKPiLd9D=NF27n=#^3jzb3$whGq}QnKn3yG~2Agll+elvzjXexB z{7}AGRak{tZc|exo(DqotMI75=_!F<#NSgY&K*5Oye%N=RnTU3r|nFbtJzE?U04Kd zN>G%~80x&PK#MKp0Wb`VU|Pgwzwm`@*0$^lZ=Km@VtQMxfv;X}bnP7tD9Q|aSY<&E z>ydxl#9Q?0le4I!#Y3N%-A}p%SjnR#(-s=0w~`~(0gHUutJ{Ai>Sch9+nPbaxIe%_ zHTK!II=H8oIthiYQkOT;D(Ix7l$4pvj?0vouJ00hQ5euHc-K6jXMV-VM!dcL5K*~5 zwJIN)OQMa5vq)g^1ms+poToL<5ggOYGY#2?@=7;FN%F(%B*qs!y|vu z2N(>}?L?~VcFhG+MKu%H{dZ0n89AQk%oFwc3CTL4X*oHQo|f5WU~qK{2S}1vK`}U3 zVagzll}mFKr$+ATrYwRaJjbEkjj5EpBRZe~&b1E>8|cvkh5@0%}2GZ4Dd%_Q; z+kaeu)`n}Z*nHRp1b>KwJy-=QvK0ec*-~1v?1QOHqGh6)o5tI{9$eBtAXe_&wS@M8b+p%Jf&&*2neF{`r$d(EQ zWoQM04J|K25kf#5Udx9Rw@U$eiWrkX*Os3=9nv~C=SWY9xZAs)9%(O3$^sy(o`jkf z5eMHsWz!_yaw~R-vHNH4+P&Po8BksVp3?#608rptmiqJ28@^#K#9E)ktm#*yl z>lYYqAi69qeGmzS3Hl|tq+4M}fxcbqyOV&#FYp(7FbCowh-d$7spTaN`_{pFeSt`G z>+HmSB{?4cA9Mn5nV&!G(vwBDB-V^6mzwJ8#fl0*xB+_fRCs&_QaUXmPxGGnGONk* z(I{fZtF=RBLBs0i~`jQ@eAQYZ7jDFHt zb9mdE{_2q`{U@v#|B52CgOyxod{QvbUM(DwGy@kx=p2sqI40YD#%q7id&K|b|8Vu@ z@l>vV)NpeunPZ0}DJnuKn@~<9328#65K-oNR>(YrQW?uwiVQ`z>C`qPnahxNGG)#@ zr`~nz{GQMIJpFUdN7>_jU)Q?UTHm$)Fi_83y5G^*w1z=~BLd+)zt-oaX6sD+y9A4Y zathwh*YC>M_thWm{NuZ_g2pvDxEA+@?jX4&IO+Q5-JUibaY-O1=RdYAD%? zry=q3g^1&u`#20mC?ubu8R$o+)^s(^i7$;nN0<_&N7!E}0*aJafZLH+C#MCu{`-Ni zTL81a-e)ClN9z9{K&@T7RdqbYVPYHOJG+}ZgqW3@KZQN;IQXqhTG};n2lLiFO)81u z9Rgg3Xzq5n5R%>}2p@5$l=#IpkZPx1$YItaK{))kpY)UM#7QdjNt|#=syeE9wkm=? za<^>H>*UiDQuW*fCXtjUsM@kmDWPF}aN|f@OMWQ`Ndd>f0LI|<^Vm+!b+!3uBi+7T zQ!R^z{_j{=e{>)4t1tZ1Y-b`XNt_^`wr#%icL%K`NhfTfGBJ)c@SF@6`sDMucQoLj zt-{VbH|6E=feHpO9a%bXG<`ZWURIs0Yr88tQl)QF+VL*DOT{XA&vVMY;>guV5ntVY zt5#TLr_MWThm#$xfbu65;zOcT1A9mWE=6ybcam(!g6+YOImD!IG=0m<4lwUs|W9lI^akd%#3sY(~Hfx05_lG z%$x1{90JAnrwHhLQ*+6+sz3U-XysK`9X0`XTkMh3+Fd&ckjNY{HYx4p;c>s9c01vB zy>*94$k~({B1-SVQ=;vXV5GiN@ey(D4^9X>)(=oGC)5vvTZaf|aKnb1k(#Y4G5Y2% z|E5++_X})y{Lt2HuS2!n{qFi)I;73Y7L)q^~-M-q7-HrUmF4`oy9eN0&Er2(VNp>9@ zsLgXxVg0ek{G0pxEcyo;|1Ol{djCpX(dJ9H&Xo*~(!XNxzDRQdVqmySH{o1Z6_uATuKpeWr+6{&v0O9vCPe9D-cG#{*)YDRY^ zCRx0pqaG9+(xB@UrPrLjIxh{rMjpOfg#(<-kBBr?vlvlr@FteeY#5YKf73aq*mEcF z;x|5Jy+-?Em*RMH`D{Hsv$$SYv(oLn!LsnX!7g5S;!?D+4!FY1p54`G_7PGo21HD^?7Is;3RXL) z8_w-kGTK2ig7jY33cI;YYAy`=^?wvp70)FOG!xcT!N1=*v`DyFh@c@qgMhi2*U9KZ zAP<^xR{=H@fm1@(e&d{nZtIjZrX~G-lhW7JIm3J?7=+*#Ko#WtLF*)-n1cGXbgti$ zDy)>v$ce+R3g0&_q*)?w$j?9qyU-68)JP6fh-l!Mt4gSf^F69NYi>q>XrqrH^nj0= zh(cO(^|<%iPHlogcM1G+kH30`=mGNROg4V7L)KjDW=FnR%<(_Jn(-jOu;34-hmO`y zVd9HmixT>QD96|Y_;BcKbvP>lvI;)9>lecx3cuEAgaQv|YogchXSHqb?_*+5s0I;e zm*N6W>$XxwvB93>uEM%u=Jk8wdb4=jr{{U80jAY-KtqzCDiiOL zWL^Mo%vlLsM~op(*(=AxvQ^wRrSmo25^_wBt2Py)#G&5)fR^H2_iWRw$6jm)t_6tf z9!Q@NcNRZSpUCJbD<1N|AA^YLo(r8k^vlPyZ`NE8Gqf1I57+W=+POco*#rH*#xJXe zeHQKYsfeF9Z#-_BKV7BPA`tQ*apX<$g*cGv>4||`t}A=JKr_%I$Qzy#Uq#RSMZQqf zvWA0_PB@+9wm;ai3!Q-Qsv*j8G;{cEq&u(&DXL#GCU8hyhx`ft8Nz%GGNrf}RH87l z4lH8!@_!n0!$2l*4Uj^Z(Y3f8vfP#l1b~SX_81=@7Y*CZ zG6XJ}&Kp36ARZCV0gS~~@eDs(1Eh=Ws@Ylg)iM1pqzy}_U4OBr8+k1+-Y>cl*WBG3 zZ-4R-0jXxLn&He3PivglvZu{t{qaAO{z>*j?x}gk+*N$JND$uq55q3KH@*g! zb;^~S!T9*MR8&hL$VAi~M3H7p8rk(co{U+G*{mZ!>!w6n*;39^{xDJ;xGJU{5vQ*HW_TOZf)5TSd~p zB6atBB#$+xneBhBEqOK}z`WH#NYx!7MESRQO4?SJvP2)?X%Ij`RBb8xus%D)Q=fo8 zX!HuVkwF|iaiCo7!S-!VhF$WVD3sqZw-@_{K6Hz#tS}|!FUm^N%*Iy>i)E)hMA$)^ z8K=-0Y$FZ~2W{s!Z1=6_gtr=&PzuBHzNONt-44IjFCBi*8gqdvIUSX-=Ll}VQPR(E{f%9TJQAZ~~~j5FsU)Z+!OHK;Chu*p4LP&zgx%@F}*mQs0r z(szd}^IL{Sp_(5qu(!%L+@NbE`_)SdqvoR^IBKS3)o<_7bG@62$c-w8XJNd6DEb&v*Kf=1~YDy`)(wRh-^iFtv72o>OQZJ`@>+95j zwu()zJG;j&T@rKGYaF2(vGVigf4RB+Ful*Wuaca5m#eVRmQ5LuvSmK4Bm{g1ei-mE z@c)mWZC{d`*rgPS%VvR`5ZiN@r!Mlq@YTT63H>(QM#hc5gWgVt^2F@DY=761!r1Y9 zYte~?Q@fL(xwIt+SDZNk<|VXIx<2NDO9GcsOJ3?S*JSyk>w~msGTNJ8I`L=|!T9`2 z*;!@tL3yd#uBV^A__=sCIKIa_XJXP8zmTwSn9|vw(UF#9uB-iEu?FGgKURqv81KAt@nC7L*Gbvz-7E^s(PDQkO>cO24!CY>u9c`HoekkEEggf^ zLW3;sZvO9&=rk_ZOat9AGlW#M=JjXn3}(&YBZQ#g^Vf)esSyu<`b2?q&b$W= zNWZhmU7u?uhKqbk$3n$s9k+km;jBze-}y=-_0-+G)Z>urRFW;V^M0YvURa-=Ny5LP;8nY_iSQ6Tv4Y7>8>%Uo~7yurf7HM4}&3nSYPWA zWxT!a@?j(t`&U%pDCyE+V;a(E%*bOnfO=yJU+M(>TV^pc=GDrv{(q5IbH%2*{`IFC zAby$7gBvwpz-i0M?M<>^)17P42P~h+wW_fTRFc>QO7{f;&YM#17{CF@E^t<&)3h*P zA9EM=S0MO@6D`qo@U4y(I~$nG;3)Cp7{hjv&R&-=u7bpUs+!u1r|_+)Gp!p44-?AKsZIE*jpp84ZD4(7D00VNs$ElE#FOCwNLZsc^=uTcw=xqG&E(TsT zqYS2o4*n2cXPiKgyC{;BxPDjQ)f#x4yA#`x;=YL^FrNB(6o+5dXF$U&O``(AtZvU` z7Ooc2x>@{a{$ubmlPr&Nf!Kad)=G($0g?w=0|)YBxt-;Y{5%4;XI(q*83!&6@2rb{ zr)a=KKB6520H&uEy+^6r_5}fi^r`>j31I6A?|GAvVL%EIbJpLf|3sjcC{s`&jP&3E z_ArCQvFn^eQNomY*}a!CzT+5m)A=;l0DQu<4z_1*MRE5l=^b6xbl%^8{HVmi-hyCh z0FFB60yy5Ks~q~_QdvOcG!ok{BH);j7)UUN{(ozr;JhccJTyb`D?yPCigK72C5FSg z%TL0wk(fwKHT^UC<$UZ?iv!JJ2esel`Sa(Z^v^S{unELi_K=fQ*r3i?9EDcfS`ny8 zGnf#DJW}}(o@Yu{W2!A7t~P*+7l)wMy{o3Kyf5t|Xvt(r8g@S^D4q0o0!9_WW0Z!<@vCG;YyGZO2 zV+O~zuIv__gJ1jtzL(AVNV}h?r_WMf_}BB$L8~gO_MP(Uijv>F?|K3mHvA>Zs734Z zPBD4ObACC#+v}>u+QiY6JeB71*(6yy>batzAW&o9$2sr)DLX>9EX)9W6G3_>ZZCfSM8%$vn?N}eVXWQ+De6J@`8)?l;oPf@Jjw#*L- zG>29MCZg{&I3A*n;~Fdm<?NVZG|=J zA>&Mn`LWeLyr&6gAi);_XD=^%ko;T{{0*G#p_L*}`akr9$e{euV-Vl?2LS%(y$>&SQjldxJy4#?39*H1ecMGr|g&v&on%g5&xBqToC|*&`rT zZ?vJ6G?9Fqrr{;f*%}GzK^~mJI%Ar>u*wDdnjUsR#$70gNj0PVe8jQt_NnNuDJF04 zc3Wmymt$K*R4y>PxVUs3x^H(H1S?1Aqly^e#zq)4b{(VjYTB?=iLr-lmt};f7?Po1 zmz4W0;UiPhJx`4}j8gvGX~z>Qx2-|qO7ypX&W(GQH+p`&5(kfg;aa|ho|&0T`nNTA z%CFLjUM~kzU*`sU)x@|IGs?h^;QC4uo51`Ym-Q8!^hn3PglG*%rIK;+7#Sl4gHiasB zRXq_H^A$t`96(p{sM+VMSt%RsNgK@568j~USnNqG%&$29xi(BOng4o4hlY4?9L!UO zrLfoJ+=Q+^@`XjFXHR$FO0^WXu(0Xu6UjaAd^Ie@w7b_@{>;e0NRhqxd6tDz zGL95(W;NR3nk5|HKNGU{NyGoarorY*LYso=7&h#$Vfj;@Br7{rYgN$lmL&pV^~R4Z zdyTV;@7%xY-Xgk9A%`yUw;%I#=-$VUj9BjKalRgXIbGH3n-=b|sb)&L=8$f2D+;-; zsb%!~Bo9`?my^S=GwkB2s3#Q~al*8B-ZHWxKiAv84AG4f)hpHN+yVWwKH4x9#-7d> zRDT|SK+Zbzy6E5JnO=E)mb_rr${LAulbR$!`vMtif2M;)V9OUUCdwt_>JQagCeB1& zvk`eb(KIKG1KNO3*Z-vYL8^@mKi!T)Bi9`lxt1PEFV1E9?6FeQn0fTZ6SY$&HXrz9 zUr?*)T$MF`9ufEGRBJAWGlw`d$L5bn&2UZn9$fx1xVKY85DQofMMv(Kpxd&Z7uE5; zW&2>>X>2W8ar0*npEmN9xHm#m#nHjRKEK>eXf{pI{k!?#S1G+=`yTVb%;c_nI8*fhCyaBZEj#>}AT5S%i|HwhRh zY#Z*DPp;gp50KRkFQR5ULSN7jT6~AmKVdjrH*BWBf08HlG@HU34o##N-z6EnI=4#= zo+%&wQDU7J3~%_@U3tdW>qOG(|zF6V>>i+Kqd8sdkXqP$0P6j-77jwy~8L zAK>m}V}s@o6f3m0i?{^SeQVtLw|#mZFv!1$AISr(e1}w`Xz%3Z8(5NuDH$1&{Dp7c zSd&$yh87pE$b%jbr60CG+1f@3Xr+aPHWFv05OHX%b@|ezj(l`vxFisy&~5l=2^J^- z{gM)1_Y2xr0+3)+p-^mz$C{ix6lMgG`>Aw&L5HyG;+IetA~*CQx9n}wdp?8Hgwoqnqm!|S5?n&xDVU0y^6OO?^f4;REXMg=Zemc%z26p016fp)Hk8Z1iIsw+e_`6Q?t1_@eh^r(EQi_V~WHci? zIy!LfWQI5@Lj%e%ApLM*Ac!Mhf{#JMrWv>53tql!NY(IO6`P15e(0~!U-CU%T|Z2@ zi)kA^TN_-3a(k`WzkCeyqU5mza5 zU+4y6gZ%YCL?3*1(Sg~*5>8oy4+AZA?$T$}M`EE5jv|Ml44c4Kl{T2st*HJHe7JTL zb1T2Re)oIf?S#!Qjg;N&$0O* z1q+)~-)J@YXoHaFt#s#iJIr|=_HUo~kUL_kEIoaN>T&}tArtEC@`Rd?=G;iQPTLxy zAE^PD$Q3e!>MUlyrC+~38t?CCddaT@xEljo`7Xj$^8TP|OIK9EvKnE+#(QoS@7fxj zyjI|GaCX9kVCmL@ zuT&}(4pBBNWnBk~LqG+-u!#M;2S(@-w~c%$LA-$2IYo6zKtEpc1peQr*nmXIqI!!- zHs)s@oDS;=a9%HWH3ZC&+aa(-dgmQUGYwKSxKVw6X3H_rQ*T|Wq-5nh?lXV!%Fthg zZjE?)V2?8{H*)t{SBB3Hy3wi46Te&FO1bmRfJ6vNr+Yrn$z1t_bLHK5O9N7pWT_jedF$`Dciv1)!R`+f-3rT5l$~v8)Ge_Mps?2U{HCWweJXRD;jL z=a`$PCVwvLYJR!OPR=|7_RNf+E<5EO5b_X)YkHTuQ!F}?i^i+B5l6j$ci(eKn9vti zo!+jj+e)9PA?|J}6y$OU-kg6L6%F1Lf?md%D-2^`Pk|SG>W+8zbZ3aLrEPp(tmgNCS~#Yph^E;mw)D#ZkXl@0W6Br z+>(;5!D+9brym6P6PSFbs(Z*p zEd}oZ^lMVS^dh)4kau%O+&Xu`R;2jS@}1jl{c_j6pLCiZ@R4M#GGFR*9)r)Oq49Yv zVbRwZUXmq_yd-CSf*f0s(5ePiD@k#iS6ZK)ojH(@by+h#2eXxBp^fd+_b+53VVIv9 z^qas)7BcedW~vTWEp`C7hCcYVMaV??SKFYo*}nRzG&AC^BHSc!838tT`#Nnbt)Ak( z&;RqgsJ86!<24=Tg@PK~uubsS+v(6=<-3DdyZr;NbOdLpZ;t6*mw#Tg!Ga^f$!v6% zX`OR4{$Cq=G)aUI+*T*%|HYA(HvCMpyoNb9h@HZ|9(vW+^F7gG8yG)e;w1US#6R<| zWc+q$O|C;$dMQ=34V5)GOv8>eZQlwdubqWi-fEY9-RVf*;Bw3La*qf1@&R)=u|f}J z_uuz2nAK&AzB-$^au3(mM3Xof?Jw;d3MdpNOqS^#OBI33%9Fkx?6c2Sm{D=}F9KFL zjZAe{^?qPXj0=ES_a@xyODvAWnQ064E}+x2Suf7PMTdglqZ_^`BJzDb?ZYngujQ=> z22bBapC#6_-Xf4Pf=-IOj+{I_AAxV$=VN^B&RWMX3S=-t9WF>*DDfITd<22oo zpE>-6War{CNceBjix_~~X$P8=`#>r79qD=i9Rk;Y{Si>Y#--Z|Mw4qG!XqY@5KQox zW-%GSQe6WGg4VrsNsbt`ljIiI;b3C}7RQ^X1DOAHyE#N4IYTFjdj()W-O1d325(AB zf7G0=dqS4vW`N?QP((YZ0$l){K^fU#UK*L$mIWu}avusStb0&~tzvGuqCx>4>PjVR z7Zg<{TfWqwy4<`Fo|$CybA_gC1K2?Cj0r5Z07I8Bs-H2g88y)UUs^5b7M@@k!_>$F<68s!;uD z{`#fvHb7wrt>&f6-ab8GzK@RxnJDP|j|{>W9b-w}>lTk=!Y|NHPytJeyrTqd%mrnG zaZvh81mWo*PZecRT^^5p-2w#JjHy27_68XCMEY`kSkSEQ<$zM2O~f+Owc!_yV##|205IByzv`y<-j-Cdp% zzh5gOBbSg!vh0SlHNhPc&c>>8-9ZH2y$DTmr zW5#z^lbhV7+{||D=(zIa2P$=KT6vOScC?k(vHHWa$Jfh&N_!7@bXQ(0+90vHyTdGI z{667AjNBd81J~6y0aHhUWQ89Aqju`{_W5k^vq{9NFs;KU|7ClG&fCf~ag}g(foAb1 zmdt6f4*)CE%nntuDeU4?3}$`x)zjHov+BWD6o!$%a&O%iemNY)eFgzO9)D(5H#waX zE4_dz8XP#cytFhtQ~vFB1tVtsEDPkAKtB;;eMkP%GLOfBoQ*aUJ^%-wMd|UxsvDGs zt_QK|%;VW!Rj+6-qLnkqF~*;PjTl?-$K{_Z8%CwBDf39MYIOk3bC{2SOgy*!HNU^T zN%GUo-RynBC?#T#7m^j+|24cHaF)o=gp5wg%-FnX!1~pztM$?3OBOQP-N^88&^2=K zjXOa%zMZSJcXS9YzoQ{H3?q+wYQ_zGMq?Qv**G4(d?iQ3k-VR63zaV^ia(6Z5s{JM zOiI;;K#38DKq>jL^+OaBECvpg!1pWT9E35^xuOp8T>iZ`28eGAL-RsZnUsoGM= zt=hTnwui$>N;@$Xf<(AMX98E2dGGjd#;-MBSax9YR6>8pXugoLv_r+(cEW^=K|48Z zLrm)ssrw-CgB3hB)JV9_Mr#_N%rwICi-#OlB_W%YX(s|h)(rjJzD!^_ffL-f{p%5& zP((A)!nv%hqY#!Nx*MiV;&>cW<$ZkQX6p%~$#V2Vd!K-(|K_1O(jg7DxprlW@5N4cgz-NVUJ$B) zV0Fj9*^&5@_A)dFqSfM%pLQWwD`(&hkBk2k`;U2CDR4Hwp1A$h@2v}KBbuDWG|PM| zSV~K@LYaTv;Tlf7(ko(jtGZYF<8!}w6kt1`&DZXwC*|X zlw-tQQZc^FqN+=q|JEpSyP{fTbRhF>w@F;rR71Dq;l!0S?XvU5J%2F|Se(KVjKkeN z*O9N=+U3j}Xa2N)ELX@*s;x8r_n)fmHwI2EVC=#tPF!z(tLjk!FOpG+7#WOhL(e=q z;0Yvn*PpbA3_<&{6WskSKPe1eo4yT{Zr%G>+msUWaWj=kqk!5)T&v$NVKlh$-w1&w zagQ?0fM92apSxphjxUJ=T_qrv%VUJKvYg@HC5Iu`cr2Ke|2v=NfZm|(n^#DtZWae- zLi^g3^qfb%{nDj@8D%4Jl_+S(jkb3Nq zb)RWSK>omuXi72GN~@vvZaU_U=8QEr=BFPRkk}QvOdn3~RBX1eaiB7O$i2oP*eTRx zu|u|a-!4#fmbWKEb+xf~)L~P&(suX23h$F~%%hssab6sU1ij<)o4s!V5CPGFErJcPf-*DH2(^*}c_?%IEtnVFHU2UgX+UQp#DN?(MX@J2#E26HrgQZ8VQ zmN4qKIFvjT?#uk#umYJ7b_4HtQDLE+Mq}w%xE_t^3^T6UfuW)O^i%{E0eHY#mWhu# z`lCPft!2T6`Tj0zQq@FvxA&4q{7Dv=81hFO32XY?8XlxnDcYRB^qG<`-wINY&^?XY zP4Zy3QfYwomMR(-A3tHt-wz1mg$5l=AQ9Gaj3fDR;b@2znK&Ji?0^h9EOK1mt~u!S zW(=7XT&LoZu7gVtn^`bh#ioSQMVtb-F_ty{&jG(1;fUPn`-yGVIgZ2cNtXBHnRk{2 zc2ehAmfX0xM%5T)<*q)*IBs_#si%{-hn}EYsvUk{{d( zU{DhgXc+m5Dxq?ra}LISpbuQ!xj5^Me*V~#Mjde_Q?iOc!AYH$`nkABG2?ud z`l*wfUAWQ@I}MR1rXFjt~5DUe!Az5hdLkXH9X74 zmc9)_TYp6t)T61IuFYNb*W3#;5A-o`2?A*bGMe}pq5=>t$4~G(1Oj{yE;+!IB1{;0 zBl*8vzgG-3v&*`nq&Ph&YK8bUP3T9OrF8u$?J(J|DM2_-XlaE=io}IG=K-%ya(6F= z?FhMSB_u`W=I@J$wI2j#YK~~K!Hk)LIu1>>@-D}A#Dd0bkX(Yr_I0XQCAyDSAE$M8 z?j({7wopau?dqaE7xCaN(X;#d=~AI}-tAwY(RM^eaKp=lL4F&NY(%JwUi*JJAs(I| zE~`cF2`Bz3PAIWUv$dajmGJl*ks|;vk@Lrl@p%k^imUXy{NUka+!Y8zR`bON z+dh-S-pez0?N9c{(p6=1HWEeK$$7?X3K+6tgj%p6CB5VkWJfaA~@;hRL<;8jv z4*alPSBV9&f1oETyG{*XK|GvA<_ zf+gcxee`JwW=YP{e2bZPiV4|Nf1mptd3!QA*1cM>Em>y2D&}Z_NPl7Ib7sbVyt#!g z^JiVCUBL1x?*8=r^v_jHiX)2^;jbn6By$M)U;Ww*N>~04kDt}7vzgchdPhSKaYuWQ zxgCq*ebk#aQ8uz&3R>1=xxeWrgSh((VOs7>a8^UC%5M3e$}shvIg69U^xN$J(TOmQ zY^1qG7$f*@yWUq0<|PN~*&{Z}KB;n>ykVY5h>!2$RnO^udVH@MJ@s+sndt`c6s|Al z4MR5{2k#i`Q@s<}26W!yD)q2a)YaJw@Ub?qF8Fb7e}f z69EO7%z7$Db8mKlL;>GL{&nRX$F{tD`z_afy7MZLX{r^i`MovQF5&vtgM<&gZE&xZ z_G5Ouf)``uRASvh(@#gj$V;-eR6!}F>#`~#(ATrWZACJ|$DkWG4inGt$QJMKBO~So z9ovmyVle^yv&rokoi5p384T=4{XZkH6Q=LN4QQi*5zBYDEm|t*e(w)E6$CALR!>yC z%=dyY{UggVUk7>3ROjJ8oOB!NyvAPLGM;yz@(QAhU6Pvf3gT!E9r&ZD$a*IBM%fhC zBsC)7W1I21O0xgT$)2ð24-0E%1e_kqnM>B8d*u-{& zCTbx`sFP#_I}$=ref{)Qnt4|<%UbMZ^LyeLxF8(vMxus*kAQO-Jf{;&e zsPcPKT2%u<5xmx{*fh4j_l!Ht)t4PQBEZ+M`Mch^QUw(zGigzl~xg z1VU%zL4Dm~s)~eT;Gq})L7N4^k7{NyLz&#Fb#F^ndA}C?58(VCz=>?73Ep}V=5xF6 zSaIJBsMm_#PUY)NB`E01sTRSYFZsIV2k1|Rs%u3v_?;fZbb{tRDb7+}I{PS7Ff+S* z;ZxDq*C(bDm&%pyr#(A(+2+v)VeV%yf)^LreV5nj#^85|Uv27M=XU7ZU*^0!Hc7D5 zV`*}7ni$z-43}Yv+~YL8q~b3 zB_(U$z(sbwH5%+*jG+zp%_sjP2-chrj=}^)iutyx9KD`-p$f29BS*>)i)phdPz>%# zI3c&-31jIuFIyJBT`Sh{@SxG{1RjE3=HjxCk3cS&jGC87sF2jSgrI=WpYI3b?3b05 zMJywj;;4v``PPW(onZP)I3Fub z0Rr{I02T=dMCH~bI$jlikdtXnRvGhiscH}6Rhawi25{rl?2#l7{@xPxepL1H6Up_8c_1H@yL= z2X3qF7mQaj3i9}s&c$7AezI&q@|%*zv@D=2Zhk@DeiuERI;IBv9{ovVkBJU_MN)xl zZ~}$n>dGc|?E8@f;*)vrq!o>it*SUFcvC(Pr_s2M70D0hxYp3Gl)}R8esXFIuX|FL zFyhp1e$@O%_mf%^qmZ{bKjfIWRbcJ(;cbIT3i_k+AhaIyOqc$2ueaWSg|Gl7@;h$7{>p{ zYq!pMG>cOTt+}g+m!6QO#CW?RSu;*h-V)iBLu*@H5^^4B^xWy>SMp|00nk(Ydzz0%rNC2`FW1%fqKFt^&JJJVO-3;1kmr_W|R)4i?*+ak3Yg!J=RadJ*AI z3H@#Kt^}_lR0H8Jj`-)uJ@NGXZ9v#|Rssyx{-4zw@J6i}mc(dd%6@w1S(NUov&k`G z9$Hfs13GXQ4_AhW(VO(PH2h8v32Ban;dg=KE zB6`Ws0HFvZKltv6*)r#NOY%#m5{1IEePEFgq&6LtuPR|gPs|(^7k@WS$rZA3$SXrI zDV;Z9iC-785!fr}mzOY!T1nt3!Ob`!q~b{sO?`jC)CNp^)9BBimJ`B~h#T=NQ(X2U z-f*r^s2J8F)3s+Ax?=A4FFdn9Y4Z*k5%Y4zAs3@j6#)iG+5}-&-)jm=5fCvkAx2Dg z`0#4_LrCV%yU=<>ztrL9!UEDl)Y;(B{VyI02K~?#Z-%0=4&yE2ehctCk(jCqf`|EX z#(0ZtU4N5TceeC&KEJ?XY3r0rzsu3e@6~U1h0O2Whd(*4$lGeZq`a zLHJ4nd=1F;hfUrakT9be#yLF}+wa0G@{8F^t3Dcx)R-m`r7jty#Ig%G_M1%JhJSxs zhDL$HY}a@LqAkr|OfP>{iK+>EfTC<=MzeE2Tw1!<$?1Ik@Pyp>)3w*9wN=CY#Cw>F z#@mm78=J$}<3T^AKL$A1Yj6J}|NfomCwt7B5m1R{os(x(!cqT*SU-nQlJHh=&=(wl zM)+*9s0U|S_<^}453OiIC(}ND9VghP?i4f5;!1*N-AQldzw(K=W1>j*G4%qhu1AB` zwvIb_MB^t?^bxF_LKcC{e!IS0{p3KKD=DsM{4M5UNZMd=DG53X<`HyTcj*zV6UOm+ z9#(I3(CzW53o`vzI&Al4`Rp#9nu`v)cGRaQ5ps}(8HqQ(+Z33qY&!DWTwX#N+@bG3 zUYi7VLR2YoWkLBG)wM0lEapn4YEf0?}Uhb9urkYqKDeT;coP(7Spho|4 z#nHd0CQrY)YNL5f&as#QjbL{D-nHd5me$^k^wISrs{WH6^BAKml|%^Cr(zrN@D`1N znK1-Z1r$d?m9c7h()dGd?3Z6$c8x;l`j)W?eNgQZq2IeN{~XX}qE9SfS833CK5w?e z+krSMwmcgbqj_#p+-*CgPNMcRe%nH@$!=L1dqnYdBhkRpxuq~kq_W-pyrTU)svsYufzMA zNZS;;Zp7K2QD@WqEL!=33eTkM0g<3?(>zvNWD+3QVJ2LGRX?ul`7vfJbnO4!GTv`= zR=0K7zM0fDqA`hIJdQB@5cd7Ofw@8m>w`#5#k#@TaZl0k0BeID1T@Gd#ny zHu?IGwWmq^f)^rp((e;gk36a8JeWF?U7#n~JKl8D{~d$>gKygTzoK_`Wg8zTX5JH< zayEGHo=CoZYaXAtH9y`JJ6JWHw?A)kv_fv@SCQu#=~cf>CLQPg6rA{Ee;ES7A5qz@!ljlV{phOuJYV2HTG19AVcmPGIMAY0 zghg?q(m5n%WnLauyt7!Uf9bxsHLL8#9o*dSn^A0clqfV&x*q$>Hd5{%C6?;^d&9^Y zj?!&EErH)lA!{WAQ-$0U`KC|L!m+Ltb+ z#O9rD58i^S{#ljpk13qq5ABJ0ot)E`h#@zR#I$`o%%k#xqbv>xG^wAl z7<^n(QUVJT(X`so?dz%E%CB@NwpRR9vell)HGN2M7o~SX@Zom;d+Y)oS(ZeZf%JyI zNuI4ZuNglQmmJLBZ2K_AGKW{uU+&nzUf)IXEI<`@ccLM4H13hv%g=*sC zcN`_#H(>u`TG!-|lVF(}a&T+%#*G_U!?)c;p+e_|s&xAQc>y}hJkYS4mXX0BqIXtC z^C3!27^u9$PdIlULlCKE=4GYGkNs26HU{Si)gZ7X-qJRdYa241&c~78&n*LEDMv+# zol<5K)(8=6GWb(1kcdYinRU=EgYj}nP_*fOEEvSVz>qTh&-t@dfy7V{iwNPI?5n|J zZq+Mx&XLtVGk>i>dN9LfX6W;$-FK9l?PU|oru5Ly3&#rnl^AO2W!&Df1 z8Qj?z07dZ4Wa)2vYI!*5(V8>Q#ZJBBpNRao+Nw9Cxbc~q_3dfB;p#}PW|h+WrCZ7H z3RM_BiS06*Rhqw+&PuFb(NnFWnMCINVzIS0#cYdgT&`Z+>FCfP{Oz6w>sp*Pe%7T% zrQAC}5xK}+g+oMhDD!c?QI!G?fzmN2U3?_G?UuEw5?d49MJt_Q7isM4>r2^PVFF9* z!ea^KLNm#7ynoKn@pFA|c+)==O`$Zdz4=#!*gKk3t}6$zUPp-hjrmt8pN8Xq$%Gl1 zC@Ts*AovG+d@&$|qZn9Mt#UshzEW41g_e5wBI>8eVWa8ul@AFh0VlaE3YJk(Dcwch zh0t2}&IbV@-Ft$wZS@SA#bJ114P)hskAqHTsU{(5dERqVI;89)Dp7d>uwqR=DoN zI?!NSh;RlaL?QRJXD?^kfBtBahs+99)l;3_J*e*9;U{NO6Iy}U*Sz)+d%NboKI2Q5 z&d0S0`&I5&HObRrTIX9Y2T!Dq4l)K5g{@*ygojgC&vG>SGZUS39}r|3mWL)4Da@n^ z(7wLXImi)=3@)wcP|LoLDwOI}glygGEzRsZ@Zt~6SFm!fS_a~z5k78^;9@1@&i^wGBP8qNI*>Nvg> zAeeL_vTg9^xym4+ue;rd&bcGB zk*n38RXmj_lJ8X|B!4)-)1h;)UA^N7r)=OC*EJtD+Sxe|r1(^X2SIS>QQ-evKr%ZSsUu)7j8@&omFU3+5BFVzV)T$kG-_%@8)le#I?V4<<-|5 ztwe*upj4LD!3PxKR526$xL|`{?6HmJ$`Z%)R#qJ6|E`(l*ND3^u05y}>EpAuUFq~U zT5A@p4QX8aJh>6Bpr5aKj7$zlI^BW+s~yXvFa%FIZHN>Ih_TESPVIN$EX^85D(4Z( zr9j{6x#gAHACeir`|OYHBR3CaW@L!7OQDU?)7tuO+B0dDPa79z!@B}zFse2G{rd^W zZK-6NuY&GPGeu=(Wd#K&B{^h*ca}8fR{OZIx<40wDWP+PTx6? zxmS|Rk{jD?@7?+s9o6itbgp-P(xPJ1gl(-L4Yd|zavP0yU+*O13-j$m<2}$|Kwk*% z7!ObL$K!44>}_cl4oVVGOTb8>hQz8>Jkp$}h$Q9KK~{N>{9SHF^6DvNjW11~J!)~y z{-}~-Z>7Hc;rCV@Q7M0A+0)-g#v?524D*W>M;@I!?r&iF!hZLugW75mn-YKZ4;=Vs zFlJ`6ywkR(+C&(3#H4QN$%dHVR(?P;&j0GXaW%&a|H^MUw$t0XV!!6QtzNpv*xmPH zX86IiNBLZwH>DU#+M z`6E~!^zvhqde^o~6bc5VV9+2pBLh3--+%7&1AFmrEU9-bvl@MKJC~!z&DI>!rkuQv z!H1Z%9Eph|DO{^og|AvEGQBlCDUB&ZfSV zcuBE9QTo?C=g{6*5Sq8=tt~iy7TF?lPBX@17P$R(scqMd>R*7{L~JkpNi#Rj+GusQ z!6RX|#!!;=TWjm_oQ?iRSk|{Mm@RA9PhDd?YR9TYR(RJc9@_hfLdn{b zi?x#lBP<_sKM8wUAWP`-0i%y^->w!u5*20teE3Sfo_0FxzQG^7n>vLn0##FprZG2b z=LaPvGWAo7r6M)9J&e824M@NOM|T_UciN|VjjvDdU%5jYQ6h6R-aE6R`rEez4>lnk z(Zu>xr%b`kd3{WF?Fq1sEV%z}+!!E|jfL!ZL*TvkCOJ1Zx5>%T{B|&Y()ELL4l2>c zW-%Yk3vDv)y<9A1^uFrkG}jZ(bW~V1Ul++B@}0qWk_sNyqZuZnEcO zZ?$d^I+B4Vul~2T4=tTul(8M z^va^cAzt?1hP?6K<9*?gmL0S5<-UFf_)BVm7`zg4Oy(VqbUUNCU%X)bk^fw~bFL|M zbvj~T^G8Pq_cHEKl90G>{H$aBR*8||c-$e>K3mDgRTD-Q$mm+Cb6Z_#{Lu0t`r)o* z)rj4V{Z>i(){R@N126o(ZoMr5+eDlr;5#DYHDgWRRx9u8ui{S;-xz^ zxEHPn=!Xk^z>Oxz5jWOCmS@!jD7vZQc5`;WU3sZn!otHnIumP6A}xoBZ+Zn=sFGF9 zLH>RduQfl~aXD_jRK#u&LZfd_`6**9#EHW)nD#6scJE`~deZKdzpAuTm=G)RSVE+H z=%7h`bm>@>B?HDV(9MW5&jHnIFeKa^mwaj#0}>2)%(z{YKDqt;??=X3k^Er5iaQS# z0&!8YtO_|AK18{#-iVe=xYv}P&UDL9Do0lcs&d1y2CXt~tNvYk>M!7-V93-iZz6<;<(lQupOMM&*SP#D4Bt`~UZK;m3 zE8T;_z{kH7JkL^}`hbQFy>A(5^TXr-r?Djqt7>Ch)A%66N!RYekDzmM6-RpcY2xQ+ zzkPH)nEy*1;BtWbjjZ+%+x|gx0M&+l$;zRoSETT8-Pn0nL{V5xO7qve-U&O4i*W<` zc=6(t`*|;&ChHAI{Itu@w^an*e6=Qm6l(c%1kR-mAMRJT=cOJ@X!D9-tbABuC}-2n zS#m$BIcIds*MZAnxOHm!&fD&%Ke_4A^@!r;QS5gD>DzitAKmnbFU;7Ve{I96?@uJE&Q^gtkUD5=(h6Ft6%+N`=rpd*H@JG z8X^>Vn24D=rGC#CN!Brzgb(rZbJ#W<75D8;PiMVBsrKwwX?`!i-_2b4Q$|J-+2(^F z08e{T?wH%)zYQJ-`l`@)^{!FY_WZY+>+!;=WUVre0VIva2nOxtI@n^0GMV%Wq>EW} zoVnIFudxrA_yFP`1Xu24obRv*3d^-is!zAG7<9GJ#Gc`S``vLf z3MMJ_ZGNWQ{CP;5MOM)?1PQs#P>V8ExxCgYnq$CzZZtg*NAZ^7Q|)h*kKTzaJC{W^ zv|m-?PQpH+6lrf)>q@Eq;qvtZZOgEP6Q%ZvrIFhFSAz#(lLj)hHx$X6GBm)^UBWse zaj!jZ^4>`;o;c{WYw2r_MPIq+;OR0x8XCe8H-#F-Ro1#l9jx#cYOB_}i7$b1`j)`L z1dazei*e$7l@I%DxBETe5qqYe^C#+Nuhu>3%5e|<=n9SJm)I1L)+v`H-*ANU8802b zJEE&Abr-o<8kk*QM=C!oN6EBcP|I~?nca*(19~+1j_g;pPX|KXMbk;%L|S+IY;11( z6PnZMdG1|zs$6ZF=9Vj=pRH~ka8R*3^V_UI-}La-!5^F|f?M@l9VkmNzZ9s7vnr}q z6o>p5!(R@n(rZZgSJ((03%n5$lQtn;?`ae@E?JW$+~+f*4Flm`-r?w`4~8v z8tL{$Z{PQ~$$N=XO&z4`;2>K#cqg*YR?GIjk&nH^%f>pr`FS|L{1+#S&v@@q&S{cK z4$h3LALgu|>Lr`oMOm`Qy8ILzOj~N^SNdmT?9Gw!OP5~DYJbSzJ_+kpI`?og3^zxi z2R$wEbEKGsOiCx(zGy>Q`6l*?YL9#U3y2;f;M8D7!IGK1qTqr+--lO6*##DVv^^yU z_B`B6---q{;d5*Pa}lbyBDHKkU?*L^Kms} z)gW+WzZI!)mH{XCWgl+Nnt?36%Ign)Km zd)4HJ;~n|;(|JLjM1``Tz!67fXL!Q%M=PDHZ@efB6pG`MYs`8bI=HuHU+^~np|RU?pDJCV&+P1Mh!|BAJJ?i3 zaQv?ed(Ru4jY)g;>1>^*4vrAj~)+Yh<|YF0|r2pb_H#!99iu8d`-fecI9Uw_Fp&#VK3NDImfCaiy zyb`T9lq~%c*CR7m4Hy_1`xcMT`}98WaES7$3r-413h-ZK_=00vw|tYzKPE3mTln8t zbd)+z7!JKP6becL*#xd6KeOKjj*AM_>ot@tG;0eax*x*Bfi8sg9%mks0|?ucRs7Q0zXKv-U`>VAc}W z2VN*75~4pD6y-Mh`MHL%*3dx|Qy^hfK^?SP(=BqLxC+MHM(;<>*rW8E;G6tIS9<#X zb(plA8(4@c{$o)_SNfaf_}*RN65kdMd-v^?3{w6h`Bk(f>>P_e-#}XF*pbzWw=dY9 z`c}oWz2&`J)S}ukJx5AtE=$G@A`+O#Kw-;8qf1Bhf04*G`%&SgXsRR zTgW#r#=Yo|5j&-~Ki1IRd8663&t8YLQE(h*ev(oc*xjoKmja`hgf`!4EPO8yTOCjh z-~f2$`tR6;sIl0zN3|vfBuCx!`jEb7*)Jv#^2|#Y78XXp*2YG4A_9R6qbkjp1%yTq_9v~SXmAlUE zT~QnF62-IAKWby2ZQNo8!1u=kOZw>PL!F*X6q9}Ed< z<|7u`(QGYHw2o%t3>KK2o6DIMS1DZ^=-%-9D9NeHxXbc9k77x6j07Zj0SnL^<~L1D z+?>1-%Pd!9hTT9q8l4>-Z#Jz@K#3!GSZm=|@28{3*x)^%q=afn_{1qU#->8o!dy|e zmC2*|k!4U(DPlJQCGhDp+t!@Duf9iv1gTA&`CylEnI0fGrE(i?RZ|>WsLB0*UMRH9 z^VG{_6I>7}rZCbw!Z>q4OWV~Thbi3XZ}f$kZ_9%A)-v5$Std5563C={pote4>ltfK zZQ;Yo-*|)0@6t-y!7cjw`mq41?b$F1&`4rr+ugq575L8cB8bQ6u@6B0pRvh#eMTXQ z=9&qphTc+FmK>H-o4iWkcPF+=za1H7V+RxU`tZ#arRoTuNA~BZlGMcR=X5Fk;_xgC zN!z&?YGQ&pV0=CG4YVIMLS!!72)yXsgfFr|(0o1db35_Ni+qr=<3?iSZo(`_&_wkR zucoY$Q508Xk%iKeldLNZ9uz#Pf69}bKf`RUy@&pdp3)w>wdnR4^nhZNY!c_AA*hhl z&`7fsAJAfvIvPFqk##BPJxAy`K!}ukLnY;l;yA4W*zev)7n9{??rXeZ)XSXd6M~BT z!pdWE4>cnhnX{1E8)k>*KK5=ut!NxnL`Btm4YT>J7D0InXfm`GMoE>&rN5?Z{2qO* z`<*;QV+s+!8Uj~)ntuXR{xIG^_v`oNMtO$!a|bW>UmFNkaX+q^{btS}P~k}Z11uGg z9o-N~$I7o+<4SB`hc9RG+=@2S@7K^U3!Wj2@TyJ-Q-uDQi{y^vZ#mVjs$5kDt+w&z z@Aw<7F9DC*S(syawuRVB6F|1WU0tc?=Zd69NmRT< zm7wvZ+2SkCuf)Ap1{>vU`bo#D^S3n;O|IfzTZkaOM0_+9M+$PG=X3Kg$ ztEav?gfN{TN-By-QT83bwvmH=Kzqx16DruHo#_*!4_MJ3I0}+dKqnIfDdm3gWj6?`$1^6iy8M%~w@}&Atm%W>ZJDa;Wq84`I3$E*J;H{P80gIb(EG@U2NovcB-o-k%)Da%FL&%@1?^R@Z zo>b=r%))+^t0C$=LPqqheO9UYUw)}5v0n{*g(o=Mzn?KzivVItI6eOKrPTa`$yP$= z&&qjV-M6TU(j=a-hR5Bs0Np{^hC@YZMScBuK8O|=20bWo>~lw|RxnKby5$#++|btQ zd-u~R_i_d+#y2dT<%JRd)6Oh9->?uXNm%M=xsVFoE8u~G-ltn`SL4f7neQrOXIAF} z$Rdi1N=suZA-QEq^QLH~y*-r^yWv#u=E9=hg{GLct%u!Iy&F|YEf;6fe@C`gr8DyO znQF6JWVft@fy@>XUUCGjo)b7E$}?c7lHPN6<;}-{1EU3_^6s#CwNAh=A!!_3Y=Bo|c0xCF;jIqOEi823xy*yz0Qm-_6up(E zjEVbP$dyUF1N|4~!znNMsuRGj7~gfT6tOcQNc z(bJv(eXz=3L8je()Aan6M(DFo?#y818qr8_gg|PS;rg;q?*Se9PSEh3gdblg7khYD8Q!Z10_f;BElZpKX-N z#bC~?pPwI??aUwQo2Dg@B+<~Qa$kD{IY~*cZJ~pEK%r*9;a-BI56Kfj1H$nN_T575 z^9_e)Cf~6hgrwg&iio4fu6S;D0`F8PDJl7Z!rlSS0nE7Jf?V;>G59st>Nb?p7p*^6;IUi1gL+f|mQH{h`ReiAKp)Llfj=FE$y z1Ks;+5)>~l_oW)9`JH3loa{cjdAxe7zK6WFVSpvYr<$!Kle+QV2}>x~?_a(n5m{cvmoJ%F zmpY#eT$QI5@4s8xffgiW zgP}ok%`17T3{P-)l)@yfPznQUj6}u6Vu6f|{0!qoj?~)}L3tTWnQ~h(N0Q4dEFMWB z@$FzZB@-Ahcp4@Y&kvOf>K?0qN112^R`cb!s7g1uEFEq=V-mpzL7n51+t>{dWI$*-FzqEa zTt#NlW-u9t*=b~S9NHg%`YO$czX_=Bno3VXQqo8gFeLKjz?oVvZm-Qk#}M1VX=r!{ z?p#_LCcXaoD(wvHnt=h(6=ih4M0Jt0B_|iUHfEt_o6_fTOvDnIIJcZ!?M?V9w|CV3 zZ?bSV_&m5rti;kQz8-K6*VaXLp(B1bp`bdz433tkk^F_TVFjI z$iWL3Mz-H8UNQ<1Yx4pV{H>y)Ap&55mudH%?9Ps7)CPKsUE%x;`|Ia-CurEkimQn! zND%YL{yKGt6_lky>imXXpR-})ya|p=N{99&%vkDCsp)o%#2o#|!vr%~;?h$?`X-(n z--mERr(f-t63TlWq;9T+-SEPe)}wu17Z%y*jvPox=!Hp zZ>?i_va_J4?!A$55i*xlxbd4k*C+F045X3G}`(?_5N)8Xrj7enU}9= zs-Avzt4HYMu~V)OLV4-16<=nFYkXdW02W7nRIR`nIG4VlY8y@swO2-06(T;{a2-_x zlH>+4Zx%e&6-VXk@s~{1_6Np%z5!z>sMG$GcNBi7ufK7uAIjaYoq4X-qrx%)I>1g$ zQy;}{f#`II=~X0E|TH8oOx$WISik_0t-o2iv6y?_nepo&XGwCOE5|mUhg_oD zetg)81cWr=a7U)eK7lPzS|tj!&M%*E1U;=6d~9|aLKaetksd}>h{#4=#t@Z&u6SJ%N^T~-N{|-KI}~l}oP833J$%lE6h+pemwdVk zBNtU{r7+Ne9RXTek$Yosmo-KDb28$GTg|jfc5`ytozmEiB5ox_lJuPC!Y@~@m~@cs z@*kktq)Fr%8Q%=e4vKt@^3?h}nQWoH4YRpDO3x7%S=S{Jq8po~y{*8C=h2(rz54s0 z#Q9Xm9({qiqFyBB1$oXnG@I_#Lv>RJp`_tm^T>N()3qf886tb+YR<9`ctHt-$*qvt zM5{if69a+Tyl$!aZ+SAVh<9m7%a_mehImlKSl*l)yyGnL6APK)oV9qEzHWNiyn<6v zI@~K#H!S8ud|m?m!hXi|6WVGbJV3(i?!ZBILS1O}dC$lpS3Z6nv9A1I<;IMD9jJy|g^X+M4pz~grH>QzZj83;t*X)!UGc`y^&Q2!C z$?#ybRYGecEg0NEtJ2Dff*vRfEpMzj+?9h{8gZeuG0c1m8v!t(n5Yol&Sb78z9R4>x_HzwSq zFF{Wlq%r^)&sl2|TU|m)isWDF= z=HjZZIPBkrJN;{2U0p3LEe>VYak3>Rpsr6#QucYJ z)tYnZEM|B{Vby`*+3vPa_2Emk#grdkHAdq)e!gsb-ki-|PyGQ7a{^yIHalVLWXU$ix z^xSe7OsS)P;_Au)`UA7V=`fh14F{w&RE!~MuFo|!EVsJgP^#1F_g4XFht&RXx51BU zE6mAK?6wgC-FZ{qi=Mo$+p91$W+*6<{|H3bB}GLS2*9aU31B!>^-jO|4an7u(s97P z{aEtO-N|l?&LsQI+6g$15Rrm12ooKCYV)Mj!(=d1qmN!dfzM8Bff$OB5!)sQyvTKSlBQ~w z)uc(8i>gTiBYG1ifgxvF$OTiP=WQg~KlLQ)@3-q#k6+04N z%LuEi3|J(qh{#%Bw8EX`)NdsMssetX6?kFDj-kflF_5$R*p3*i^qu3*?6 zZznG|RpaMZevU@5DX@9g^UME~9k2j~A<5z%Z@A@ci#8kZa4AXBhg=YE*d_5Q(ukfz zbvTMGkeP2(dv2i6Mz`aL69us5bWKYVJt1S?v>|DI&c~v}(VrH5mJiDQA1L4y%F8T= ztS$3_1MdK#i;d$LVO?karme|PNJTNcip-mp7ZD*Yi^vdhGU7Evk($-2B16)oewcJq z)9T#-4-yme!OB4uS8LShja`&9sxB%el{>2=t*N2WU(D>Ssqw~^8w%7APLP3JxT3l` z4`7C%+dXc|0|Qg>41n;KyvUoIt_Y%JVuHEOVejUO7TKJ;zeSr37{d@8gxiIIxRtZz zlAXZaFSb~8t`u?ulL(*^x!KvhAU=1eF2kZG)Es(5BH4hKYySxo$)%*;_%BP^>6YW% z4EnFYMVz>l{u>HzI#;?u5IP*dqRkMfH9(#g!8v~fs*&nsptN^ZI)T3Y4uu=5P1f;{ zZNHNMy~aoa9ulQ6lxYo-@#9oAsPUEp_%94|XS>vsrn*CHk{$8_;^ovKOEHz~lZUT; za0x0mIf4eP+4I?Kbj1$UFHTQCgw^ECmPbZLLd#qt5@~M3=M{0kdf%MW9$iQa$J<(1 zLR`Gt_MuXZkED9=kcB4>Jfz^)i2iZLS4b5a((jfGO4r# zO;gh5fn2UJ9IJ}R0FB*esvPS#=&-Ahh+yNmc3d7C%p~pR4{8o` z4;|dxKGI1m-x@o0>-EIX=|93p{8T@DzA6SnX0j48hZ5z%w!--1b9SGgd@n>MJVsZt zlM5Nt6$Uden;GeEbv3G#K~f3OnuFD+0?`vX2~b1`90iQsD!0*ft1%m=UhRdfLv$NX zj+t53^jMT*q-L0`%#T~A0A)dq<6uLJJ6Pk^LI^PL2A|MXxXmWJe)`RI+taJPbO_d^ zMc-Mp+j$CdVT}ckzvcT(t;}w#o*LKaC2qTTZ>BW)Z7i>sZ?4ZIu7}aT_>Cu#GFaRt zQOsh;K0>0$brYH@q;AglBtBz>+{S4mB+(OWrmcEK)jE}MTUaHPDqo$pMPj>=ULQuh zgYtiecj9dgjloDvNiJjRoSOmti?|n%(TU@h2rdWO(gr9TU?-CV^X_wrk(?q@j4xFA zTW)>`krjCmi78GyV_&ReGaFSW_roc1!D|Ewz|EBif7msJV7b6i#0R#nsUoDS^}SS? z%&edy!^HPuaLXnz{72wH@~$H+$=X@X=!?JOqnY@`j0SQ}p_i{6Ru4LvVV%w6blIE- z+U|A%b4z0olpM7Pmi+?vO{o5!>`)cCp}PxZ3-SBev>f=}H3ag$T=S~Y$rU|2#5w4| z({ho41;ojRUMcRoSO~~jI^$RA0WYl5TT|Q5n%rhMsMLa(KT!6tNwro&bCqvdvFN~G zi21!83rM(zk?WE-{{%1`8R;*T_VL(IF|6?@-}Jpff!d`sU5|V|cjH*h>&`;z5a-i> zusHg-Fd6yb>nsPXK)0j4P?<%p<&0V?iwO-Ii@B17LB@) ztoP#Lj4bF^ZPpI>zY1%EnJZozW2lC)WPT?S+sFm zz}h0h%;vogQU1QZIAD09+7i^$O0pRQ9AeYsU%*g3xjri;H>SD;2{zBrUs_025M<iD2?*Ai;x!oh2X3aMPwGNOm_cMQF_uHt=AJO+vs!Yo9%6gewVTyc7s z3FzZ<&|CmKJMkx-4&d6c zPF1!HHVk;f_H;<6KM9e&S*WaYYkskSb}~vxrL9n?G!OB`+k-uchQ!spjBX#|KnEog zTpBf&1%?%(1Zfk!4u-W*OT!1B>`A5$%@57z!fr?psF1hvCAVV86a9OVs||)t9Gy@y zC3?Ivgt^NEub%fD;7Ud+-BzIf9^QnSs4(hr)1%_;xuQ-}m1|LEZZN0b(Qy^3?sw6e zu=Tjxh&AG_qhprk0?Ln_Hu(+&no#ODXUH$#QkM^&Yd`h9{jB@(eMm;wj)mD@0mhY? zX=_KP=F$cW(15C^&@%}M?jbQq-c5n49_oh9RQ@9YMvIbRi((HgEaaGf+Z{<3kVRU9 zp=Nd%QZ>M@_&1KU-RwN_hP*0iC!MTzMc(={R0*Q%hpkmV8p1vgSj*PrTfxPH(yQ+( zpXMs|9!gt%(v~_V*@0LWZOL#&(>nPw}CzG z?vU*QyphG%zP!H%242G?8ZKyG4_sXljw3xn^3D zFbo?2h_WNvp0S7jPh2wjV+@&S=VNX-Ua};KpYr*GlcT3uSYY5w1~S{M`1g+*C!a}l zve)#|DDMFiQU~61!;Un$p*bJ6vJl35pWK;2M_#e>*|sAqk>_eQi|I}tquv}J4L!K| z8tSv~-WwIprJ0bRq?FnG8ZTl8&=XaAPF!;=L=w*fi$Ec&r{?x_Ff1$1kc zEUCS4#*1qx6dVk8V`kgwM0xhhX%yxTxsc#|git2Z}6`rho~CdF4mi(*8tgJo+h1x?Ml5}$Z zec%Xzeoh9BO?W&Tq!)KZuzLcT|LYFya>y#A!-}Eyn&8?pzrJlPcEpbs&1bOqu1n0G z5qemyt_kWWz3xD_v_k>9Dke7J=F_o>B#;JPhsUkL zDeBDh=Gx+jse>#&q`{CA2NkS&;H+wqdb?ysfSG8QKjow+h67#&O>L#NOHz14;@#w7 zTulDtlHvAAnI*ssE@y+cX370BB!(K29K0fT-4gN=mPo8wslXC8_wKExjr!>;AX0&w zk%>=#O}HZ#tweHlaBy&Py3&QBs6C|8<4Go9`vdLAt&v;j?haBy1#c=n^Z9UX2k29w zX`;#g`;B9iEdm4E&#H4iE6zEps~L=0^!DyA8c?n~M~>nT8S5?KL33AdhK{oy1Ok@1 zIZgMTs)({Rr~^SGE+H;S;-lrm;MYBUzkYt(FL?BiGdn|1?yPvwNs;~6prk(07O;Ia z9!Od!SG>QnRcU#4OY(4X2T0I8+4QA)&k-Sw-kRcRIHU`34smFu03_tZMC0c_V?I|@ zWP2z--29L%JCyRLd<3$aP>Bfx+alQ9EbP0Tm>L4(fhM3giAz6+83qLo=TV5uE*7R+ zemUv#6)sSfLtT|`JZVP_GsBZ=_+_Yb5tJX2w_5c(_{jtHZuE43X1bY5CIsolK$s!9JPpe@C=6RnsvW&mT?6e!<+ngo=MY3WAmIdiz--8Sj^V|%V|vkxEi=D>D^G$V z9W!X{P$C#Sr~-X)4&bb}8C5~d1?tUJMS>y;xV71Spcu2cX#}N`4CFPH1 z!OeGZ>0&Z6{bM)tZBreUB0%ESZ`)`yp1i0!bcW=e2temVYoWl&_ZFOt96|P?Nv>AfTgsPx?CRE+(iw$h< zZMn&*DofoiQ0B9W>9=c>u<3WuDXH0#((%SP6ma_x+7oqD2E8{Mumln?5w;s#*zIdw z!!rlwJ?OIWOeH;6cgmZx+m=8QsaoFAhKM>4LG z21>q3ykQ@;F1o-#J`If-n1kf8`l+@0mx>@@alh`8+@zzXEXp5QKo28M_IjYgFFt4- zZSgzW2?fQGzlv?Rhy%NY6+$W(fN7sTx8@MWN(bsAX+!39UB)--`%7{S=Af-%ooYb% zMoE}{?){;p(9sLw$D1tzWBeO8yb^iVf*P%7SgRx;=IY>OOpE9J1UW^h()B12YHa4> zjd#5_Ch(Hncn{hMLz9Ch0>V!%Xt!EmF@s>7mn6Nww8E$O~97ZNEJIEH3|*@QbcuvJy+H|DpwZU`=@-?Go-g3 z`+X&Bug?}$So2*X&9w9eFj9@o57~{RQm$_JxNfiA$g}-o!K`1;;gMv7fyqms#b;t& z8tKc1enu*OzM|M6vQtP>t69mlH*nf-E24N_OwlCktE4M%w}QH@?oW5rqwlYMpmEdT zmSI1w`Y}tfE(6`gVA3rF@fw(k<#Sx0x@|#*u!JNo%5KUxp|B4}e`US|M27RM0tbOv zjnT?`VCpyn<{(u#y^#9~W);NTU6VBXi$BCWowgKmF(&URm{wmIF*+=}yjk2d@q&f0o<>Lk$5{`O*QS{95L z`Op@SZV9De1X100eUZ(tshW%n!V91m($ZB>BtH_ueFeJ(A((&=JVMOQQq*~8x-vO) zfG}cfXv6U0>ua|1)V$fbb@#vqo(6dELsCMjpk52$yV;u4r)z8ix`&_JtjH?d>t7?b z#_@G+Th9=xt0mceK$%$@bkv$Z2Y$?$rnmP;WmdM-W8 z78UWrPeZOoOj~l~{LTd}Y?~*sW?n=Shat1n|?c5S6;C;2$}$^Ma7m6_se9Lzbo=1LwK_tetRr&YTa2Z}#d|CZVY1LCs&Orq~X zaneJ!(WcU+@3X*P;|ahtTYuO{p$x2mYM9c!g?H!NHzzi3E{4r0$+$a3`O@@skxyY{ z!WLB?>e`gqmk8;a_cyh?CSwM1X_G%Q4?=fapZgxgP2rKVlF%HMPsUp(Ksoq1%)%>z zL4xEY!}qo28|3p;#>;XG-!KLCI8&2yukWr)H6azhq5(FXByl;ldtin!7d;KPuTxmh z&amtH4}%1o0F~c{>!WdOsYfzprwG0v@6@J0K2?WoH{_FS@!_dld@6 zt6qk*&#NLi4o$!02y%?@w6HfO(}!vqD#2~wR>FukS08h58I6O8c)_YXGVS+d#~BCi zd{5?6=t8?RqD$w>m+~@m6Z<>S7aLltKG}2TK(d~3T>7@Jw9 zYkz%HuV`K%+l!sLI8CAiLj{e3r4Ak2rXp2@u$uDDYb>@~Eq((SpB)F;b(Oiu#EAtN zcFbcIaECk7{`+mIfX zUnJM}Cv_Ap=H=fY&;8zkGzA{{>c~>e(<$QItBq!r+7sOUd)N;?8<>;BKe?$cR32Lp z^CyDsw=8XKD$Z?WVIeGNod1Yin7~{yh)=Fal7EfYSIo^5A3D`;czJ1Ghsq56rL3nf zBp`d>r0w~6f6mS=x}HPHR1g_X)Nhw(vAy$7>eSw_2aF#|q#QaWwIxu5qn0B3 zm1f<~sEXV8I+Q!DS0sw(*D*mtD8e}Pjwz83s;>*Vdl(4$G}qb=Z;ncn^3T-t#G_$F!UR%i4da)yRR8ay(P{?N?hzp_Kfo`Br_AV z$1c2lHp=HSuWIw0Qekn596JTfQ!lF-HFZ@0Tz81f4&{tZYL4||PxF%-aBjo4L|E>ji zIsPTjN{sF2hS!X`u39N%VV2^m{XUGwnBe<*+81&&u>IEx{qPQDLh*GL_=nJG7O5b2 z*aVVlAWjU)F-Xe1lQ<2LHy&Tq_UsjO4Gi3gsgp%y4>q^Yw82>>Hk(JV z>lI!+3K8%zD&lvnqtjX6_Amt2Da^Cd5axL8A81fl##@xL&!R0 za-TTxijL3qyLg$py)ia0EC_<)q;T6~+p!i!hJ@A1`2bz-$o(TVD|9~MuiWAr#IUZ_ zgfJghZ~cwZoyL_)pV>}NTrabd(a9AUVdA}QCG+LWm7(w6G&{XDt05et1}GD^Bnj^` zX-2gCjr2%zf-C5{tvRrOUQm3Y@&LO*O-(&uK#N+IG|auSSZ#r)7NEXb5Z3ya`_n5rc^Vff#l&H1MB*T~Gr?#qva8)ipGeVuPu zK#}Z`8yXtRookEjQ^?P`7?uj1A|VeV*kJdj0;?~;1pA@&=rL0lml*VRM?^+oDJ_hO z>$08Z9-yq^IJ`9lm7cdw@Tpc@P>66jjfPwp)RBMCR!LUO2?&G6T_EUYdxn@9_gz~Y zYoIEjbNVKssoE_Bt=G}e+=!ss&kW*9%ter<*{J$0ki7yy-#7d36~{YT#}+fFyRmLh zdaY-S7 zoJT5^(sB_`YRG4q(8GLsN;sOD6omkiUIg*~!gY$P zAe{r_<{-q*I&WIUyMEdU>re)rvN3svKwv<^P`l`fp$0NOw(v~+;b#x*?81otjE-Jj zUT$t;iXv{;lB;fEG^2414GkO^(Dy8=_ejZ`Eh@TflXC(#!g^*?vHim50%$RT26W$* z!Io=a-bF?~Mc96i-cTAUL4<_Sa=k+q*UVMvy~zmp^R{kz@W3*3C6pj@`gS2nOy2CD^612_i-b%b{q#}?hfP5k4AkwE z$UJo2-T}Yrm9Jz3+ru*BoUgChE+bXGvy-(Nyk#mvX#CBa`+h^d*BL8Tz5Vr8mm_h- zZ8>DBqI0tH%6#6+`|XaU-uPLKQ4d2*Teba{_@=pc{zE_b|1kd5(+_1!|N2!M(?)#J z)%2zGDE>qp6Np9}!!Z2z$*Y~0RbY!BP!?sb^@4Ve5<5TE2lyMK&Z%rc?_a8z`RX>a zSCsDfvhA_$->8~1P1oW;*}4!O#m`;d5NO&vERo7)oPu&i-yiaoVTa!~3afAPU#Foc zWw>~PYX9bOM*Qh3VV{hC?w+ZSauho-C;`S3E$<~w9Ug`tCfe*HOsNXbp|ExF_V#Y; zxf^lNH3QC>#~}%oyJubChC@JpPl%ho!Hd}`Fk7SzyCL%i5;Igj9Y@9SuDrsp9M#>V|=^6 z|M9}>`)F8MgO3@NojCKmPVK~Vj_HF(M)_Ik9~_LO;y8X!mge3M33+F1OzW!I@9lMRJbm2g%9Sf`-uMug>qp2(KRDJ> zP_jj~l=MO6`y0VCFW(Oi4pxy*IL(Yj9Pa*@lcVg@lDc};9rB+G3|H^3m#L#nv(wYf z@t1`xtbXL}JtoT9u0wwLPQSRg*n^z!b0s{f!X_N;GQ@iNmBxn|`oA6>`JEM2ZGH6L ze>^U_Tlev=KR@l+?W_LlPyh3!|JjYye;*Xo|KYRog_kK2byMT+-5x{Ia*WG}n+2}* zO__I)sK?J>8JXQ7e{9La&_e_;y$`cR(lh-p*oR_QT0^@%Ts0(+!gFqNB}nHrjv!;Pif&eJLwo5@H{5_@7U$=tc9R_;76?mYMFa);>nj~mpz zVux?vyB3|K#ohPwr;tTQ!kNqF+`1*)D>Y}u9jEDPHXCZlgc|%{vDK2p-s$hxb0y~8 zcb1x1+$LUE#SFX8=BCPpEo6G4&hv~uqFGF*xT!P6n5^G`a(s7NDXfgax8rI(hpEv( zq1ndplg=!S>_TEau&)Ll^Tl#3UXCXsTH8P$4_~!00=qNG`1_sTvGTDXu26{uQJYj$ z!*PR|zy{+A7d&a+&WDg~NWAn~e&TdWR@NUb!>v}asf4@GZu)B&C0@oltNJ3ZdK-S2 zCcetF`-4Kd4u!+<$5#%y_Mpz^_Jnrk8KcA%!_%6Ek6xWhF`^ZWP-bWGm@5ci@fJ;H zMJKtAt@T46>D{}TIm@r**_gdny9~+O{rdxjAN|bqA(Z;ecBRT)drxtks$liAPN8Xw zOZ7@35X@67S!&7Br6caM;pc8FQ}4f;>4d%!5)uNBr@5~EFzXbnE`?^KugFo>Zt<1P zxl0G$-SF3O|BgX9UOFqA;Ovxdi#^C}jQ6_8SvPlPq0RpNwvNIQEP z=LU;sfv-s1qM*I$nwHUfQcZH{mEq3&PXcz;Ta#*@V<(@79QrW;XGKuNsxJpgMiRJ% zdJl)c`TO7`dU`sa+I!nQC7St(2r5yMA*lFOd2EQ(Y_(sp>Z29rzKW(bn6X?N^`kz$6MBRDbj5h61oZM~ zE`CBK%E8*XAiBj*)1u!0eIDYL1~iUb4SfFBqOZfEncyg>8F_HQE%L-T_0JC!W%vpd zEw3b#JzF9!HoQ!bXJc1>`{~J4hw(njX-T+21zK}uQ%M9onS?*TzlOLzBw{YkO5}<@;s1FlMO-wZ7m@!4`ZoF1UHV>({R@aF1gQ+-Jx;$>buBjfE1D=Tt|c z%yw58X&y_;UHrJ$@!0P-aN|nAuvFlyCEBSjadD|h%zutllXhDi{fa!&$B%IETTC6A zLYbguDZhra{n-*mVGl*K*R_jaJ+WRJ#nC({K{``ROCNCqi|yh>-PEn^WgAu5`%-AU zD4X7whN^J&Z3V^j=SvYSrgBp#vq$h0bo!3!y6vw6VC5kqBfn~V$R#AnSmo-~ZY3A2 zmy0B`+Saon+lu)w^#X=yooMTWE#MoG<_U{{VxRD*MRB|AI6+PyvQicQsMgc7e9VXjEmPUyp-!UtcU z0g;fgl?_rmre{b9rPgoq?+naC4lRaP}?1xL)j_WOdk+$4+5)_UeZ- zyYE!%uXk!OiJnPOxtpPCGy54Ie7WPTpqXM^Pqh~JeRXyFR?ZCNMDeu?EL-xebjnGR zVk(_x0y{HmK990>S66$~YVg$r*-*yVYF!~fFq)dlZj-UQ7C3;Zug?m3|CKcRr*n3X zo;7J_%LZdV-ILJ?hW+tE*;IPX`0-Z_mo8lbGxa5zyfX#n!&o=pZM93T)D{z`nTJYL z4u`7%JfE#q(kb5~`}I`zj0pM4&ra;VneKnRneRfu*B^oB_*&E{9q-V~nUUatd!t!0 zq&1KQUPEk%d}`0EKu4 z*!PMOTMR5df5f4U2T>7&(y)=P8PrXKe;xbJs-n^rK@`(k*Z#6{2`|*;jR@=Wmn}M! z%N~t=3)C-nY!MzseBttHWB+yTeO!M(rz4Hakj7z+r+M{$o#Uj~$NsmkT--em4ksVY2)OM1(PBye zoYnxoA*wA*bnIn4wTxtdFJN+Hv3K*_ms`+J4!-phdonp!^Qoj{eL6L)13iZ<$6*VA z!}1}j9|QZe-HmPR`rW1yW7K}Vz96^0fRVsu#Ta^vB{!oIZ)Q4K*a6=x4YgW)Rjb|b z!e=sMh%-6bMJ0CFk#n&q|4aXyM@t9O=dcA!k(p$C^8Kvkb)>o0#{>xHUyl&Cbmng(1|VW?7BO>Q?8ixM6@XwICYlrKo$(`HAn?qo z$)jH`1P=iyMY9#x#Ny+b^xDeG>Mk#Ge3D*Mh=;*T%$d(nNw#l1vqdSh+c7kk1xLXydO-;V*HwdS&y8w>E{fHxtSry-$?ktXa>m4r5`;h+ zPN~eZ)|bLfR+T-HGsb0p@Jc7_vRpW%PG8v!e&)n24|`{tu@DIxc2*j?hLNau8ktU% zzIP6PiQ89ciF$4BdEni*zb@Ag{=^ zU@`LIqH20+UNsyO9rb-*ZFlR|E%oueH+5=ZArXiExsW})h?SV`?mBeU4FI1~tDHG< z{Mt*61n=qVO98r$Vv3Fzwz>2u0M{kQA_YFw_-2xnhjT0LM!+$i#vuxS^v{2pg>}PU zfcl;d)5@<5U2LfSNO9bfqCe4V_;LMFk>STT*z-N-3YwVRr&Ell_8yP;x4kmmg*noH zJ;|cK`X&SDuc(z(<~G$?%r4ebBmX<)7+u!b*l3aDW=_VzGt6LXd}dZCUcUEL>g-6A z*!b&{_xWsKT!wUdb9GCfRqnqUz9&yYEIY^1ZXc_}-*_&#lkgZol{G~S0;*i=ICerx zI%=1FK6z#X0!Y)V2F(BL8(-SZ^Y&ATF6@ylM9oA9J(xME!&Bh1z#atAc|s8^XAFc5 z!%R`714a~caoM~j~EeW>n&YBv1mk56Bns0BcL z?;-v3ngZ*A!l*XF+N@^yCJcyBDf0wOxIfTv51NMG znC?hFXt_tz1V&{KJEG*(Fchpl|Fu1+sJGpbdtq-*?g}k2@)0n~-qp3@ ztC%ZnwmET?^P>c6g72S3>aKgC8N_5dU@i=cKY#vQoORp68wePiTri7f%SsC^rh?32 z7Hen-mY8L{J;8ehMbTW%j7rL}9;w_apUoR8cd}|N_M@aGRn!nFXfpO4=lOFCwMF&M z`vw0R@Z3wrqp6FUpjl;UrIFInQtoKE!lEz99M%_$4XEDk%}??nZB?Jz7rr+Q{R9aQ zN~_m$g*@hTvD?wc`@)mT_g*Fa)6faPKZ9HQUcR1VM?;r78V_Mk%E3#2l;k0Jx8R+Wj*1A~E60Sl7>x;i*3|ADv^!X6IZH##2r#_*0Nt2eL zpRJisn(`q{t-3JsRxZ}vRTWD!<%Bc$zpfxdA69T)Wp@RJeF`gAHyLkEQ!EeY6q&cD z#Tb+W-V9aU$0`_=Bm^FV*pp29jIq0*=h$@%VFQ$+PhI`+-@MXpemF)b83k&e-o6;8 z!yb8k-Q5umZf0hzM~AW7eWmOGQ6bhwe)68Eq$qIy31Uycoh89(OLNmUGsBhE5a%I0 z$}0SM!B}}Vgi?S@y1l)Y+P#}nMv_botZaQgx0xPbEo=Lbi+diwnbQnjrOn`Mm_M$sM zd2dv3_uYFE&U0_Yo&LaC8uY?xRxiH+j-p1=E)GQ-4m)$^KRjYoQdMjP#lbMJdf9pU z73q3Oq}V^&mf7`!_q{E=Em!A%5FI zb$C*D&n4zC83@%NQc#Js$p+5`z|9`uNt(hDR{sCylHG^HbRDwiq%5VFpXBo;)&qAk zOCQea%1ODea{SbdQr6eUd<#5Do~s^OJ?V*>thvFsn`!#C7Y940gj_ z8+7@(TYPQbzk-m<(tB?k!?%DfIhcfOaY@GxsBQohiYtzVVBZCbLLX1Y z#KVhT8gDXmpGo8F=hgW<4Y3E8J>2nbOC>cx66*sN2yFuoOL`;6X#ed>zuuGPa{*E8 z0=}P|2H^uK{*HS7`oNOiU=*rN>I^mR-E+i`Q~?4fYe3Y!Uu>A@D#dRujfY8ZKddp?bDJZvXaRLw z>z~d?Yl?d}Yzb=(RYkS7jehk5&<8H;+8BiS1n|0yqMuloBwBaDew${Vp7xkB>U>7g zo1|i^eu#S0X7Hkp^Mh+~R(WotPboviCh1)mQHQgOdYMo`=l*H`XRUX6rHrvdsW*Fp z5roLZVDS?YWJg?7S~mpQH5s4S?1aF|86hyr#vemCNrG6W0xs^bJ&Gf#<1WyQN&mD2IV(}S zR8crOxDHD%?)b132M@T7Sbd)z2ygH;p9%{L;Wceh+O?U*=$DW$&qG)WJX+xOs$1|@ zQ?64u3Inl71Z=)qGGuFIWdpudLsNf^n!HHOta$Xcb>atjW%vH$m7zIzUl|&FoX9bt zM5EdaeTZv2J~~p&VHrDFKbnAKc%NkA1g@Mp44?cR;N#)m=~#AhtD>6V0eN(DcTpHX zHq`{tg52Wz0O}gpQGj@N3q4WdMIEd%l~`xw=RbsZ0pyuhdPnFF_+8YV5? z**sIcM$9PbxcTH0EHkQ&^61%nnWd3XE^HY8Y&bVeSZ{(KwRE%C97M!1h1tu%(r~PA^`!(b$2n|0>6FsUEPcBR z|1Zdea{tst?c=WOUP%GM$#P=>L*Ro4`3Y8KJaq5XfP-J)s0jYYQK{X%bLb2s+I03Py^YTdF(9*9RG+LW57PC(&ndQrNKGh$a9jWqwcvIZ3R#7b*(g^80=5=p0 z4WK2cvwH${Rq=ll{(g8oof1&ubREuC6xdvi&#sc*O-wEy^qiI&=wc=V7i<#SRO5wn z!6zg)=T|Pb{>3T9RIjEXk@clr!f_qk=0eRUtNuJ2uZwgLz7@i*8vn z=KBz5bRV&Jgnb2Wd`fo=eR*F$#G9r0Xg$9v&DI5pR%yT<)bsy3fvzd8lX za$xZi<1C-oj1tm{Ifc3^uumKAY{7C4d%<54WHJ`wTvNfV@0U9P9u(x#>4DSk;G`&|(V7{6gauIC8;0J0K4zFFp->Gc zwcz~Uh%&kocq;Q<)Kogf?HA)kRA+oY?Z1yu`^Q)O)gLPT6-hLPu_QapOKl9VbV%U! z99k}70O@np#a*!?5wT<<#s#ZV<_tt<6SIf4kwg1;aNVTl3t=B5$-01E;lepW$R5fh zQKA&%{NlN(U>QVdaGhKL&)HO&!#6UAqr!7*6+2tsaNXsFj75#XPpk$cuZF;w=u~c^ zz8=h3K>axPAD6XO5mGZKnv>VO_gI#4oCOQh0a`@vad(00va5}2}8Br1T2kq@#}xIs9ClB7+DQAn;OMs^TSfM=LY)bEoG zreA8{^Ik%-SVQh#;ct_?w-J1_U4IeIHw0!YrJ0$Tn+RL?I?R(T|0aca!2`ukU{>$8 zmhNR0`3e!H`0alN&8L--nEWdD>1-sZ$AxT)+N##pMzwIt^oav^ixquQom<})K>3_VS2YsOFn@A*NWs}iylEg`}S1M#@udI+{XQhmkY>^S! z?&n+Qe81;=|Ng!2$NkTJ{_G^5&+C1?uIqU{pU>-h7cWm1Z>M0;dSr@d?bW^!qy9*_ zC>ekd#qFZl^cyd^Ns!Y3oTsk6x$h;nZNy?ToA|V|8wjf79+ydMsm>r=tNsT+Y}%-M zxvjjrCa@r_7}xTW#NvS1pFLm>jcOipE2|cvnn!{!mRxOa2Q~tZUUdfrRtG}=077rWduEV;g@U+Nli zsGz64vlFApIpv_F(Mm-u8qAHhA?}-m7YBlXxOGc^^w%d$`fV{ikiNf;5Ac9Ej_SzjM7lG#wuU z6d3`ap{5%RJ z_(@)7$KjP)|NQr~@PGd2{}X1D|NkFk`{#5?{$KF&{C{@5FE2nBCW+5PgmxNux)THX z!_5ZhfFUn@_FP|e7F+vD_8Ez0ZFSknS&=w{LszXhu=44yG(1eCIVesL9cXzxP#7SE zQHV{wraUUUdn1gW)j%{*kz*7>e^OVsPh3DWLJoGkqxRma zVe~{&nDxEYa{kkEg~{^L!bRQ} zkFWan6B_E<{WpU7nMv+%h5d+Hkv{@Xixc`QATf|nxOMYOP>XN#K=l=y$Zf;kq#4fz zAI}lovgv&bynp3u9N*{bc7&j$2zm1X4d={GRWE!F&d>N9aY@4#(%y$7OZU^_E?P+W z7A4EaZ~X2?$wfj8QY1OVq3~1eB>E}oBYbv44FsBjq$F44zh3~f9ot13@Fd@moVdO# zeZ2N&D{+dOhh7{ZAvyCJPkwJO2#rBB+XwlL-=Ur{J;vdQi;B_5MAn&=%L`m6m2 zWeGKxk14>({={fQv~W&YS=ova@pt31koqI@S3$v!jBNeGu`pRnOIGIHBTwufO&}z6 zk~{rNM4@cGz#|T{077JBL{Bve%ImR>Ul!ll)6?@|LlaZH!+;;R`RB)vf7=;Ha@V>k zTG$7yJ$xV{B7xL8Iyxpz(Gf$W=%t`O{{n=Gij3UnD?PJ54pN?d<3s)Z1)d6k&LNT8{?c~_bH?Q`d<0B6?F&|ZQjQT>1>V!N4z1p~el{+MVz8En}e|NLc0 zaHtGcm9$4$h<|l2?HQy%5_&%vD{xWKF|z5>AqhOi%*eOL=vpO&mU_P_t|C3@0BmBhs%<0+YfHXbhN zxrQD=7!sM|dVE>g8X&40Fu&cnetJ?8NNeF0L*0`WA0L@aynlAC{us*{id_;WAVlt& zk{pr#Ka^L~J&bx@!`qxx1}$`L#^S~UO z2>N%ZjqD}@^FA0MbZt)f>>zxki+RdMUqnH_Rq;xjX$NH@|39%zzY)uDI1uD!@a2nU zze1pb=trzaYa=soaFXdI`%!L`sU6`_4{)>ioo<|Mlm&P;J$27}1 zloX1fGhF%|W&eaUJrUB%$P2MhXHifSJU@Y6=;-Ouiww3^*3~`e`|t0t;~uU{Wjk6e z;tdR|H(>_RYud9vJvG%&`rnys>p28Wg$Qr}xY)2YA;J~&ZQ9vvrZ$vy;}w-8j7=Mn zb=7`!WGl(j`yMObm?h^w8ky;5qPWu;xZQ%7kx<7*cI6dynIhd$69rMHNj)S{WK*;e z1-65AaFbd06y8FY3(f(om&jOB90elflE+LC)XNn#j9QVw*{!Xu{NTEvR1JB<7y<6) z;DG}=VFqYT2y?)$8CsP-8Q?qwFBvVDGa7|ZAa&$mjLw5!E7mQrB9H|7Z4m&&4=X-< znDvpEmv)1nB{Djg2Z+ffi$hTaj>$9c0G@jVR0Zr5<*K!bG`+1&u(#GB&@r5+&4lXyOp zh2P-!SZoRK$c>v-`U+aYd2uj|_>HGNI~!Gak*42XgInZXjl_HwzB8_|3c_RtG9?UV zG3Tb>0(4uP>D0e%i4+FYMN@0S1*~DvmHb3BQ1pELI4SeL44#OxicxaBZ(*cWh)YNq z#5eI6O$Z~pT~KC3MFD2?tG)*2e)VIGgd=FUCvK4Sqirf-EJPv^5&2ZkF+V5YUNey7 zmbU5p@HGRvu<|6&`&s-F=RC=SAuIA9PR{s)A{zJZMX z>ccGIJoP2}KoZ&Uvo%_^RvfgCs_;${58H#!#_tE$<(pFn{NaUK*bpnZe#vvGjc}4c zg5WkNbHf3LgoNNQ(qU%)$ zvs`-8^P$<|3Z8_^+kmAL5X=Z6h+sv)GTd9K3-Garx--|)v&;s zEK1Re(2<}gZF%1C4Md*l%EEMnWY#Etc%{+WqYVkEL}{|&h}zRQ zQLf+y7|dWH4g0!=jMhwa)wcAG4_w9fy$)ya4G_As8r^)W5CI|>wFsk9m<8ty3H1Fm79cme@5`Enw~e*R;#m)7weVj;`G>v|#I?E39Wk~1XFU7P9d z@T)x`k3+Os{F+GyrBr3=EB*YHB{X2O@jae%sRjuvK|g&HTrxmn(H=EvT6Q6*6x@y> zr=Rnu;LYfR{l&Yqncu3XF#jZh@|Mdz@S2^`AA1J{q;#!{*%~YKbakU<<_KQ}V&ArD z9lM|Ob4-+^9$VKVoiv~R<{vEpTOJB>A=*;_g9l;8MT|RTLT1AwT%t#qUM{i)Raio! zCT_6Q6IKY90R*R{n{QEjyKk#=?y-Hogq>{QU7+xd(}tCI2^NYmM=M|9J;=9=$ z`|&66sOcmHx9(9OqdUbT>>DONFcV|0?3N*>?+fg&)G*( zCJU;rwKYlI-DPj@;~kwK+<-J4v1&l9K^iXcEL$1m8Mf07b{RTe#>8I5C;W=}=7H;l zu|d^h6qjW$mM`LpSsoWKdh0K!tCE!6@sfXK?>Uk37+_o^otWmbzpAf6RlSYA`1$f+ z1i$dxy0I763?050YGkY2!hxDe_yu1VyaDH<{H#72N&Piz%DJF!+v11!r90RL*`>iI z#sQ4KSnON^rlt|{KuMtTm40G9UHZd4BYk1CJok}h)d+%~aB@XUE&;_5Yo6e)sk6J? z#u-Gljb!tO>0fS}cF4M%^oM@|#s8H1H9~Q@_pH^x**j`xMUj` z9IesErWbtHNn*ISdp|!AFGH*RD4D^+SzYVg<`&REgqhK?t=`frU(87*@=si2*I2r8 za2)WzDM-x_KI;h2ndNTaIg~xEN4t%(v`{KHM3rOpv+`^y(KQVX-=wE)8V!8*SV5mB zNIWUWna{9M5^zoIN5MA7TtZnV($U%|45H(psMdKcvRIpmn;Y}PjdeX&QV=$1WR$^J zttBb5*n2JIcxI5`n^-66>gw`e7$a^Ss%bO_s7g8r7KAXW(%(Khdsw9LzS@E1^|mIB z++Ft4KHg$@`127f#0SP+)tL3Q2r(C1siE(pCC04v&WaBwYa&%YO%5CL1yogr-XY*e zqXu<~MS@B`^ELY60_fk&0w#)5`))cQgO@Dy`;j(eZmk=m=M0K^;N9`nN4r+G8u<8B zBQx#1ls|0imuB@BPx;F(4djbu96h2Uq~NkED}aKT?ZI$y->OxlSVqxMq?;FryZmBK zRSzn5PNZ&g&IKsLZ7YTvn8jvmg#w~zV5azj~Ql3RMTMHO|muZ+mFS~d;PO5 z=@E#IOK+OQW*hLfSo+=?bPhz}{U~@X>m$5|29NsY-q~DBLyq`uO!UDvp z)&*~}_567w5M?g;&nGQWsfy0W`1 zUPD)R8I&7)s@r^6?HesICP`3K{0$u4JG*Q@%S7~u``3I!vv{5FF(Gr=Ho3*7FF=R7 z;=fy$oJni}ez|7JW?PAU4^o2h-8>6vmF38-s@LcW3RZ7_=cjIHnL&x7K3cWD5U?&! zYd7;^$>-_O> zBvW~BggvbUfEj6@Fzi&dvvLul^RDp?H3K6aY0GT0tI=FTx9D+h5uW!|B+I$yY2FYN z=34Kb>(2fT3&gPo5yz@Q9Bb3>V{PTtVZpHyevw$xWjI`IDLlF@3-XG$pC}r5>^9?x z2B`Z%4=f@-%bjA+SD79OEF6lw+12}iLF`wL^?EKEi$f&mrKQyD7A+P&*G=8s1Q~oq z+OWHj{Qo@@<$b6h%$AUv=+A2>O5aSe_tlE`p~5&4MCJ z5CC~9jFrwSa1#W@uEb~FKDuzPcwRY80CF zjY5+vdZ?yfvK?6ar)A7&uYH@6rHs|DuX*^$#0h(sY1l z^k_{ii6(2}?ngd*EqA zvEc70*7MnIMcnzB&w-zkld)OO^qu4IR-4=gT=Jy-Z?9#6Qk87%>S-`Q+38#CYZQ1wi`mynGG&}n73z&dF{vho+Xo$S}@{F9l7TeRGG2XBa zb5)*LOodK?2A5WB_PKt5^fe-*A4p$~_Rz%J*S5XqJ>a{C@6~VtK_)+l{P-E6^yu8Z zz@b6hFo1 zME8fU>yCa9t{k8)n27fIz5$Jl_K}uL%LY`-UpQ908n_`maFlhmp!Jf!IN0$0EK|>R zvzi{w@@r*iK%+?XvXKP@4+Y=iVjX7&BEkei1k=u9f%0#@O@p@P)-PEghE~v=vzS5e zo%rOLvffPSLAAP=sQLoo9~M(W^dYFB$Q!^0K+wYt5q1zSe~x$Z1f7N-x#@7NJi|^I zb+3CZ@(eFYHJ2&~W<6r%zN5N&$MG;de&iMO%tS$h^^B<*Z4VkLLLeh7SEvX<7e&~s z-jq#w^B5P~J@?2h0b<<0rthMp)CdJx0QCfia!N=jZ*mM2AY^sIOhu<>BgG=6T6cJ2 z_cGT__|vEVvKGUiV}yo~{CsXZWB3AEX$&S`VE7SW2rYIP53TaOz9cmYunKbpK3(}r zeK}H&9WZ7376&mVYYPiKOb0>N>%|L?6>Tq;n?c(9j?&u)A2G1^2XUeyFfdq0Ceedh zH0r7OvV)XPPx*BzrDK)pZ$we4U>A<1+Jgj0Ocx(`bPn+IA?SmS&d!1-yIA)5#)vw> z0c0}N5J9v7@Hz{8+Tz1tD?e`MMHcQd{Zj5ZKa1QiqrX0QTr5wW6{Cpz%zGeY58w0Q z0+3zizqY=BH}qRgKrH(I&&wwR<5hakpx3h@C-*DIR9JwX>HhMriuCGePg^2N13{|k!PTG1;V+lOtwX10WS ze(zT6*3sSMacG;YyZ^ESr62~t9U&HY3yr}3{8jX?VnKUMnaw7}8)HOIRb5yuz0NOn zFa#Oqs#QHJgeApE7Z9X9$N>|wsV`p=?q`k(jR^^X)3kmdFTMwOt{4@I3J1zJL<)^R zI!AGyIXyd@zdP!SiZD_T7-h5I+OImh6PSBm;*@?;n%}(1jM<3>ClxS?n9>r6IIdG< zdtF16wN>r{rXh?!Cjr?IpcxLUB~x%RjW#E5GJkrpiU7zxn1k62eDs^AhK>362h`wp zMb&!HMU!kYGj66W9(*eN zUQ07*;s|R8esfZh=T&Db25rL8yN|&GY5t3y2T*(wQfT1$(T051;@$>7wd|vUM3gAW znoF|!xiHASG88<^d`-I9TJl#>bHYw7P0e56sSz8jLCTm^tEMv$Lm;-Y3cD>#WiJ^n z@k{EwlSP)E4WDha4bgqHu%=UZGhFx*gwlZ5s5wPGK`j}+TT54S?ZeX)WW`mw zH2D@XHIoZd_`eVtS2?|xr6^iy7MU-vJ)IW+I+Ir zBPac3e+`^G+exXCb|C%1bii?rEi#)D)+gqOVHBTmvnKjqM91C}$%5g!K8=Q0xHl%& zT=IR~kyY{W!#gBD;_>A#Pc?x%yHWhLMI5{n38N?2iL1dbRU_+52J4*euE<(9Psvx@ z_&`j-=0CrJlqzg#s&WnesBRFit2p>6juzBh6Gu)NJxaufHYpB&;-u&Ll#gV?;SOi9&y!3|na5A)$emSj zkO#VAcv*e9zhVOCp-8n7A9S&9{^j6jphNUXu`Fv4%Y)Tlk1%nAXfXZ7YEKLpGGzBc z&q+>v61iwq%i&xs_YL76eXc3}!^wf?Ar27yv#%p_pDasBy>)fa4|Vvs(G z{&?vfKpZlt(=>m;;Fat+A(rhcS)m;sO~<~v54bQ`^_7V$O+|Ny@6yeGK6hAldSxEm znoi{I99NbliB_>cxR4&{c@Gsxgn0RV;L9&K(yPXGFNwjVnx5up7w>`Ipl;JEa?)Am zxg2jLLz8w>ljedJ7WC~UFu^tpb904t?H@*9iG<^0UeE~yrLLt>EaO(DT`4~4a||SY zRM{=DZk|%sI5&cX`nxllz1KnvKaIB44`^zN*j0_d5AONm(>(AP(YP~UbPb?5;(PdVF3HCO>(9V%t>vfsgY zcI4UCvpbIkpXr)hvl>_*4&3ueIHETuB1T}@^|P0F&Tw?J%Z~^FK*zgxoqqF4W9X)Iw_xm9TK9nH>H{2rA_$(8Do+nlVB$TjN3`1xnhX-ljL6My&N zL)w*{Or^XRKATc9l=(U5IuDS~%+3P(q-I}lzfo+`c;J?XEaWhFjWN)&As75(Lk z&Wm3qAUH`Qj|O|86n4K` zSfoY1Rf%|3^)=~o;=@C+Qh#n+)EYjr{Obpu<^tLg&4`e?sgc$MzfQRz)y{kD{q;&c zJmo8@kL=9NQ|jCr#0-C85S=ZLTzpkU-sw(gmhSt2x-EToHf?d^N_zVADby{mBlu5D zN3%QgT)w}1wtunuTSv$JqW1O?h#`Mbl~>afpp{7@7G@m1ju6q~@2^(p2`Nfq=*Q9h zMro(DS^O2KO%&<5kNo(e@oIL*=)(h@W@|=)NpbHr(2A0J7A_?!`uQ_U>X*b>Pr>I` z)3yuC+YHzXz#^v9N?re0^Y*QNk!^L`7>%ZumR6aYixef@2|eYAkndZzk=!9o(piFv zOt#m+F6)zpwzl@$c4=93lEtobDXL@e6I>Y+J=byn{{6jrjG3$JJd8{F@5%K6azVZK z)hMQQNkfVETd0#sejXPG+t}fcUtrnh$cY3KB`bUH>Yot;H@1of|D$jy&1?5&RqiBDJ|O z9iKv#&TRf2?i#755#BTa7hBwUDa0J(DXZwKe`*@I=VfLp2W4XovW?Bu&(XG0iOBob z4b-FWpH+dK8NRZ1GKxUUUhTob)ERaseL*gRD--CqoWw*o)&bPVStN*_ssG5mpsA+T z4hyAQL%d=HKS*Y33mXuUsAA%=gK!ex(-(A=x9azgDy`WK!(x@mU6;pH!KQ-V3j!5lnJL ztJu!KWGQ*`16M$P!Om`l!E;3%+*+AucxyDti+fL$=^rk8sKY=!u|7USYLdNd9BN62 zK0j^uxwhp43NDoIEeXVL4qbXEIR`c4aQN9(Ggi!e4Qg}zEIaQu@-x>(G zS#joR-RtTa9|vuLH5D=|fa*BaQwFpfdlsP_ZcT z!a}EXsyAL;8{?~wuX>Ndw2LfuQ~d)j88Z#d;9TcH*q6snLc8l^T2aFFqyvor4h`X{p6|Zj8V6j=OA^zy^3l^g2 z(Ek3?Ye#D6Mq!5>;Mg3?scUWq;4kfthq1PHVi>oCNqk|#wg@QkS+MK!L;;dZ8u|rH z%@YUPzY2OnBVy0Lo|b}mxrozbG@nplQ$vIRBZZIZ7`A<+)zXxXzwwJ)!8HDX(Cay$ z)>dXO^^IG1uq@$E-1RbZMld3yp4w!tXh4O zM(f{Csu9*ym4tYtpT#HZ4%|Aq$_lEB*VyM8Xt_Z{^RTfgD-aWh{olTcr$+Esl%5Fq z4$T+kRv{T*mk=)m*^}hqhQP3nUBx!2F7H#)pd>HP%$awj_@27&>pMM7D+4PW>4j(U ziHXaPi#%y)X~D}+Ltyo?{O-66Pr7(a`ib66I&ZBi%ImPRCBr~6-IhvHA{V_mq?w!Q zp-O(|^3|7(b0#!W^X(|p?>%I>@ioRYWjg%}=?A>^hpDqR2EPv8kylC_Y;5mpYg^)} zd9+TyZD4s+r6@Z?VU-{npj@jaN4~n%LXMJ=ky}f`5#?wsN7XgT1und86bwl}(+38O z=VYQq927>Sra>s*JZ&}uUZmw%Ecm5es_IQaCa+0Ic(;rjY}*W5Kx^`{Ls3x?lAwr} z=4OcN1n_UmFT~1#ID8m|WQb`knQ44RZ+ARNS8IN()c)+;_UXYra~$d^#|k|-JnB~* z`omNn((|274Wanc%L`7{XTcmEx(UaRO6@Ws(=2aGvCG-X>TkXfT&`4o_KOamVeb9J zOy{M~mRa~W#4zMsHY{+fUs`Gmb237)_A?+KKTSBo$#WshJbRxd*bTgl*S+>xd&m@| zn*QY&;fe=c*hc!3&rb4ynDZ3u0B^bpYWu{Arncz6(^)6_&WUBw;~B+sA9P9UML${O zqcUDd%@!0k*3G+gvfC=pT(nz|Q6w^2-Rb$Kw*_7;?~r%}wXL|>*pfgQDJ0{Kv}JT( z8B^be?TPF{$;9^@z{yw3?VE8R2G2%`WjEGQnY@Ns=*-i-(G)bb_4NWT zSZsw|e*U}Hq_0-_Vz`$o;buztN{utBF^M&h*rcZ!<9|J>A{CTPb zHKEJ8(HDnNrH_340$FG7g~_f-$ZQGmu#j-f(P;d&l|7t8uklP!Q~Lcw4^lKUUaGU7 zjG6$IabSq$D)Lxe9VSTrR5i!o?$(=3w};U_|K!`A*e2{UW1OH?-1|9BZV$5`8@r&O z+De^RMg34aRobIxs<#8>}12)>vC7YMAUqQ^^xcU%;N4;#eCFLe&&Qh`Jl&-&z?I6JH?li z4rtRkW(z)9fOJe$ZH3=EPJ%fLKKqNQX={QmCUE^WB#n$?d3kb#r%ws%Cz& zz;ny4ao}jg4ITY;!&C;1GiH#-~6cvA# z?x@5({GkilE2)@7jU3)jNr}NlyM*@W=;($9#l8zI z1CJ~_BtBUbcce^M1lf&@Fs4pQQ$4gsZ9gWD??&ue;u4mtN#QfO_^!KFi0>j&X_m_U#jFNGFo=c@*RX zkC;tcNM0Wc$F{m1hb|^wew6ZS_4aV{AhQolG@#Jqo$-htaWGra7v+IznX%gBG;VvjQNhx zX|xy=7rOeMW@b)-Sf}Yz$nBm$DV&>pn1(1lUrf3__Ax7t>C^mp=cPxHp`k;!DgOt> z*itZ-8g;~&=1-?LnvAz62RZ+VbvTpIZE4cdkFz5!3zJ%epO^ccmN_D(kd{e)uxG{bh?lYe&hXP@7*{SMKnsrRe)Ew%5*)TID<+EC*0&^FB3hHQ8&!`h& zH(?I*BF8eI{_AwEi^Fc5?UZPZ3;qx@CgF^{~ zYU$d`s;^pk<{=yT*ZxZODsfivDQ<%i`?fq}!D!k0;vJ)eGa0z3-;!8i1@p;|nXpL` zZli)PP9m$$aP}XT7k6983|PEr`|ic1`CzBwj>-wHZ|_?~X+Qg#9PI0|$cObXvE34+ zn>w-=v&TZkk2c@jYryDfqkmzn#`s1;@PNHYhuHc_m;wu8A;t8{tY>yl zpujm5|K)7tqQx!gr+yw30$#<1@6PmGRea$*j)fraRjU#UA*~B zm&S1~R(9m-FU$4Uz|K-I+p%5iU`bI;c)(-8QyWIw(ey-IS6TUKu=(TL(SKL1)r+Z3 zjr6#i#2k*iJP;Az3+Wu03uqt?7FWuD2@COj4E#h_1Fg^7*p4sqMRb z^H_`gUh@ve{MwWDKfQk!Cqx7bi)^Fl3(PjJKv20WpJs#o$#DACdqzw(9wVsW~ z6^2$p<9VeN5W_S?ozkH4331iMHm*7~UOz@{Z8M%;aNshP@BLVv52H-_locYX7ZY}=J`m&14r){tu9 zqf7(r`TF%MLSATQ(7?nm6f6RnDtsRqmy6JO=5+QcUAjaUKPLV|y5#IIc4N8M>P?xP zNO%6F>W~WQ`4SJZo?I#BB%ecMDx3+^lZe+7%)%P%S9wZcTlW zO1N$c^l@w2N&NZvZtF{YplZT>`p-^-v1#xoqkD4@v`j~Mr2H{qVeLmcsJLIQmNH3D zmX{orl$1Pn>`mB8USyUbf)=o(v#%q1!K1_@mD2f5O5h>V%igJdi|!(k^@DYI<4Qw= z7!a+FP8TK+enFV9>^?a?r(6}zt@9=|edH8B^by4(+d;7D->aRftqo~;Z4cZ2;|1U{ zc(!x8FX$!>IQlK3qCvR+S zc8bCasI{4AJO5po1S;OQ@czyOw8^>!MCUJR(m)?jmUj(Vi&KMowHS}Q)OAilK_SJU zyo@?A7hs@m*Xw_Qfnk7wO`lbeg(l!>w~4~WKexm-_8s2z3@jUX+94yJdQ!#Nx$s`dbPHNB(&TCbuWxeyB!;GiQB$x-7tWvmgoShP z1r}I*0^RaFSM1JyoU*E_>el2}FSS)uHMnopBuMwLj*Ca`>+2y}Ql5w~PR*vUjB}-x zm6cF@Pl<}^W-5U`K?~=VNG11*7VmE)iOqwL_mYtGZ;!M*+09+hb4^jn_^WM^V)488cvLG_NTV8C zmDE-m`8`-Yj+gF#;i`LjgYqC}z{>>J@f-p4XaRIU2g8;46$&0Mc0t4qzpe&4Zq|#@ zd*eUDU9m*N$jCU+OIK|dUl+TC%MGg6TU!AZe&33HZF zrPJ2`oZn*#tLtLug#SK2!-8&{etPh$Ti;|8jwQAgVM=@>!6HDGvFp@z{Hn z!>%ARFg%>0lUHZiic=3R8;p7XUfELMCn-T)xbSWeP1xVYA)l^Sl%3pku<^{OxVy=h zd2ZIXIW|-g<_Y_!SDghEtuk#kn7ji!C>Tz^#}iiw;UKID&`+kE9K?+BO@$rCf)A;8 z9u#&}q$ejMYb*Ayw(K{u=BnO&n3fmA(a3bZ1uheLomeP0d0YEGXH;Om>jn4F;NYm{ zOV|J8$W7J1Bds4q13CtNbY|%sE~BjpJE>T5flXm$2Qk!-Mi@|yMR>Uh4U_FA8Z=Dy zHaCY1{t7v0Z7y89{w2jV1eCW8<6?4Ryr8*DGYF0+U%9qb1yR9vz^e zxvr%Yto1vh^764*kQmPeEdysm%gN!#VNnj(HabpKgxo9zoorP^#+Qz1yp( zHGS5@V-3t`2W%jB@7~4e?eci_`)btZ_`QcvInHk{;D3V3u|`ymoVddAm&L)45v-|# z%?@bZfx&T+Yxkt8B|o>1*L`K5tU8KQDo||&!S^EAc+>AgdEggCLNdb5%E~G(ekD^1 zBn5e@KbNBOAKyfRqKjLl-|p4Z%l~A7a(b^rdS~FBGgG+0s4oui({!2WqS+>ANi5)2ATP%Wb1q;+)lfBR54O9m|0>r@!bYk`qA#zI!LX z%1`&5GRXe)e}lw3X2c+bQ}fA5%Pwq0fjIJf;_fo0e4!S`VWA!TA}zeSJbR5i=yn*g zF#ax}XA(%hvvFWLCPQDm;5?v!hR%d7Hc47ZYKp|+*_C%UL%4mZ#+MM!B<>nsWH-h5 z-tU>LACv7+X>o1I55XO4E z=3N34SzzliOtBu!W1t@tJ$PhN1d59TcklQw#hqoQXMDI`I(qM-`T3HhWXR?;(l(dJ zj$=p?NP8Qtv@+`7V<3x!@hC;oA2FQ{vT^^qF5WSw+i;k%a4lWD*wj;Gm*;M=40asR z%Pj7i%e-gxP55~&(T0`EuzCgXYK97t8dH7hg~=GyQW5LnMn+`0S7nL)-Hmx!sMWKIup}DBrY_og0*#I zZ^Dzcgou+di}}qs-l5x^7&r1EJxa9|WnIC;x&O`1f=m9`<)UOJYlK;$kO#y(R_z|N zTIsp&s;ZAw9}DqrV5^4#H@A>nWkR4w9m+$OOG!z2PhFO_-^p|9_U(4=4_Nr`EhNmk z^2k5k7Dz%C1!D~cfu4FSL*^pbSrh>Hp-@d-A-CoA9UJt6#)N!bp_C0(Y&BGi%HSyN z-n2E-*A_W&c9E$T9}d)=eSlx998qCsve|-={|yS0??3ggs-(8mTNT zEsg7o6Ij3?%o7m@f|dYpG>o`$cS)~+1*a1zt6Z_|@Y{ykYlcH~z_HUy#ebg;4_BWG zo;mPgJU*RqE7)!jjpGL;FgX?1?Z)J>V3=?OYqrt1hlGY|@SEW|g8}4NeAeyO-`@|S zBTenW-{<8L8@QR|3@5lvF^`qPt6S>Jhbu)54Gq2265Gty9GK^1srJXICMbA;f?%jJ ze|}f~j(QBdQIJwJbFQnZw&Ej$k?{okMM(J2-ZAVU1ByF>n}hb?K~DL(!6E5neAl5~ zI%J@f;NXaeQA>w*5to_xLwTrSu9_tJ#70A`>1O%-0_P85tgXa!|8E$dFs?j>T%vH^ ztLeS`zw?f%iIkKSut)&dTo4#`wzilFBN{H`4Ci0hJ`f8o(1*+_gg&4b5Waag!T_1A zB`o8DNMXpd*ygevbGhF|eBva#fI!Z`v1-8aSG|N~Z(s0p`wx=1DUX@gAQ4!dVgk~C zy5r`5?_HX8T`+q;IZ}$DqSAos7}e)(B}c0Uh%`iJBVsq?Zz!a4_Sox`C+LAy!y1VN zxk!(AhKpb_)YG(D!XIegEA(u$&V%^;)nTZ=zQ)zb$xB-T(i!G4UxiZe;M1zOY1W$L zsHdoz;Y3|a=2hNq$@TB`@*H)#oDPNqBVG#0EZU22|6$pLpJq~Br(|HzgZmF-Ju5I; zfMx){2fKz08h`ORV+?PJs9(B6A9TM2K_x*!d7QDQ&Y5YGrFL4}NM}Z@YAarD7n7ty80)CqzBCoTeS7`q7QZ4aWW2PRx&1;uD(9KRB`X{zN_Mh|0r1XoTDJq zqgF@gUHYkm;SJK{rF5BFqpim?$~pB958dk~iG(pM=1|8mvbC=wK2It4`CVg8}i}irK~e@Eyywn@gR5T)_-6$sOQA|`s*!w?laGnOyqY5 zKSt-zvhc&9qM`yC(LQQJ@{K}W0fzlf^(s+|*B@B(_|^`|n%BRy;B? zf(DUTx5dp(Y`aUaS_ev?S5ED}&qv1V8NOJJDRQ^PSHCIQtGmyOK0w39A--P-52=4$ z>EcDlVr>AXY8muh9O3UtKccK&Hx`#fSV3O>u znyf6UDOEg2smQUX@1?hGSOOdn2>>j2H7IcBDhxQ7j;v!fh;w&YZEXj>(!2| zJg)YV=hw;`yLkJFAOU`U214K?Xrmg@#;vx)W@ZE%l#cYD zIN^vxcJ zRpeUIbx$P_B+-?1f?Bv>wHNkjIyy~rO1OzLx|;)-B|Y$&o_nGYtikDNbqcKOm1G$$ zlK&vLtJ)CiH&FI0CaURG>9l=g6P`$VmKh51apOK9&4GHktbi#qaU{?o?~{<})&A%% z7~i)ulYTn&DwcgwGcmn1yagf}G7{zV-G#I?F7c&PVf8`~tTW2>lT{M{QWM&d$ajTu zPPM>%v(Y_tChIwmfqG8(JnH-Kp*}*j*Q&Fa{~s#us|}%C&RSGkwqigwh^y?{f06!2 z-w&`ZH1GHain3o78iY-) zwyEhvkrY_L_UJW2&tNx$z$~+_tdn~huj)oYO`tXWA6)+x#%OV(1pkS$ef;?G{pyVD zy)Z_5`MLrQ1E=I(lsSdOVD{=s_psioHw*t6Wo2T=>N)4{H3Q}(#qaBe5GqxPEW zKX>BlVU02`&?$`BvR$-=9^rRcWWE$5zFna-3=CoxA9)khe5zEmw2~}+ue}L3+$`Mi z5;<}o!A0Cue~$va;(8So%kE(>5O;9iw9mH`-)_qs``bC+ir>DDU6WjJk?*hd}7w-X9 zBr@!@WtSkc-QH&UHH^KuHT0!}0~U_Cn9vT)v&(9zLjI_%Kigc{4DRJvXNI++yRq1Y z`K1#PB-A_$iw|8qF(@1vHX`&t$oWiyLP+pKcR0b?N(#|n?NAlcGgdi%t$}_MlZgxf z$WeLjxli14An1p0v-~C~UOU)RTg^>$cTNlg?1NuRQ4&u1@oM};h>RE^o=KLMK6je zmI4o+S@9$0o=}MexhB!0)3!^S9o~LqlScnMjap|fX1WiA4%(asl_W|o5bWnHn2j?* zXqsv1Nl8^ehl9pOB#uK4m3Mb~&2^WsP&`IB-qb%*!iy?H*uP2|Q8k|0M=7xWlf{66 z&?|o6t@85nB8Vw=A;4d#u?J{}kN)qu!4;?43Op~wbFoCH2zR|in(yyZgHdd2^62Pj zWbos#u*BNggTE2=#!UbemRj}_G8XC2P zJ`K}j$luxRJi*{x6+$$XV2g!Zj zv!A8fe+Vtr%I?y8oJIt2nUY9@|CIAM<<1=pU1b+R-lwWO?B(9mtQ2+{kwh==Sz0er)yqEzXv= z<##V)W6IXcG{pNH!2FT>%?5fe8(*H#AS&y>$Uf(lj%kbjQPZ3KJpz3suDaai8{e z#L`X$l~q6L6AE}Gmk~7yiD2O4$Eqk>s(pAVd)1y)&j8sw#n_zz z(*?W*d7b)g`EM{Fz$OW^UB}%$q98fw1x)-8&0&rP9-H^^PZ39#9(83I$t4^^0PcfB zMZUwlVqa9FhL+Z8)AxtcZG(afyTRjF=e~+iQC2=Q`Jx?SY49Njc*+5fBdOJhcj9=p z!G_$F9-??J7qtjT(J!+;nG-0&EEYR zf6vh}G3m$2k|(r-GceQb0oDq63??MOQk#R)XxpI%7#Di2=o{Yg7P?S67GTR$x%W#O_~aV zfWOdU>uPC*tC~AH&SUm?>^A%U{rj={0n(tGn;Wc~U&g_woMRYMxUkuoSPgL+1xlmn zdSVgU_DfkF6WxBHa#G< z5@b6;dc%inVw7UPGu54>F&JxMUq9Q+} zWwnCU?y>cQt(jZ})=k_;oZByJB2Lq&P4s^~@cK11Ff=sTUC`WpV0B$F>ZDTDWryF? zlU8`5BrT@{^?|XjywvVy4Ce_#GbuO^-Df&!M?$9^v7QEFVOBw#Z7k^sEC)4&jpX$% zXjX)`*fu>3+#UhGuN>#}_45NvUEX>SERWpO&m30>3H@H+M9Co2Z&5P7gKJiC{c=>} zNo?Er{@udhfsF_;#7=F&>-y9576nc=ZUfqGeDkPPm}fjtW!;$sdo?-h^NXCmoT2c-L>@|9usT%Im%ZU|n+K-mdPTdZ(48(p2v*P%_ zTL-R&HfFyNkzM4+Sy=Afy<4b6yu+b(&(R}CUcC%_9eJ;3?U^g)?tC2Nq&t;!W5_z=&p>S^8o0J3su>;C^=F0+F_Xm zFZQwK2o_|p3Y905OanaZqE!K{ibrDrvu)?%4HFaeeILd%iiKSs| z&-FF^;S5f)U$rl~(rK-3ko(@~dlln%^_b)H&&1Ka)Duo<$D6@&+kb6NhP*;J?}Bxn zo%M!l)OTT;g3pAcs8TUeU!`QI4}7P`P{aNowkNo_z61Hfrs8Cv`M0~-#cbIqFg1?X zzt`&5h)&PBJ>t~V)B`G%5dLBQRW4se<)2Vl3$1{O=8KaeJt>KNTxKROE9)?jJ%mQd zwFM)jY?M+Qa;e**ZHO?T(INk|=RMX?$3Q)J)?Fuwo#t3?Q(7hx8Wd!Q(}M(}kl6?f zDpo3HcnpvqERzCH4SO~&0Ve-ji-qHW@Z7L1W$Qs=^9~Xyw-7T(%)PLCly$bIYVu_K z7}Nu(L4hSGnYxKQ_sikJNOxGFD3vK?Wo1R!8*a`vG&BGdEf;RHI}iE~Q|AeVJ;+6? zD53gvS*YaG$DYs`xDoGF&>!B@$9UT2X?w8}y!LcH1$=+smn*KWuJ{0@#dEju);S== z2g9;%VCWRarx#-Wshm0Y@R}GFsWJS+*x+fRbzR{a>sX^zK{@t#DkMilL||!8Vt}1J z+;Y&Au!1Nhw*vCta81WkU%oBxXiP-r9zYw}YYjbzhv#L$;P5a83tiAD=&PMq{0)I; zTIXwyXv!JJ%`Pz9v>@P{0#Y0V#yUZ4t>iedm#JG0fB~Er0kJ(_k4jf%xAv+V^&;+dD96StA z$JHbNzuxM@AkKaE3F@)zW`$!l;Z2rU$KQVy!yUpX9da(Tw6sm(d`CGr6ryLz34k~! z^X?!wg-;x?L;s8W{{Ab7U9mbx905#jOhScn4ptx1B2E|VqTztJ@-|L{Zg8c1eKn)~ z!&Fj%(|#Hzgsn2iHN5m9lKQaLmcp~%yEp`R&cy<@W$1S>YldHbI&m4-34UqruT*q+ri7-wW%%(IU>wujY#ry=* zmFF!}=Kl7?V1cEhW4^P8B7PCX;QlLf{QUfH>bJ>BOXD1!!-_PBkq`Soe>|`@qA+r55`YtYDO&*^#E%Z2(@EW6Oc6ikgnbi<(m>P6Wujd|1hgF@n8n z%iEsl|Kd~~qp2Q;-B5h&MKC?XJkd;3CrU6UZ%3UXn_3q#Ah~lrSj4bBfRLQS!iJao z=-*MvUOCZ;MNAhg$8fm`br;pwoWG~svpmx2si0Zwn_{xO9t-tZKa~D<{{CQ4*!7?>$91;L{WGr@&!MsvJN5VCxk=Lp9d7_EzW@35v`oy4PwQ zgG3#A$(Jr&0wv%EIpxj%R~=}p=Q=_~bS}n9qz?&4pi5+sa4T%@L8?7{?aht^MICT) z=kway+B&$xTTllvFq2gK{;N%zUJ*aK<#sXDLF<5&v1^qh>w`vg6E>&uEi}ihvOihq zi}4PThIr=v2D;+Tf;pM*kahr2u9!FBvbaxGZ0|50=`B_LvsrFnENHMd-8L_$o_V;M ziCflTwWXh63ufBq&HeR6Ro+fd5Nf~+m&>ZE(H9fz#9$ucMfFzA!M2C&0?${W0}nQ4 zc*Y)cH2fT)!P&wzs%>tC+#v}}m@L$Q{f)Udz?lX=7K`K^d+cJv+2V57U+%AQ!SyWp zb`^SdK0XyCGC5h<6zkA_;y_qDfe=6~E3F+l&+7lmm-Bo4+a{7w!>*li1j?lI zt0<)Tf@hh+yeF@F0#|tfzLSSc;*m(Lt955l`S3NcNNon3Z)!R3v!NGHb>H^U+ts#7 zs~U($3*2}Z8OjcSBdByt2ceT+9H;7HppY{$83F`kRSbVR)anb%8|HB6G;54~e?QuL z4p!g+*oCGr>j7CD0|U_WUqWJ~tsJISBBUr3b#}5daPGLUO5(9OdoT-p5M#j;TBl2}&SORCozA%Xo=m{z` zJtcie;(8!19kw9ZgF&b+zMk0T0?gp=?~i_?1V}jH;^ht+T7 z2Lp`NfZAu5-~p<NF#?fQuA?SmlG$|PyS7jhXRwne*k z?NXBn`UFy$xKxRW!$U)~?wzCdz|V{C0*^vlf+n2!r5G#@owRo%o<08_tLwr6kEWAu z#SBT(`iks2il*vfqXDss%lXRPItNcWZk_mAgJVDLs)Xed#2e|tdL$3YYktMkhJp|> z;b}Oq_Lm~PLy=w(i_(mhf%C6)nCou;U+jJNKi6&leu~OyS`8r?Wv3J(5g}z|XHz6e zvW0S0LS?10%N`kp$V{m0C|RLIb~2-k&vELyuj{`5h416*hpujS-f!>ob)L`j`8=M- zaXbyRO7TslCbCr=UKlKE0+P3iW*pmcJR-Y*MR=QM*+ep~CP9@6tMn!mGJb&F$FHa*vlZZKWm z_-pg_7}A0_M@;qFpWh6y@O|3DNlqCLIgI|b5X<>THiN5N+tA;O<*ii6`- zVJ1CwpdmOuIH~w}H$?t_-J1(QviMP*{FW+eH7Q$6KHOxrFD0vr+rR|KBROzgJ7c%q%us*$&m{Ou;RL$E*(*wjHq90!fkMChb=w^a;OE?jL4#u4gp9})GHb(sb2qyDZYisL=4gPmi=KnxSt0%k=gvo`=tzE#(iENg>^2*x!eVHI-0pG25py4aN8y$oNUVTq zlF~gIhuIwmk}7lleKj0E!7j=?pX9gV??!+ysw%>qoO4nPDEje=mh_#})B?YW57({q zc*aoJymItO3{>wG-CAllqLR~KaqEPB*=hy`CZ^|(!`f1Ablsc&vwB{r52UAywfU@DnNAE{J~9Z$Am|59$I0w%EP& z+Y49a$6b?1o{4HKlvis)iVus&SMarGTBFdmIpvfkf-5o|-ou9GaOvB|w6l=-z5!kW zeyV@w;k|qJA|sy+yFDddbKswg4vH&3>lh{dY;bR0WUNd7Be@hN%t6dSBy$z4LQS!$ zkxd_fR@YU>=;@Id{z}{2BZr1bgMd_6&H|dIJVVxCVR+}sp6A%RcN`A`vFc+kgE85D z9Ax{Izj{Tgs7ErZ)=k>LRs=u^=mUO>z$21PzqR}=;S-ct(2XD1eOq(rdLt0B-xJp{ zAx9G}MVAP)*Sd%21$+q#V)D#rigLy0g3q5nL%;>sS^?lM5(~1Z>Qq4KZpXgrz0>6lyCTO=;T3e{u^79c>3t~DRCZg!aOS_ zW##w1sm{8(txzli4nW#wf0XcZpbXUM_RqRaumGruP}!BhMh~897~`~>pM(5!K%W>X zsoZ|{H#{TI=eaLx^;rB5^l{Vo_HA_Szk&&Ir6Cnp0h(d%m?G`bP+iLZjz{_FX@Ph3 z5(K-u;u?|?)aqM+OY|L<0y{Zb;TzoTx)3AG%+06Y8XT>7*cHEa--25ux=KjU9Z?sA z_s-yYp-u$64En> z=$hV~(MJwREM~w6!i;MveXRyML`wt;5A0?{Z+NeKy|ZdJ9kaw{!# zu-gzUuiz{jWiF|s(M!T4k_lMQX%{4k;1vO>&8eMCL(8Wc=Xl@6F3HR>iK&scNhIjN zY(+;dg(Kf3+Zs1X_@^uuC~B;&htLx8GrGCfO6Bih3WxhgL{rykFu@$9b znpRrkh0giPf8v4<26UW5>yp%xH`Cq>`XD~QPlF8qMlOYL{+_cOn-8jeu+o0Pl#OuB zI8}=gFZOvo9Bk*idE*8-Qb0;?1qA$*2q8JJwC6mCt@&TB89Gsb;Tq2YQ?R0(D{S4?RZ-pf! zlKllkk6rKN+%8K*fy&|qMZ2V1Nht~=VlRkO9;K4BcbaoEdv0W8Bw|czj6IkT1Q$jt z84|L$kP{2j{*qBJdj3zooPputa#9< zRDN7s*ksi!aYVUYz@;DiPWx9Os!a`h_oVk>k&&M;a&-FlQ{0beBJH)=Kfru;I3&H` zblu1Lvw<-&r8tHNk;7=(Ji*l}CwIN>ETq~e6ctf`mm|y*!?64J&qlMcA5xcANxBTW z4)%X^%f50D8V_TFHA>Oh->T!(dlUI4eZn$|W8V)V?4CjM?88zqv;oL$zMa~ASw4E9**7*dHM19D~!-LnILqP$pV|9H!?n+=u zh_tDQk$_0iJ-t{s`W%-r>ZIR=C7ws<2h$%tBJym&LZ^`kqOY-mRq`QzDkg>v9>pjP z9zJ}CkBTOLFLaORar#j{F66#q3R>a%!XRU6Y6^$&0uC172c(ujWKn~Ph&;nn#v?|W z0K_04-85{{Z9?3i(TA;e+kkPjwShpa6z2Rb@~h?_D^&$@auq`M*P3A4#3Om8yYsy z()#=Pf#RWUU|@iCK!%Qhw1t_O7z54~RiRlt~h(O(xhv`6su*xCdu5wB+G~ z2M@x-f1!v>jE^7b$P*G3od!S+2msV@m~_~nl*cCrBGHLwes##{L=(?x&%E&Xs4uim zu^Hg68%)u6m3n!BI)3cfYw*_qOol{6oX_jPonmHYh6D*5>~t&ukjDcUt%1KW9inA_ zJ;n6a^!|efc|h8b%)n@A9ErBVT^8_WHGv($SQ*nb4Gca3SL_0>4!;9hUNxF=aw*GJ z4UZJrof!g`S-Y$RbzlB^8DA8ww|1X-9&w4sm*S`tYA=ZpU?Ae7)@X=a>1<_f0Ml)b4-2vc!l;=6}9)S^gjUwP@{M z7%XP2`kxPpQ(Zyx|CbtT@?SgP>J^m!C;?@cGI3+g78;TNI~?U3vgmH%2}uZoONYq@ z3iz|zj9{mypDg0lvOX&u2(;#4KcEKkKX>1#>D$aAa?8|8mgOvrw^B;^23S||&YGd4 zMyO%4r7-wD>D5Au*E-9YpFahSjeqHBl(-1+ox&4WFcr&C@WI~DHMq^Rt7i+z77f&u zk-1iywt~_RjLQULmIvQi4efiJ=cBN8i!Svz-RutOqbUoR z<@3TcNIjzNBOU>ku=E2~cSSVs*Rkc8b+sFC|86dDe0H5*`H)6>-3sA!dL9*0!g5KY z#?6ze^Xp<|-DzUNRk820^E_Q2BP;77B#`Ua4j0Y(pm`1gZyO@#f)*cMH~Gy!$BUf; zZAdg8AIx7t3`Y&Px8yMX#o8mb%v(vB2hP^tpYQrV(U1Kaa>*wkHTCwByL>zp5Alcz z%?3Axcxb5B#O3?U*xgsl(89popfxcGXdO`aHe<5*$^XP*MRb_o zCXB#vecYLfA_i{$rpP9_q*b9=g1Yn1`(FJG!Tjloa>#hWtN!!5{`(RugmY1;Rt`Gc zpPxq^C{iMVcQ^u9m35jPs>B{~z6 zI0r&#ZvA<;b^pGb61feL+;T|=`1z5}=<+99k+B_}_KpT{hji7{Ozg;peYE=T zz z1MOdarK=j_O&oZ?BbsVzcIbv8rRCz`VZ%Ta^uE!M0p5r+jx^)Mi4#xou>pIGK^dCe z=~G`*a|m=w@L+;NLQuZggCBr)Ad;e7d^(cy0pGlGWu9aQ=tQ8qs)>GO_q1qu`4=(x zy5k2Cjxfso8tMqpXA<)HqJ`R-x3v z3v!E!I^uT(eh4ED)GoWNiEB|erjDU>zI*4+wDTE?pU<+h(P(;(eS@?Tex0m`ugoH$ z0|6DwPTmIh47c@ZcF zx@vwBrb{2`^@E&`oCy&&Sao?m3pO)I{|ZmKp(jU|ak~p340(4nWARfko;V2N^uQz< zHj5ak_&$E^i&tG=?C=Jo;DiHs0Q2}y{tBZJC|M;Xi;#`uCj$ZkAaXl~R1N7f{pQWK zAOm={w5y?j(9N?ow6~uCnE*y7>K|4;z;BF77B#tbYt|Q#J)23b9Joz4BG_@4>*Kr`UhBA$b8S?L#Z!%j@b3m3@9QACMZeG-F$$UR3V$4%CAU6oyX- z?w-`P;g2b&`cd8=hIs3F=-$V%Qe-#>`mLdN=$V)fU^>Z%51Qq?=Uzp*^i?y;G-B34 zW1LzhA+kklPb0x+^O#ZxkVKUx^ft^`m9RubUve`;$v z_~qEp80fHo+}`8-ss;nlHPEz%*jvrG0o-6RWdyPP*q@Ei7c6XWQp{6W1IMIu@fuhe zc491t&)P;`Bg#G)M23KHnJ4NBBAiF9aYj}{T^*RfN?6?DhY#rK>G$DWpc95msE+S! z^i>#+{6>c!`r5d}lkmh~!^{)x*^~w^ECuk>0JNXmMi7mn_gShS3GnoqSVtaTt=)`u zw97Fiv~$Q=`So5mqK;|vX5!I}4v|JcS0*PdoyzRit|KjvZ?&yFW_Rh_+rXVAy+x+w zs}my8nTyq0!1H-Ty&O&`DWTUx0frOo;^6o!AG$439-btZ=-0Iu#oz=Ame0^vk<|cl z(CpUNQqoaL+9xN2acCu$B|IlA(qdlEyZ+$G8szSwDFy+tGpMuoX5WV~iorN66Ey6ZZU(iKXXT zFeLY{g5Fl~jrOOtH|1?eAk8=QY1QbB&z^hBID>qPXb1P}m8K&DTKe6+gkV&h<{MPL zN~W|J=Y9Kg+?TNE7y6*u$1k{N&mbBoJ3z){ zF#<`}xP&D7OGv8Fh6;>`NISLeq?p(j%j9SI9IH3TpV%TSD8+LdePiAoaS&9+{r98P zH3lIMuj27SLXVS|*BV{pmh5JC&!a|0U7)ylWX?F^F=E?H7n>Dqu1x_d^TPBivK<&C zsf4_qLoA<~yhfmEuWObN)gLw)J3vw%@Jz&>opbjvs_Du+2Qe1X+)Al*J*a#%BMV+(6X28Oq>d6% z0!&0_%)~5%zm%<8m4%*jOR{?TgK+4eNE&eAB!I&M7H>BiiwKEeEF*{ls@o0LUA~#a zV42AzMo&kHuuXo*`XCg3wt%_XKfcTPi{A4lE2CwrT15`UE?YJ>v`q{$fGNxDxttke zjze~pwaANs5phrhYKx-)j1VzB8h9Za!SxBCVp1wi1DA@Bpx}2x3=?iZvH;oSB-($# znYNuB7DDR_orGVY&+o6gKp@QSgtI)`#&DN3jb7z%@|Xe?dG8*wna}Rpl~s&QwqZ*njGly+ z4D`j?rQQ(-2bedSIffyZX(F^%^UTv-eAKO0v5n$u6!O|VTzH$Bx8ZmqM{X~t(AqO- zIDw~hEKRvro&<=h;{DgqvW0Mb32A{_GDTMHf4Be^hY`WiFAcLkb~gzu7GT;!`D=%x z(3Bp*;rYmW&?$Bt`dwl;4(FnElW?JnSD73=!6hc9J3ljtHi350%KOeG^ApN4so|k2 z{IC1$7ceKUd8QXO$;r}Gtt=Ed2illQL&Zqyg%Uj23* zr^da_sfyFyFR3Wb(HN;wo}*FJqU2v|L>s%-d+jZD_LGD1N5Xfr7jJRfy^}Lgc5R^S zfx_RvcXhL|u_}GDaB@29Z0RDk)a21n(qP(O`)#D&yyudlCXF}db!Hn6c#*!DJZ zytsR_81x7D`a!}@<=AaBp>*;j$;irhm39zjn6glDy!LaPxoELVJ!MOaSW4`gOV1dl zO%b++;Y;IpN@2&kLD|8c_k5qY#xDHmURrbpzhtQDpiQe9b_DJm@vt{5Lg)p{y>lY` zwwSyWi^KlWcnp~PL#Pxvd|RkUk#rLvV=6Yq`5;%^gQ)A9IkKxP;1r{Q6C-*&+7kc4 zd%u9OU}Cxz=SAx4z~9dYT|q9I`s6^Fl0z|ILv)W6;;jEdlZHTU{2Tx@i@#WuD}eBkm^Rm z1BHZzv+zrKuVNB1dh(0In#o_@z~>h(j?@mbAP0%ZO<(QKEdCIdk-CIth+!LjbKB?) zP<5p1D*m;Ra#|r|m0NeBLBi1~l&KUUHFFYU$Dpbr$}FI#pBkHv}!o`Hj&>fJh=!)y!P+ zKD^nw*;X`BvVN@nHI@^Bt2xuyc=}no575~2$fnx+oC|@x{`g^6Mv?lU)^Ci!v^Cw` z##qTP>?6=>0oI?tGjW>#zDkq?%;_wHTSsRQr-iT3`Ks3DH56xfwesck# z7Uy}N)~{WsuoX|8I%U`v8v+K|v6_~Igap+6lH%gx5)u+TJPOnE+#!SLZ=iEy$Nks$ zn+`Gsvr{zAc-9yz+zy|R9NXQ3f*H8;s+krdM#(LPoP9K*ET4LI1&1bXq(mx{0M@tDw)!pp};qs9GRuVTEpb``Y)>EB~HU~Pu zh26PZgcc|ROm#q+XJcl55EeG~Ih52bxJ43GqP8)B7{2U&e&9lQkBa@~&K~rx89xop z%pl$s{zPpyx%ybwnP@PpgM*&|QwC2x8I_{F{<-dw1zee$!#Vw1k*=~!U^pvJ&AQ1= zLJ5S2p4xi9-yM2N-obnRhWR7e9c#V!qL0dv?DWEG@Ghi@mWhZwLP8whCrWw>4yIdAu`42B^C zE-N}#$yS>K%x%|0Xyb;?D>BFXt7h88fx}ZhS9ik7Y5*-(Y#wy8Y@X^)tX6Vza*~yO zg_DqYB8;PdY!QEBm=~#A4xF;*_A~B%c~#xtL_fCiE|7v1YOmJgPjeXa+JC18Jb;R` z*6iu6Y;bZ^(chw)tR}h@BP(lkXlS3+#oRcXPJduY zz-_YL_9EA_pE)))K8}`)_B&VA!@jr&LZ>yVvr&*xWd?*W%+rHM1kq~f{*_Hv#)&e3O zK!cDN3-mMIx^qYCqbZ{j<8bfzHD|M3pf2X%gg2?`3<&vD~ff0m>n{g~Uw>N(cI8vo`|<2|t7gKf}@ zw>cXwCpRDqqo$){;9=QoCa0ou_vks;+Ft$ZYXYU2Jeaf{0CfB6Hn-m&ErD<0jHEYrMMma@c^G)+n)8pfV@DKuaM5Zo`bxHZW4*q`A z!_BQgY!nzz1T6Ec^b0#Z@l!xgZiVori9dILJ@p8W9(TS-2y%k1$GsRZU~?c-FZ-D1 z64r8$O1@Pi2bGZj-J3ZX(#15J-P(C%{!%)AoY(&PhV2JxA4@MFJ|hG$_oGXHwbtfW zc%DkzfQ#80PEh2~-Uh;GlpEC3UY2co~`5XwdE`396kO)5& zz%!2f!~6QsM-hpJ$KH*E)G0%c4F-%~p4-_fh0}xaHc5j5cXD#djsLngcWdk;?EI3O z{LJv2))&8kRdeN=H+)uHhYuTF`K>1tdb`=0QD^h--@gefQRX59Je6kXDf`bhV{CEB zvtDZi9FTClSS)P#ol)w0=1F&>VAI&V!o2&dZ#?bm@}!dOoA9EcQFx zvUe9NxY*fEpoXiypO-g$nba7Hfm!hOx%=^+WUY0sU$-&}|9fYgeovX8MR51NA_^RB z&&5ZN*u`ryzh$G!m8r*eJ`}EId{n761faO|cE9tWIB8j;iKA31#TYW1&p zoK(rDqqQH`lrvs+?2~CO&9PGGTT-~&A%-~)eZ~sA&3`h^2|!$arN=a%zgCJyAjW-g zYf_qBdKAlAnG(4)?TXw8WUEKM_%$kx*QF^hIxi5USX(XB5;dN8@8QFT*9!>5y$?yw z?6@v6=IY|^KGu<^dWjE^)!PI;s2z4oKQ5s;R(U@1p=LYVJU)Rpw5V=3cpKRp%nJH3>Y-WsNk^vdD_4 z^})g67x~MND$XrZt<6!)z)`~MUAPIKH5(fnFxod0RcWLc@aaln||EJ0Z%(!~=q`}+p65F@o;k1$LP;7(;6BcLBO57t0 zo)lv=>h_z{iWB~qn>R2jIOn+N;ss_cRfxP*#P>TlkHJl<7xuidg%sw_N@WA67$|p? zcrBIirenQdZhclFNHTpv;H)0dBY3aET2Dcx!dpM~^($Q8o&!6q+)4v#G(lHc-r-1M z{AgX3HUI_$P98CK0L>6be&B@NOPsk^<>fmDj45yj;7S7bPh$*O_%N?8MKpZZwBVH64I$dY77spc~JPG_(8Du|MJr6X8TLx(h^V=5QURr< zUO}|7Viq7y0QL^_gMB~LLZ?G-V(PI{*v=v0tBM1b1H2N*4ggDtzZ0ikTwDZah?zzBToZKH->)3?yK(*c ze$=0KFJS`_d9e>PH+s1poqA1Maah6}#0F}b3?VbF5@n1wR5PlE!& zV515p7PoFgRowoIUCa8CN!MlVaV`kGveJuyhF*j zm$c)28GEt!Ef*=@zOW|1Oy%53?)T_}@4N+QLiQ|c)cQdV*Y+fxe19lay$lwxf-sjK zyK)qb-!OJw-LGvHpO$Oo)D!ZzB}^jwku2(3Km(SZF+w_$H1f-ZvW!i~^E$Jqit;!) zchICtYrg;a@cpCUGh>+9xfCmiLkLu&wXOQp6Wyoq@1R}3QRsKSH~_b#YTNjpJ2e0r z_;{#!8ZYx>NQ2toKr#qi$2P){5)}S${R^%Pr~ttm#n182bH71%i&B03e&WraXjZ2L z_gC@6Fv#_FzeUq2q1igrPtYJ=Ei|=kO+`%yKbkR>&l#+`ON!aue$QM8^Ae3GmCr^3 zFYc?_5sOSo$)`MY?k|S%m=?7D@}Ka8!<{pI(p%(uqDK*3-I54RiJ(GDbz6dLMm zY%yp7q&BJH)i4`^laY~s-1hVG>ej2u(@C0Wj>CUK@djoE9n_g2na_<_6EJ{YvRC-; zCOv!J=cMIciUvS^|E7zF4?)uEc+nS$Dg8Cr13!Dvk? zZak@|7#OCIHR=Lpv2{zvsBWGgTz87mmP;AH=lyV@UL9ei$It_wV|^zUf%_`mK)C~y z;oAv&pMguVXPUkM;bE6Iu-U}K^zB)+RX=oQ4E#Y{F~~JpWy-9u7&}HokD!aMRr^hl zXxW$agn~;;OJ}cwPj|>zflHT3y=ZB=+(9C~QgRe{nH9=L?*Z8Ce$Y2-tEoAU`ctD3 zmzna7+Y+b=_!UD_ZmF-itxqZaT2WcK=IvX%GnQCPwT;W^%dtS5{#KndbS1r~8SjBt z@-Sp8a00}L_}H`A1Qk#@pdOf+nd!oofzE4cS8{=-!PR#i9fe@!X{d|m9T4}8{tAJ# z+L@|AA8K2D#56RSlRF~&lVRUu!rX$or^a{>Zwx>@^j~#(+u`rUqs-xO0SKLS!o(oy#=DR1Dje=y_j?Vc4+OUAN)4RIMN%Ku z8DdJQD9=8IIp%nv1S$tiMZzd=*h1P78X{AARKGUvaPg}#OV^6L23XK$r&$e+R;^6^*;+nYGb+F{9+Ib_KuGxaQObr zM%9?NuZjwXkMkB}2C{KZTAQ|P(JgQ|$4F08@-p=D`H+x-ouCnEwzZ4KzhAi;X{@g5&m9!>5Y>vg_uSP8?6do(GhPka?b zo_UHZ;QP&D|1*}B!&c`_t|46%i;*+Pjr;y4%^PjPK9;j@caEMTw>t6WmNUlIbIhy3 zdmt^j=f_kKo~h15^4=5?#=S#V)zvYbi#>HV=_Wa%w97}dz%s7`JsmzqIGfT7rNp*E zy)#hz9P2pq($q$M8>jpI znE1F^4pup_>V>w#PysNJZJ{d%WUZ`{O@wr)C@LL{|bCns@Ru{UMNcQNSw8teZc{ z&Og}K-w-sk`S4#?uBK+HP9>d*qG^d9%&+53s_x(~i92Zco2{y0(m? zBBJ#EPP<7YtITr52I73XQqP@chK--RbK7is`t3JM`S3K@$^Xyb}-r z9(QV-IJ)i}w*dWhHeUA|{3qlGhJ@^Tc-5ELx`_(tmDWsLOJ|nz(~63UrNy76-@o6W zp;YcnlmD@5r;f-_;7l@LzFmc#CFXC|mr)4jw^q_gB9_-GAeJM~_QRcm3!jZ}%<@n_QqZUG8cx^z|?%@2-SZWFP-&`#zTP)F&h`GgFJlhGvV-;$Ge z%S@s4-j+K|U2(=5b(q8cFZhTFvM5S>c3yBH661r9L(*=L7_d?6jJv@e?`Es|7>wfV z$UU#W9&s9s9P0I8uSCU(Qw;|{M|-(Q>vze~{=OQyl3LHuMkf^ilW8SwD3A>L6}`~8 zl~rr^OQk6mR9)N7Fl~5&PRzLv89ZyLsW;Jm1-c}jK$+W8pLoKKxM zmddd_?ddQ3hlkJObUy!aV18HA9jbd0XBGa9Yy;9z?Y^l?kXz-b;B6`9&l2aZr$kj>b!};ss>vVJ2}2j{Lk&<2$)-mF-xESKFF$O zmB|`dBD?L0X82D5Gd(>XQ~|3J>K!zN870Rdw)9T^sLXz=bg#2j^ATn~_1No$g+IK+ ze51=-T679~@tbL+0kL;Qe_Toit3cUE`o5lJ1Ay}5Wl80xm3H4;Y9CA9#iL;Xv#JpU z8`H7kIdtd{JNrw4lhQV*xizTbxI@n2@Iw53FN{Dm8jk@hzQ~u*{%2t*#$N?SYoE@% zsxN;L_2qgD67uu)U8XnvA?!h#8&Q{d{HFttu<*N1L%U5_k$_)QGzT{?4F=r4?VzU` zzvaL0VMpJkyQj$I``L(foK_zTAodj!2yZK7D7oh)knOh7S2~^rM^*E_HuojZfM4RC zhgqi$d3hR-&i?x4=IVOxfpL~ zrsU4;5g3#*ZE#qn3NSC%2Qf4Bg~^s304;!>-{d|73Or(aX1(cr#6-=4#>1^F^NnYvu1#F5M-8g>F$ zj?)v>W4-DZZKLN`2L}ax`7ZeI1b0YGOgGq7yo`5zeS!Z5hgbp*(Rlph#}6b)yn~VS zh?mRFUv~DA*K9#OFF0N-?5E!C{@^gI{}E$Qg-V;eyo&yBS{L6!)6_xr=yI2%zbFF2 zKbPI9DBY(iNvjdG93}OI5h9tF?}X^v0fhHl@Bk@3u4a$vMCo7mjb zQW2svKAs$r7%8{m@pRK|@9El4x#Ed@xmJy@Yz`>PTh@hh@%WlZ{{kr!xjEn9*8N|r zLfV3v z@6e2#u=};7y-k7jZ)|~Z(7v@TmRiuyoJW4W_BEtFDWTOS{C958zdpPg-3n?5R1|y z)bB1PlDhUkTBn+EeI_!(8h3(_R_Z;?DLg#^k#Yd3q;_BgZd>>&dQZaN-QzVB&1df3hlF<^BEMuOdNS`nGLErvy2R4nFW=-`2!*D;^UE#EyG!1e@~5n% z>E4Gv=Nt+>2tZ8ggbG#EJbCQxaHFI$^iHhs((SCdY<;|_xELy)J&YJgV;7Wr95_S> zO)jz-6#mtRl5VN+Xu6TAh+(q#{pj)Nd5O1P4+ts*#4F(=zaYp6$oZgVD*~qmmUaYb zP9F40+WR_iHD!g@6)97B3vM2}wX2SCk6Z3u#_~S-N8QGjnmReZ5Z?1^RT$);p;GEu z0*&aThB_$-j{jmJ_xRr*W?sW899GS8?-O?S}L5#p5gaIYL(%YK`!Bk7iFsSl}2z-IEnO3Wur?{g1w{0Wm<2mjMJe z^|$>ge6N4~4n7L-CyncQB z1}MUh3=3&6i}C!u7Z8+q4t^TXs4>T>ZjxEaJ`6db(hZOW z_;Lj^t1R?EB-b1Ob;7=-_$U&iKcDHIprQW8y4qUYOv|5Y74i$%edR^&fmd z!GEZaI5YCu%~u9HEXA7U9ulP_)!1i7Y9Nr&H;cB{@iv8sk=L+o+E83 z<2C~@|32C9OpbdYQTl171Z!$$4bG!MA1{mEz}=-umZ8$2~7g9Un6LRap+zon%nI% z+;Hy5`f-L~pnrnHz6^hF&`Wbqp!#3NbpM8G3Um^VGs^6TG&atOiqD5pspwV<8V-z> z_rF5kx>=4&nd-ACK1fht;3M_3h_}>C|RM2vNNd=IKBCLWc4t>0TKUyM&t)&D4(#ku? zMee8X6*j<5kNiX%gX`AoiVCX_8T*WfrO7zHg!8TX<$kE2N^j6^nJPRxPnTHiTz3+VH1nZ^N9yxfU(R-J0kOE??t-^5K<5-jeWU# zJ@Q3&*`zbXE(f6t%OsvWQSSltanL_`tbN+4&@f%ojv{LPxg&|B7}R_(y&$qz{Myki!uBAZ zAe&}n6iQ!*r^Ni@p6@RFmjQH(RCct#O07S9$L+@`t%Cu*u9Igg!~7jEtUw03`seMU z7lg4BztmRletzyfcZwQ-Ov%*VM%%pe9+~P{!95T!pb^08*$WUG&4OSFwD}gTXXvcy zGxzHacs~nxg3b=@>q#8C2`PJYk3nma-C&E8iB@WO)aAf`(HPwKNZB;hQ_lBqiZ3+1 zC=!OzL>Ng#;7j7i$a}zfY0-l*TjsnQOViaWJ$Lp%S1~lR&H2wkTTgBRjpanx>F)CNkcJ?E@1RW?7`WA)2K_im`*Me=i=Oyt`G4ZMlPKV9! zzkT}#JjIZg7<2YVsEvO#k(Kp!Ix48TTpe85{%#3ygoXl~%rWQSRIaVes-7DqfN{p2 zMGw3JiXJbETfFAycTSg8Y=9%eJMAO?`K)H%^lq>s)|sgY8MJK$B#4@dCKlNaDNOw8 zz*tLpxK985*TB`i#7Til+6Qf*k7j z|CHAil#b@mf$J~rmlZ;74R8{=ICkF4`dn;%mA_)&>|FO2XS=z?!@Z0GdM>rRN;o@W z9O);H$Dc1=|C6MNBgx>p1&`Z;Cp=h>-3-gw^RXYuS=YwGaq`ZPfFP(*RdhWav9JTM z7x8)w^h<~wjtiJG@%h*e8uX3VmwoT|6F_@qBY~hIIbpOxF9$~9j^U6TP<&ECkDEYO zrSTZp=;7AIX>5G&P-%!U5!E zbeo+b!73VklKfL!UtCVoeB07;5EQ}BUzc-)6DYBRDI1ZWq15`XMPTpR{tHqKq+nW4 z#r-SEfK{FlVl3%BfIeGptC>4O6L8a0h75jyl}ez_haWa0J%GsCNbys=?TAWY35Eoq zw7PPos9cJ#7O5ieaZ4=?-~ZGZklH`^$p-S@gMy$_AY%YTwQ3SiCdQE718BrNmXGs} z=)*w=7OTHM)ejlH@(qm988;CymAOPFl{Syv|N1ZFL?%$OV~Rk}vuGDFGys6S(#9ge z)$U4PiGA$yvV7H`t>UWn=K!L!7ogMzsF2+H3EXQ+sXY#PYnCHJq9S3R?C$o%YUJ)xMrg7_!a{e&Jw4c2z zd>)7#Ry?3U;H-rOx|#C460rA`dHSpaRAw@YiFdz6cH2aT117m^-DHIp7dE`>e)B~9 z6F64lA8wMvC+x%?fj6s`#vL|kqm4Tt zM*eFdN^37{>Sb~uJ_E+3_Vk4UB|4jQ+xEY;&P@%*EMMY~uF?4NrW8`_ioT884qSABsjI|u`&~lxCs_b0QUt`;ATHvwg&^Xc({XxD!YOp4 z)Unp-FKk7^>@Q!2x%Mr;(Kh}D)s?&^{7(e@$aKAT3YJwT^HeU{RsX7rq>Z0ufMr>6g4 zJsf2AIbbBq6CDFI?sp8Xi;mP@b>CT*4TP>3CYtm<18~_*u&# zptwfBULNm^sB?k}5crXz)_3R!8&}Yt8~EO&W&;A8_W%-0s37CDPZOHqlL_1g0=b?^ z%fVXH3V9BoOmEpC1ZTN?BM$NUu&6Qel=z75!|A(QEx+}xxAqtS?HMB8;I zEYgLcp_Fc`u$gzM-tv9xvU2(Qp^KIC-3)ya14|ZIH_$4IwN<0_8PD%>FDxk9`d9}6TK z5yyGADN;eoM%>uq_XJ`f&BL4+a6;7ouG*G+* zKW-QXAq@ijA3HmEV;gdb{08FYq^j!tEEE_9*uG#SVR!af&g*tjMZHW4 zGE07?Y7z_)sfplzM2i;88L5*<;Qng3&CdheZ*P=tIwaD8V{?L@$-hr}X^xZ*3G2bu zd}?&89=A<`EDG9!%l#^kA48R?kj=V>Tymf#XqAG%NhHj?49v_)J;qY2iaLg^THz^4 z6AL17H%4>?FG}?SOhBpS6QV>3L4#xr*q2>_K zxw*SD&v94vR)o^oZ51(zhg6w17H@>&6yg7GQq9*NKYzx6S@ikp$jAt247>R*DJm(Y zV2EePuoOe@*cc`!(OoLU5}rJHQtML%px_yjL#zi%*h-olV$xIYo5{l5!g$(6?5w-r z914NIz`c9`cN$If`CNVCA_WSJ(vFQRERwJYRd{~@Gc>Lo!R5{Hi5dD?gpWIq^4fh- znyNjPeT;z1kvs7QkOvTe#51Lu=5MikagW~t_tEYpOw-A$R3>bPn+`GD7228)H(OBF z&deD;!D+zpxN#GAKaIyHn*(_m*j@8a3|L-mtrQJ;HQAlJC++W1U_{3Lk%fhY%FrJ0 z6iylVMu&y9l_JGk_*Ero)JAJ|mE!B1!~Xc`yW=BFNXh~7M18)B`w(*(boA;55CRCB zt&D=6`^0X&XYpdxA@n*TFVDQa8e~t1F={|Gphz}oBl3L)zhx%V(Lp>|H1a6dZ~~!_ zmnUt2$2p|i2o0Ox&m^{w_yqVmrr1&A<&+A(!+=h2%$)~!FVS^muwX&wXz z7Q&9K(>Z>X^sim=S{k$1$PfUSpPmBm1f{n4JNb|*>s-)1Mfmw`%Dky2ViIg(jLqq` zG$h6COh13y(s>YA6q*ZEYxs?dW-FPE9jxA?t3qaWfC5$HZGOeWqw?ab4Z`A=wwfE< zq=)Lb_=h!5_l+Q3*p2!O?#W2nZzk0wSl;DFf*wKA2GCLS5kxP~;+% zDv4`O+-tEY@;WYV00H*j9SM@K-cjp(Pwswrr^MP`CP99GzZ!2;bOm4}=CCD-?6wiG zguvlMaaAe6OMK<#4D0s6Q2=Eh$37GtwK3AhMIqr;7DFh&d+K5K^!#lXs-`6b8u`TI z%E}R-k!x;Fxk2a&_V&+u7Mbq_2CDUz4wxeM;(h*oWvcNuLC?$d-8by_pN2dtNXQ$L zi_rhZSms_%N!SKQ8vcdp6QL0i!|-m2ViC}ihM>HR)u8HacrV>%CnyH#fslGTnDNSL?cj*Q7D(Kh zgQqSWI1SCQnHiaU3N%!wx42ajkxFaQQRlCW(&3h`N)A?{iE9w+KA(uIR`f`MOrR57 zADN4A3={z!9_?jNcOg?MvcW1L$As_`Anm=#z6G%Q$z|i*W%l$fzZFb$f$fD70i-4+e zP9o|Lr%~e=$HAs2&!sm7()VR!TXcGmQzBN~n0EsMx zVc5J{-nnKx#$SI^&<}dqT}z5~JD$3P$gh*eh!wWogB7-D1vwu|qdiuQJBehlwzdd7 zqWL5|Lj{#3M+vES=4Hu-JV*6gVvHQ8l->mrKKkcr9d>^H6K$$&(;|co_g3K4reeA+ zg)^BAL@ga!3bd-eAO0;@dGDP#3W)sk93&tIQ0CqVMp}^pDMy=g_)5gjQ!`X)v%kk> z;bZOz<#Fl~{iDK=Ent4MuGJL+yBTtJO^bEU_r9L1?L#D z{Twn(Lnw;OB@0_X>{YnE<*_3%Pr=PJ`SYjF4+Cxy+y24toYls3 z4Ix@EEk>qef8c@hEi^%aZ{pTUKmHsni@oqz2-Vy`yM8_PgeH(@C|3a+4b3Io1Mw7T zgZ*8HvUD|pEnl0|bWn*pkG3Za#*ne9_&q+PpVlel&Vf4u(~cd6y{6z9xQ{%2WAKix z|8Io4xf8c1_Gt)B)u)dJ+`Ec9hRs?DB>_M~OL9oem5C};DU+UZ76&5Sfy21bAKQjX zh8Y`ZOM@-w|1fScE}pDE)GoRS$rC;O*V^kLRlc-a21P7h_HLSQ|I)p*n73T^t@s0> z-L^qd0Mfqp)0dF_R71VwDOls z#A}0$YbRr=Y57q3s3B5&lAK@z<|uYymm%fUMjGeeo59)NwFDmfuy=H_{2y*XTFJK! z`tUyv(!YEj(n;RMBd<)xW(u~1>jxTvV;Fg}#A=N#SwkBwMBM8;?ei#LXs2_9Wd*f)@37+EEw+c>1+iOuwx z?oZ8^0fiS(7W}>rhsgwK%v4F~)X?4VAysP_?FR7EH4lzLJ`U<-e5LH6-HOIM<1NNs z7f>k_h)VVqc!3x_sbkC`8WxE6g zw_JdND5&ElvBzgE)G`R7yL>L0Z~uN`@koNv_%TBlms#9#sF3dG@ke$Q|JX&}55unw zp-OTxny+YkR@I)p3@FF&{np(7Bx)_#YRGHu(GZ4faZZ0P-*CemR< zK^Q`wDBEg+B=$_k&F>rkT8A{ve`mV!ZOc5o;%PL8!0SoVeuWHT0XQ+vw>fGlEv2`; za_3hU(y@(G5FuqsAXDkGj^q|07mo>8@dvk?bhvxszBU^Re< zk1$Hf@E*_?ng*JGK>R^i_wXo!zi6crj2l>(nE|hi^%Y+F-s9bfmjaxpbL9jMtYH)L z$t{CTY7g3MSP$6f!i5%s-zfgIcm4eIaomx^+|H3Q1_FUIBPa%b1BG?xD`&31!Ci@P zX{&UE=j9582?pj4VBgqlL7>{w~}=F;eRT?3JJ73(GP> z?SmaSi;Nd@A-}()CnG7rl97IRRb!0Ctsh5zNzOf?l0FzcelD*A8tQ#$#^Nrn zx^f%^6qp(5u<=VNnMyH35Ze4{W}rP6mCNE#^`cdU;)9z*BK!7{hC1GA0k%XFF^t=` zK~%kjv(*_^eJq_xU(aTX^YJOCMr!UoTGHXZm_^3PVlNOg zq}f>)@i!5F1k-qoh-D$!y}ihgja>T}%lwSFLsGEo2qN@}b!mxC994P$hI3J7lI|;^ zsl;-i62)bwivH}kYykgXCpy=yhc#AlV<1WDh&!@W0_j}x!Xsfn zLL?V2;|37RahZXY*n(IE>M1>x?GX{%H*QqJdL<_(gJ^@nnorPJ2LF$Bn#%?S46fk6 z{mx*Zi&l46{-s?!JZ~BrG6Ay!Y=&<-HVP@$ap!^MnenE%hAtpvz>TDjC{Iwg;bVEA z%Y=Ciu+xVs16BC{wRiqMQP*)Cf2StN7c&RwTyc#uMNl!7;TO_Wh9yID&Ol*Z4!_Kn zT0=aBv(wzzqC88Q*aih+B>_uAIk*WJxsxmHqzn-+KNE5i0(yF!(!w6Ey8~J4hyDO> zgR##Y?|Xk{hRqvRJ>JN>Q?Obva~rNvwwen{yhMsf+x@m){3FfbFKfz zXE{%1TO46JoyY(y-$EOb^GZrgtZeOKWr#uY4NzhMspU|Oq$EIpK9fdn4!W*O$J!8N z(#phlLCps3LSUl!SSM63H9O{{HZN?W6OPN{F*m&FJk}*_4 zLD(*vuSyRWu^z=NWk#JQvbSpiI1EO|a5R1m?hQ6?X#Yv*un=ypw;xTJ$du1!_QMDRuru(Se%b zIozn<4yWHx>bx!>%GJkbDzzAL;K`lv4`Rr)^-O_OX!?KB_t7te)>alT8RcCxe&B{C zqV=8+!HC?5?~_JU#P}Nb@QvL{gV>MMDvaA98#P=aP71bw|4ZF%Z8L#2YIbAKs(6q8 z#~(R#JTv}uX*>Z`&30a?z%oP=BRA@v0SE<{M&(`nT>}6dJKVBS zr3%=|aw3NTLCAujFjaJoR`q8o2Y!P?c#r9I(h;}^llG>iFtcXk!gDJ zx5mxV-)1`F!`_U20bWN%mDyL&GDD5`xeedtT1KeolQ=;1@6jaPo;`o=+&)auEgiC_ zu=Ox7GOeZ($INX&k26cgHszkYlN;g%E8a%tit0_`+ePsGiyAt6rU7T9wV_|=oh3l5}#1DF*6)S6tUhNpcWNbj%n#PnQ&l z&~XEIw^VIRPp76`a4;a&%H;x`O=6+LRxwP4y&Rf5F+BVlg--Xwzy>U5YOm)8jR`ga z>M*RJ=QL$?XodW98>%woVRU->L(uOJI({o}<%>e*&zL>?1PZPcAvf*>!9;*eu4fCZ zj;()}$f*-RQwB1Eu}v17z>HYN%MS8}Hs)lBJQ=D!MZAxT#Y!~`L;#UAXPlXXfi#%7`%OPi&$O?`S9wx;jdYKF)<*SfcT(fZN&QkTpcTESK;Tz5t~QIy#u3FeeJi#1z+?3=xYD9~N7St}MJmLsnL` zyw56`R5OUFaP^rs#Ry?^g9jP RT}8a3UWrdyQn5(C=O1Qsts(#b literal 0 HcmV?d00001 diff --git a/_freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-rand-hist-1.png b/_freeze/11-foundations-randomization/figure-html/fig-opportunity-cost-rand-hist-1.png new file mode 100644 index 0000000000000000000000000000000000000000..6d49eab5ea5f1883cfb288f2cb436a5ad1557b57 GIT binary patch literal 166216 zcmeGEWn7i}7BviGpdyMvtALyCMx+forMsjFG)M3IJtgpx{1NT+m4cXxLqJo7@& zIs1O!=j-$BX8(4`hPBo|=A2`UIp*c}Oj_jn)jLs=U!A%D)U_o>RK0iu18Y2rJAsZ0EeSb=3vsTS7PnxHD<-_q|B( z=h(dVdU=nriRe5z`9F{DpF2-*Q&eJ;uXWP$(s68(UY@UK52{~4@TP5pm< z>*e(SeJR+H|GQVnwfMi6;Vd}*KfVlfb8Bb88{FL5`aUo)@ZCEeyZK+=_3AsjkgqJQ zvPG+h;(Ff{(;QZZxt5I1oqedYfAr&E3&S6E7$O)oziF2I5PwwR@mncfWkNP;t!!^} zDXSurSYAP4S~d!0V{7Yqyivb5=6U+-^HWq+ZEdYm+j+EXvI>n8w1y^MS?+kRG=gI< zTOu@-%de65c+ISfB%kmE{;cnbi8Wp4W294}Y$@LP`=4yZotEwnn)PL_nsm{lp&hXv zY+iokQXJTM4p*agoaxgNS|usLHTY!$ZzSi;XC)?*b8y(7p8Vd}*zmz3;_If z(k@S@7JqXU7uMFBDw{BW_EoZ0UZR?77!(xr>eZ{0%=`y~23ZbO+H!JotMI=>u~9BZ)3Py1KerD*8cdoPf50**7mQujUA*l*B}hBa+vzUz2$3PuwCC-k$GB zc=G0IU0*j_UbEJUmnRXIO(Oh~@Y)-FX}tfv9sR6Hn%>2zQUf1bHl)2EAa>W0&12eB#{^SKd{p9jMZkkd?Fd63m7W{}`k^mj;igl63)?E9ZBLjWS zgjMNwr$m{{PE%78D`PWVR%z#t7eko%j06#rm-3qNXA3aHH*4{=MMM5`6c!5&L1h1^ zwZ-tvt(n3n9Pe#9D1m>wii(Op^gJo8Fw@0-^XAR(!=0f#lMsv|xCGttk6&w+IMmkE z5X8K5IB08es4^`-IW#lL`TNl-8HzMACnukK_908wdj3Wh?d8X;^24Sv#cY2#@cw=k zTSJoKnc3MNCS8VeZ82{RKWn(~OKZa&lX*Ip zBoRR${GX2vuX~?D307}RM@_xo?s+n`rl#^lOiXNTv}|v6#LPx3rE4JHtgp;<4>q9J zche-IJir2~-tiuWFlrXNogBgz9$Rh&)*3Rv`I#yFV>2?>4w z{vGz4SV`l;3a!CAhbmNXa4@@`a3JxEcM!7w{h~oH)L``NJBOxY!c@9movxb8{xh*6 z{u8(TH?1<4$&C<7DVL2}{I$|8>DGqr?d==<`#Q5NQC<{*#C$HJrOuNavLYqJ%bl65 zlbuNt6B84(=YAjUY3G}Une5#9$L1Ta{i4E1v3*7yvg3tOL?R1l<1}sdX!l9^`O6j4 zlonYC2?x*o-THO-J0+r ziRE|arlb@m_c%E|aCwm{U4o;YkE!Ia&`HrsFc$X__1|j=Z+f2s$q*Jxa6jQfZ^HGS z7_zM3vzz}YI=$5{PyuPo*Y}Eyyr8h~>QI5@bVCqn)$7YQ7-?xY*=t*kBgzKR>F8)^ zWN%!#di5#>#&@BAr;1P{qzm&o%zA5TY98Lh@>H%l-Q3)a^*A&MYTz7onhKHO$GEn= zxp@Z%hu!n!8193aFq~FPEZF(dxSsgASb&ZihvD0vJ_C;u%<+YKX40UDHzYm!Qxl!Y% zpSWxdcb5mGQ0#tweglQp2^DF2xJ5-pmgNV@hAMV;+kM)eL^p4ayVk|W$G^YJY0BuT zs-eN_xT=wr`-{;vAM-XO>9_3vzN-#3-m+-aCHJuE{jjOR88r|0Do)FU-`|1k-7au? zyfIb(Ta(Ewiqlfd+WNa;zvt=E*!Z|kS#WQrrYoE!N*CVSP)y9vk>+eGFudQq5&QSy z>4-pTddd1ZJA1wQ4W`J4d#WW4D*=RTunBjFh%_@bilAov^Ym>?oWSX1?YooA1YE9r zSV5Z2^#O!rIW$EgT5cP)zkWU2iG++0=W*EhuG$1SQ7(ma71{s)J!-Io4gLK2bG~Vh z=|GMFR8vanPlfu8!H`V$OSB$jzZm+Fo=)GIZPJyz5L*n@1nN=mHS8!7XSTr^p^3$7 zFYu=;VN3q|_0p3C%IM1>6pP+l!xniNK3rmA3&GtWG7-}{NX2uos@QPJ5?%&XZ^#Pw z*!$x1W&eG_h{CoUA#}1+mzS5X-+f^Gwrqd$-6h5Qq@-UAn!}--F6yQ!XF)9HIepKQ zD3uH(=w?)>W@MC>mOg=WFgZ095)y)a`*vq%=jPVdYcDUzn|C-&yCKjirBHcL#Gd+K zIgUD~R4gr#%rr%@tUsV?UMbYbw4G}s;&ZWsJlNRSNG1JAR9c$f^Th4(rwMUsI#-RjxKLe@EKddgIlF%RekeiuLM0B!~pYa@i&q7WV&^ftb?D zGY+~X)?EFHAuJ{)=Htg~*S%HvDGDkoDoRR2Lqo`9;Q$I;b{5~?;qd?P!JWT047a>4Fp!?U8FfB9KIq#1qrjnWiW%-UKlNum-7_<;wshzIs4; zTT*`Vbz&{4DGmo{`@&I`}~FU-$W;f7ECOt{!5TFUZ`)6I)$FRAg-9y!>~woG_UzFDg{)ynOG z#o2Pl)b&hs$q4kMKV9n0;G+$3Anc}&U|Gq@fqTrTU0$kQV1ddgSAr0%`#|KnzpfkB zJ_(_{_-1=;Y^){RpMX{0*Cj^Vb%moue?#H%tj;Wjg2gj~t_8K9p;8=jcbY*c;axy?dANV+1sY#086r6wW^g)aqkIJQV zMSc9p{9-T<&MOc#Zc&@t&R+sSUtRs=^hY&?Y!;8}?s9~-$G}&4Dj5N+g8u&gcK#!J zF0O&Gm5-lBD)yChX7g#t$n>hb(2-K96CY863kaulr&k?*lZJ+-BTcF9yZvdXN2te4 zQ<(iy?{z}fns=l9$x_jPdIx5%#YIO0fSiO|?8nK>&FumgErLmVmr)M@0gA)SWp8z* zL-s|-ms&4$%u?yAwxa(!K?pl;{f3)i=js>&8y9=hFt1)c)^z8X9qWz=!VG73PY!U? zV*Fi>>2rgmmzNc;tuSZ(J%be2LUUKTn%DQy(0C~(j)~DKuSYU3#`qAsi01ahd7cz~ zwilI>!sXiM;^LY#=wzHC=wLJxmyy|XkLiY;&(N+o2@m`j;Kaw~ez>i}ut=e=ub+CH zAsW(?+xJbeIgj3j3jlwi^^~A#5+f_?CY*k2Q&Z=63(kig$AyPMs@XbKD<=;)Irj#P z;(E;Ad{_%Nx6{!)ubr7|)IPduNrY8@xU&TJVnt6v{fBvxSs&xmXlEWMk911uaN@7l z;*>>28*2QpWn#EzBHs3=^^JV^InkeEAYpEvzINT(Y#?VQ$Do;h2d_)MT>GSyPHB~? zT+7`01uZSD+V|%|5N&S9rJ1<5Z?ifq_j`L^Bw2FcF(~pJv<_Vj+TY**{M6^L|4{*i z7K3U|%`di6LuI#}9%akD0@x7*8fE)nA7ygrR(nGh@$GxS#%5dXjiJ?k#qq9yhns`L z58}&fr}G}TuDb(99GKe?z;_m%<})eknb*`ho?xsiG5(!n?CgWg{*7`#Aljf z+U$<(bqoyWxfsW5i{w8D9){&~pi4~hleG!QMKo`(Rm1sPM2PD5-^9U5)EWYuyt8}9 zPJ*sYYb4>?=+%w;SJ2S1#2!{$Mzgv=8Q}6cKK@Z+k8t~<6?Y72wC9U~9HHz-g9iG! z+m;dNnngB3(^X#zAG{b$OimvCSnJ!z2C%s+J-`J6ZV5NXVK01ULp8jyq@<*swK46z z#rGrvClHp!-RqYi11^4@YmIhn78uSol7ZqNM4Q!ILNP?75>Xkk8HG92)ku%f_q;q2_C@3J` zXRa*_1AD|{)G!`oQQ$50=li|g<&v-9sH>~%LR28vd2LHv%rkRq1eV@IciJIBGO~H2 zFH4(*m^iap_WISUhtnZ4cG}N|CoiPP{V3598#WT`U){2aI?;^ew2US8nf}2}6@VO5 z^@ov!^pQWuq`kkLpo@m4Z$JO*pVmmovQTpFs6oMd`S|rElefqRgtMYhiFdTKjOZ~R z`oTa-I(hoL;xt7s3aUcjhYwmsHc1~0s-MAfPEYnK$jHc)v$Qf?CrI44Wu2V%fjFzn z$$fF1&;sOzA2D3cbF*?g`R?v$Jy@#bAk}B~jco+y;0XSK=YtPxG^z6)~LEnatydL z<95iWPs4Cem9?B}_v|dNeDwC$C!hpF;qOh8bb5@^9nGKS?>msSuvmS0?gFvX__@}o z94`Q`{onPVPMiN4A0{&#?T(1S48P}|yzHiBVdw!xExFj|KQ(O)!TXgA$D7SeC>B6B zSXZtv7gIt>>D?ik?U)FQ zc|4At;FG}?m>P#GYrE$|c?DMY*06&eQYDLCU1Ug_BvF5NcQ+si51@R)II$5CeejMT z6;%0FOSl6m1Bm`$GQTRHQZn)vln+2`gbL;CWvk;=uc5AJmb(>M(+opVzw^L+zm;>0 zAVyUDw%Z0nwYOQP2^I2jHsh)>P^y&M~*G z$_qDCrc=ZXKC=HTm4hUAOie@cRW?Bw#D~r@{XMQ16V-2uBk0>&q7QRytAZ2SLu1;T zTU*w=E;cFbWiMphyy1n0_6r@+Hww{%N?L)9Mm-CGdumemiPu@qO2%Q(fZct_;1&e# z>r2;B05d+8zfpv3#y5ho!vdwf+EgYwPQyLsl=r=>s%tZfIcsvi?;*W%M|$Hc;TCP`koI zIMH?pkap#(3%@yL>6;S?XTySzH0HE<99PW;^S(YdA}#=RE8s3?8&k^pE`Vg+=n`K1 z^2z*6oNOdk1DdK!#1G1FCm%!G!$lW}V1s2#Bnu^tXdPtmOE@{W)5z81p7sruAn9VB|RF-sdg29@;$PaxfDi5axVd=^zneXAnGFB)?IMD=8_#6${XMwrB{c(XuP~J>$@?u{Jo& ztTK!kAnG8hyqB2!VKdXjRK8z5PftzJ#hev7JjZ={I1`}_83{o3d+F^)syN=0{VB>* z%9_0BLst8$;Q02?uW&{4kSnV8zbkqRxuSQVXdG*z=f?26tFa}+!9vDj{mcpo&kR0+ zVLu>tc0J>WXRU4tdL`+VGdAxDSe^s^O*TM)#K3f|sRm=8Z9AXQ$p!g>ndS&b0P_L@ zV|f8%9!Dz`Cp%2ox5M%;AVMTCM^t#*g5B;?pG>{7Dx~?9?yp^duQQcjO@cx(_~S)d z^B@N6PBEYB?)J)%a>SR?bx4?mc?Qw?%O|x3SlF3T3kwUNKe4jE@vVJ_AH6F+)cae0 zRn|pTRyK~`T`5z;M7lVd4_0qzAsrJL*$-eBd$d>Jc>U)p@&3;n0w5G&3a8i})eD^b zWAhVhtdSi^#9mQb1yqkdKmc8x?t3GSKrA_4d^8-Ca*rz35&LD-)IB$2IOzEJyg`O* z|F)9v<;Nfmze5D#VT7=%S`OsH6-HbpF=78Vx3Xx!a?Fv@2&H#HRl1hD%W+!qTa@u$y?qXH~E zqdlf_`$(%7ARdCS#ra}N$X-5Kl4YVm(P1s_c3>wFmI&83M57C z0JVc)h{|0(f};mja|w3i`n`w0yzP=&PBX(EvtHlIq}YHhlaAvjx_j5mrW20P15hI+ zIqOPtxuj+``8=D!;+75DO3D3KIlX-5E`JcZT|FW%SZsraWm0#%AmhpUnbHCfLT>;U zU>?J3E37_RE1M-NLj@HZb$4S=6oJ75HiInYxX_vOBMOOf!<6^@Q?L?j0ycU8HgZ}-*YP>O&GIB!lj0u9_uZHeJ=zj*DYrolwU&SgZtCrPJ{7ACxW-aO4Vj0BrMBtvLfZ9dA zYCBE50cK@McjEa;dhY2BzUdD0j`8tvIAJ8uLZl813}E>rZ0iFdsx2%mw5<5u+f{U@ z;`c6+5qZ;(?DZGzpT4~Y?B8F<3aXe<+ouCaS1CzJnq@Be+fz_<8k?J&TUr7F13{GR zK|)D}ryt%*zb({^C+7%%jJu`i0fSneG3?Xi253KU?x%o1K%fo@sK;XUBr z0EGVvP*DB^>*_cWCi=OLvSd%DNMr#@^JtF2I}y)L;IT3SzY*mGej}-@W5Nmt2L~w8 zJzgg(&?^IZH$|4X+QPzh`Fzs=YLONGFdrZb z86CyBV=(7MAreQ!6BiL3HHMB6`gK)zO#L6?i|5ed1@O_( zzUAcPG!3FBLD564{NAW1kxFa-K*YnoB%h(i(Q0EH!L@A~;R$3T39>KhIt?x!-UDF8 z%gg4i!7!g5$IqXCahX6WEC9M%I$O5AWxQLgz(V>XBt}5Hl#`bivH@Lr zq{Pv6d(j2%RC!+8jE(d57j6L5aBr9x8S!Yin3ya(z6b%0!KUXWCl{P%ca>n>;jVfi z2J)HKkKjFr|9Ao5dV_l8q_7Vimt>hZEufNBZ(E>>FTIWYxz`-mSNkn@AAjr~UeN37Ww=8!>{4p zx-}tt0A*s7qm}dm6=xKq%I&=o^Y7=GY2UZf)M>RKEARGX9#K* zD9cXaW(NkB@1lI3 zaYyx1a*+mOAfC4eR1OX!`{DHX`0*&C*jthlBa-K%Tw=Nw%!doV8%{tz6@WGt{!Gct z++4-sVj5}26%35V*47>FAPoA4y4{D`Ze1$VgL!rfazP1q@bG?k{C3eET(aW^cF6RQ zD<2BA7FBSGXA`G5Qy2C7zkb{uE(WL5NzS*3nWkEw_BgF_JCQMNd%+2I5P!DN-wwdlK=K)rFvyV>)5W??$Vw#K*`(A{xj114dfs|pj z5&~~mUtjM!0x!(rx@#UJ2-RmI@yB9q#mL3+)C*vl)F@D+WeS(D-2@YYEfRyTL8D#`3mlE7c%K851FD#Tp?k>ldtTxvD(BnY|GTVJfy zWe5OthL3M#$)~jSq$!t){xbk@vu2JP+llX>yF&Yry)oCIYKXN1B-98a z0zl+p9Yc?3wg(Bc)vjCsjnjhpzQNwd%|FPApr$xb0SygLwwE#>IVs66udik1AIJxy zVYhGJK06n(lrHCXzCB;|e`sl&_67)mwIA!M(ohE6LDf=}PAEXxFIAD848M(yjb3oF zv1*Xp*WR_%{WTZ#HO;~K;El@SQg?zf-Jh38qGzohUUb|6t?Z2>jh4rOLC_|EY!~Rv zkwj0~6eUYWkp{1V(7K+g(&#b*+`OkbT`m9HK4Th6ka7%8dw)}{);Ju+YzjXVm2UN- zsimb`QaMRH>>WPSVsP6EoF!D}&X(pk3zu?W+xd^zp9XCvBqWr@in-;2lKLoH6M9Fd zrPO2ZG9Q|DQwOb#Th8V8X>GA5e4$4AdK(_9Ta=I!fIBjSaKt8q;=Yb^Hmb8F<2k3^ zvNR<=p#@KP!7WyKAJ07z91|aM9_ZQuXhglge*HQ}krHW^g6Gi+XBcdHl$&J)Nrq;L zQtqbz7g+T?hkfOQ)iok+1#*+KeFr{3M@m<3x7giS5<_80#lphE%nV`}Afi$y^0|?% z?Q<6{fh}O6=Ml|~^yW054jzZ)Ur8oj6@&!*ZiV=7;&>dT6RosIH^wR#?CR?3ObrnV z=oA&aQw#!NYZx)oKqtC8X;Xx#4JHrBDJX=-61j8Qyk*thHlz&Sn00|H%)xfD-6i9a zM3?V=G(7o~4#TIKF|%c_?6xc%Mw zhl6{&XlS7{P>@h8P&QaTQ}%sRFUT}(d4q|sa1!Pa)wt(y@J_<~GRXHIp}a!|(u_z1 z0}0gU<^Jypj7e3FmSsCiva&%glKT47v#rtK5XsUTh5i+jYK|Zq{E!~9*DPx*0U*FZ zXCIeV;aA!ttn?u$i$cjl{$Q+df*i{66U4Dap$Vq4?O@SZg)j7(=T1IWRrLNzDiPTLXx^-WG ztTs7y?Z=Sw#2ftX3m-@XECfgI_9uCY^NLph5f>qGPbAz0Gr|w!jwgG|z+AySlLcAN za2k`T6s((eS&zPg4!2=Lx5^D5)}zCg)P^Cb;2|_BXivpUTBcn~j)n9q!l1d63ZhlJ_5I~8ZE9zi*C3{)&$VdgcaKp>*3MHg*_Ti26e_Tge{fbG;3gTq%J`(u>{M09 zCr4|-(_ydQm+#{l)#QuG;)X_tdj#esdVF}w$y;xgGGc^10=R>jf9wkW&okW zD_}Yd>OUme==u3a3l%M?q)-Ye(nOm6(2p$B(TCCjeW)Y}Iicm-%OiNjyR6XnLt2jH ztfZvRA?a$x^~~IzErJ}Bn+(#YS!Vp~8<44>%?S;4Xw4O;FdEcU`eBAYPvidyD#fp} z9mP2s{-e)NF$-Tr8|MZ-))(-7_F@ej)3;-~71ofomCbi~dF(+{L|e11Y^mp=Bi!v6 zb<+vFW7=D)x*#hePLQd^XJsz-LHQKD>8g4fL;&|v)`T_hsT6<}$-ngCW;bNiuY|Uf zH5eP`0qqMCqhw-v2Yi<#;FE(mPq-6_bp9=3C=IeCq@|T^FdGxqq^45uWJaS-7unSMUZuWt?Ngx+&5uPk zH?5?ALceSt=n!jK{OJ%|pQ-8gf}^_LK0eXULd+B)ZLv1F;FBIP1(FD8 zWocqs;t>$+!_6d6cqm8@H^CNf5bP`gT2bSW_WA;D9sE=7_!h!!v!<8qo{Eqxx5F|4 z$SQ)3Ai!rCN*Wp_JH5L5!2IR_vBWe{kz-vTNfz>{`zMP5{d^A6tc&K`wFM8!GNt^#=o=ZOUFO~X^|Y9ZVP;Rc@6Szz{(fXcL<%uB zF76J9-ULBq3XdLD`jB{}5<Og55#SF7d(4mHrRGizUpLNVMtQv<4pD-^j>(&J-Miu{z!)w65 zA9LPv5ZQZXZvUU4M`WQ)Tf_nt38@ppK7(hq@F|<{Z_eJlX36q`W;f{++qwWklrA@; zhphxy4cI2@TW=-~TqY$Y1@fS4$FbO#l~oiq3nW28Ts)v5^TSZNa9HCpP6;(V? zcRK<$=5_NL3`3!J(PeE>fBg=pg+`H$!A>OT5NVf12bS19&AtPEd>u|c3~Go(*ex*% zodl-xT0-j=ayS$a7JTvG`4gVDXPdVnYlB<4DqGy(5f8yyj&YRg0HTRnzUd+hIyySa z^|{Mq{oWW6L5BiM067h)_(?%Lx-h3|V`#=fM-iIaf?i`zQ`box6(VdRsi1IqJ$d@{ zdJLu_=uG(9ZnA9Vz&(WZIiEwaY}Rsr3+ior^p%nXSL)p&T)8uoLeSqU=y7L$r%qQ3 zdjL(y{hjUE^)o0>OiTonkX8@Q(Whg5{+yUtSRSiIbJwI^4S`Mb)2w9Z|9}+ zO6$s%D^6f$>CprIGJZ2FXO}x@Zx6KA*U$2Gc<;JzFtquag{Z@E^=Q8Y5Z3HlYC&3Y z#QNd=VMenCTPyVbQsko5X67++Suf{8fZ@)aqz@a5}w5-sI|#BhN( zc5r?b0&fpA^r$E({4VY-bj<;}Sf_|d|Hk<_ho9LSY-HiLQNcPLHz9w==lA@4$gp1AvNAIigaxO-Xhad?iOmOVz3(& zwE~+N@t}s()KuW#`wzq9dv#-x8r*s8j#@*pn?Ug5?nHuuI^sE@_pfR}xg_NsI8W@K zVetkBk-~Jy5yPPsQII`}y=Ov#*fg=0dmPi>D+LZ+le)+)weR5GqSUWy#bZ!QB)&;V z2)?!#wzQB#k`7{Z;4>alUdP0I=jYc^Ao=D(8nyqI;~6H;j&>b*zrw~uC;FnigAZyvjkc3mj%SMg|6ZByVtca$`HL4XBK8`#WsrBdDLIV)i%#Sc%l+1G{lDB8*7xo6 z3{Do5tSmx&Z_n_16up1|VoqOVfp-IEUk*kX9RKP_NdbnRRR##i@a=E)yqgVV$=yP- zI28BqKgzue&2Xu)L{KSH8w^pz6P3k&yrVmBW+gU&4pn`DI7}cU+q~T@0zgc0j7rUb zPR`FYW}N;Nq})+Zs7*{vNUNAX03uN`tjTY@3hLaC=e1V_lq&zErdiCR%F0U6#}^`H zHJ?3u27VI5eo))&B?qA?LL^~}eQ@v`1aZ6ew8jNHR9yEnh_YL8Hs8Vj22HKQNLjc< zKszzP>=@F3RZ;E=z9SAjz`-ec!mlp@lwR&J+Aqa%wj_0fY`$zuH(hrYS3jN3Fq}D# z#mNQyAhoX*cwaOPH_J3BCB(!!0tk7XvN1TUOHNOYq?*wSKnF9fvs>t_^+ts*4j1LR zR6_iMUh;wP{k+pX70%WkbhpGJ)yVPZ*C4Tys*^__2RVyRYEkj0%>qS%y@_GbyF@3s zAEXJ;jA|x+{`g=E()5lc(Q>B%1#yx#6eeg6F0z2ZhvlHa6Ix5%P;;Nv5Pt7WY4|Wl zn)dODCde-Z79$|1Kvs5H0s-IUAXedT4Bd_jNx=*fQ-&@lw;}sv?vz(j|F`ya=OQsr z;w`L^pRJ4qPb|(@_Cv&rKF%Gkw)Z`>LGIq7dUOXP+rcPf$jV5GGTW?-=V1t}oNX&& z*y;#06AnGe(V`q^H!Pl$PLUs@dMSKd9eZKPp`OTbUVZ%fb}=3~6_r^X_(}oDN=4XR z3M%aD0VxPcs?HL3u1MB3HUjUkhs=w%3$vKG!dd5*Zz+TsKRz^(+U_(_JJ=2^Oh zhKWhtH3H^GS$1B6ShKLr_AT=fVf<+dUrAZN;?P1D5Bju1$(FSKoduR-jUiM^!ODO4 zV6itNn#&Ie6^Guorf#?ID{OrFS|y|^N##UeDf`7YylnH|Bnlr`!xq1{)w{ccKDda>EwrBHFhg_-#=Ib@y^_ z>!*<=H>%Ce$~5hBz`MmpCNMA0q7%e z=(V`5kmr0s+s-#?CvJ@d-39Qa9AwPC09XscUFZ^SjfrEWf1!q^%Bxqq`$^BCdtewa zRv_C;?wEymBw_Rhpz*W`5#%250Y9{!tbt@OTIPy$LZN4E1|69q8(v%%?=wd8_14r1 zbb2&Ooiua?+s$LeK7@&L(p5l)7>n!8`A z%e5OfIJbhnbS-oTAdNN1B2F3&uM}}8SXt%jJFh{rDuuA?#|w3A(@D$)*AdXALB1Ab z%r8i50VWGIfBd8ZGK3qXI*=FyIA08Qx6s9Gp8;u!vL>4%4e;1H#%q6yIELvZ}yTpI;P(1(g@ zxoM(VgxJNeuUoP8g=4F}egH5t3nSrdV+PWYETg(eSi*hgS6udBC-8qXp~rUj+fW@An7Hmhv`3F z%Yah+A!#9BUY`alJ-VUAK4pio7c9Z8N6rAaG!rE@{KzW#^Im3|qV7>w2%mw@bKcertNH{FS*#vfSWEG)! zI`91R@Zm$y4BgLv`oOddj=`_WvdkhL9v%R8&^?0>5$6;@8E(S}`#*>nz`T(mcTm&@ zST0;NQSS*JT36*LgKl86btL7@(ZPqX+>w_^GoIiT9SIs*->o7ez|T1V=6WGsIP|*r z=KjTMV;86@^0255jW z#R5%ZPzPboVhq-wot+IC({i|wg^EgK49CC+;-)YL`jOy%LK04D|-WM)ii)1$mF30`& zcj4QbJ4zu9O0%Txzm9z|!^?m*;Vb<5v)q6)@4?wXtcHmGNIj^~D4?HUcs8v|6?m3# zR%#7z542G5@(z2W_Br)b4LADOXzBTF-&|P2yL0E8o=KfG7%7*8z&_mQ-Q<+9yj={_ zIrjuSN~L4CFDcG~3wg0CrJcxecq2vNw+Zx6XS0+n932iOr@~>7Zvd`5c(%%+g3CF0 z{K=r;WJ0lAzr()H7laRHcC1!{GOhmH3&~}YQLIUJRPqSs1usL7yFI6>k2Cam(i^9> znGmUyO?djtIMZKUjwv<%EL+ZppD~>BzYNFXVQbvW)Po~sp(X1Fe==oAL+*{B`uxM& z&T^N^`u8Hb@Zy-8UfBb&>io_=b!C+iF~=sDO}=C8Spq+NNN_O7ECzz^;^4M)T_3N4 zwJ-E#jX~GL$%m=|?kx{YtrZhAoGA~*4P0Z#$whvpf{sNR#naDA zRPGLdcM1eiLDHvBo`CCCw`Nl_2WyL*zfU!!u|f+E+91x=)PE}^Cha`2g+mc;G0|DC znd}T;$22sEwh{#GknPydwh*=w>`2*|oJsIef?7Oagao^o+4tcOQOhMtQo6dIE7IcM zURW}WXuNrFa6qbyC%_YyuciF`c`XP+B!H*DeNwEva0%L`W#9t&^5qM-|9PqwY7L?Q z6j4L#Y7DHna5Y!KY3gkUr84Tl3lxT*MdRNEa`b5zNH}=AS^|k&z&vg0bwzy@${0X-7Jt zKTYhq{2fvlvv5vib31f;EK=;7c*2 z+eX4>)+2t~ynSqLtn@P9yuqe5){%L8*jPe-w|z*Ph+hZR3Uy&YZkfRyv?b4jW^KVy zTY4$?L^^)ESPtxY_qbvD`SVlALEt;`00$-fJPDVL;21r) z^j$zGiJ(`lZob_6J1MqJBoSFI1>Q&keLtA=0N$p8`_1*p}P=Z~AG@_diY^lFLwe13@4ir6#>M2Y7w1iY-Qkqf+6G0?JTITfVr~al{uj?3aH7~ze);YijD^nZCb4t(myBKVwRfgJBOgU&&OA z<0XJwF!kz{P>vX9p->7div>AGQi013C8@=$IBor@fobpf&A*P6^&J8PhX3@fWMMnm z^`M_AmFhPH1&%`x)Xj9lrzI_)l}jYC@$ixf6OMWr7LRkzJyV75B?ztH_d`9yZnV-_ z5we<`dk|mAR~K9?gS<~ zprRbb;ue1|t-Om%anu43mF^3s-Ko0LQl&rt_J_Q#7GFNorL6eQ%4Pyw6tlWx=;y&H zzJP4Mcn%bA*w{{bABU)?Sq@Rc)A?OtbjrZwB~t^U8`JO~>Fd@)K@1MQjZI624H0`0 zWCV0{led29zsE(kxz|9x-&^Xl1a}*tOc0Txn037xo-6l(LMQCuQU18+f*p*t7a=c- zjAYLNiR5$H2IZ5vSgG(8$e1wO*V>vtH92Y5I1>a8JhM8L#R5;}Y6J;8%ddfslM6Rs zFt01&FKGmWr7ByOiS+IZ7=D>6%i)h;7F2A_h938y6|dx3jHs~* zTNTlGe(pPd4$Amy$V=1WRFoWy>3*Dl)IN$<6hX_0kgfY_s+_YBjjC366{~F zX0NrqkOHZD_S$DSHw=p_nF%nLXI$5vrrhq0s?_#?#74+w=qm_MZ?J|=?(Qg<*HxJCGAMv96{Msa!)NuzAp8v_9W3}3_;*n(;8cXc8ZaM| zw%1&SaF@ebxlPk5!u_LJ65g^qKulDW87!k*9~L}(q^5?#;0U?~5CT$fJfSUE z-4SNz62o}@!UZsi6hjokY7zZpS_UQ|E$lMT${@l;*peZRfy?8ox(pzI>rxm!Hd0tC z4#ArKNozq6q-Nj&rf)fne^q)nRWd+tnxPAsAWPy7N5mO+35OzJtew6=OBH*5$007(X zKo~g!FPvmEI%g37O%f8zCsO1;U*$(cMiR6VwC+eBf6z+Ff>59Who7*psc@!t#i;io zT6uF@8=fkSDHs4j7pPPG`AOS$AO>zINGm3F#unmfSzswZ^jE%QD8-~hUOzv8R@s@M z&RJz&YY5L7V6B&R{2P?dz;0mD{EL#35_)K!aR!VkyGS1lfWpiB2#{^Mau$)8kn~}G z1ZL(jI8?#5YA6Y{>7qn}rf^q*X0qS=_kV^GhcW0g&Vx_gt=hlOK_Zq=Sv`M4Hrph$;E>A!uk$?cWKN6*$0M&A6c;;EreILjB1O7_1d z_N52{em)YP-N-jU<6uTMtzM(t4QkrJFVlMfSGL~T!u;t}XXv#ToWPf|g1R_(F~4gP8f{wRL3;BrKN3D+k-) zAtCH~0Uqk%At4Dx5yp@kE%#*Pc8dYP$d`G;fasl(kHE@I>u~V#?;^`b)S>`Ce}C3I zEEu=N^7;7-$L6DJD8JSCBVdb)5q95S3_WP&Kv&N*mW8&w?c#+l@FJQ6o%O1MJ=j?@ z^_9cg!Wn3{$FqZnLBP0wLauL%S57m3^Ix?--fLBt>`bgSJ`<~ZktTm@B)HV#;Xyg^ zSAlE5^BvUrC?7m{0Qy0~bCU>>T7R}w&16ED(>H7Zn@@n&H+>L*@R_vO+0iYGx>F%> zCui^#A%3heqcNBSnN_G00q8`?ZI^0@+?MMjR*PVk>I^Ue>wHs1Q{NJTPKdKTPd(bd z%@n~;nAL^SDYwm=LJk9WUBFklB>&I$%+6^d>LEy+lf8$&#a+kCju}vBjO%z0rb8eM z44WDo7a*o|)}fsagMpUD?t%@REw*Qb6~F;oo?A*6P3Mi3O+BH%f-Dl{=H3W!B6xom z`}2??k=L}@&`E1Opax*JnWr*1W76n#%{0OU2q)w1U9fz?Y$JG%dVXzw zexiRc1o*E8W}u!$fm)t+88PMNbY)pqLaqi6J|GQ~w}i!tGa!q0UwE#k*Au7O+=r+U zJr`iWVpcVuch05=Zb+=&<@qQ2ChdSErf8pOXqXS`Q(^#^vIK|7EC(kDPScJ!{2(WR zT|UIH|KmST12QpMrmY@=QJ(A}j};s>aC(+vankAkI7JFZT_p6amhz#dz}V~8dUilo zQ1R+|9{(SKaOGctkPm^zceI=f-QDv2FSEV>Xn`LC5kY(OpqL^f9x@Win!B(Wpu-Zo ztv_zfhDS1u6>6qJ=ZSJN@!BN}Oib*7p`|coEtXRF58v`03bjY*)jkz);V1P$+~^FtA9m{{)TP_!+ug{r`Zc&--;`3_0P? zGca7Bch0T{#R#7Mk>HhWs6|lj z*uLodVmt364~78rM5ycoNVK)l%KytXn5Ze_p8tSQDW)Irv@GQeH3Pw27^N_++g=?} zXA{oRQvQ!U@8LZHcKAXOGa=$up<)u^`?{4?~Y^EN})zS_xH>%;8ndr zKlk{i#>K~1u0H=q#S0hn0gkKRot>c6$W+U80uGj7mHRAsk7Q{a%murBDfmgn-{S-& z`EKWg8brL9`~7;%ha@Yz#K=)*fX%Jqbfv{T^9aSY*VYnc8&kw--hZ<(tF&M7WmYFx z5_@Tf!0=fHvmh+upq{~|Fd!2mVXeEdb6Besh|LW~oXCR1p&fey!^PmIdmbYlT*y?vLWvLlK1Db0Hqh6HF|~rt2Q1%+`@c42y_4oy$%~{! z>#!Mrby;b^uql-0`+RYF`f_@1oBxiUju%y>@&d4jdAP1&tscLZv_I7VazgeP4*7U2xi0 zabh3Vdbqn14Npti8P%)DpriO&7qItEoPfBo`u%-0Uk>yHv}aKQzZYZ_e+-m5+v3cv zGtkj3!K6)CE_i!9&8b}|q%Puh79OS7d zvh4lja|N{X6(2+cG2j=h6B@k0E)^E^8^KH~%gVOk2^yPkYdwW*SzD^2Q zSa#<-$dV7bAFVTPIb2!)p4nDB=})JWrA1Wx68wNhpR9$+DU@#Tu0O&#dVhf`ohaC# z#i?TP1I$4RrmWk(6}fFqb_MOZcoj980)n^z;%DUyfTY$AnV*A}4<3#5UXfpu9)nvRB56?(@CN)R4b#kY_c^1x!4Ky1n^ zvuJiPE$f55I0trib7{A|`_9hp(J}87aqn_0gs(Bs4>PxX((> zjf>^ubB%BlY&;4Bo8Qth{q?yA#rrd-2Qv%BBqZRmEehlead06Kx63Xc9uCeukc9z^ zXSq{RW zuxqA!V8zkM8e%tB99V`ieD`TK*GuNz`NkcS{d$2JrLE9OMVZ!;K1r%zR^5`tY z^0(f^w2zOF$vdEHVXc{klm0*!g_G)mG2a7J3JFJC;mZnaSXgX$_yY)dQMD6zwgHHN z`gw;8^z;ZQRnF8~aEd*VH-+>c7r&-FkCAzgzRYTwf=05m zm=0$f>o8~nmhAihY%CvSqW%A2@6DrfY}>d0%RJpO&mm+g#Z5>9p^%7*B87~R215yH zFlQ=}sR2n8DO8eF#!Qt`QW>I%43$jL@O}<%*VXep?|Rp}e(U-E{`jq5>sj}@pS!E` zI?v-gj{Vs7ZQu6o82A02H@7t2c(G}=y445o0rPMDY}bg!z3DM)n0f`?`i`Cci2(hH z0E#DkZtI?i=(SsYUXpvA-$Nxd%7?!|uB~8O9sfz5-iG_9w9aNY_0D#>nWEn}AoJvu zBiwtLms>nx-e#rdBJ^J@h$HxM?dsLC8TCQ!FPSE%mzhqRmWd`5N0~GGpKiYXf^Mc5 z*3KUJDDlqF<(q#!*w1O%iV;+Y47JK`DEZM=)^+WhW2AGIyEK&s4opP0DN<~`jPJWO zKb|rzb>9^Sr$`umdBd}Bz^V*Nkf+;S>PdZ*q;uDTZgD?9ULL5VJ;ud?W;P-ln968; zSFzG^S4}fF*O+%>8+z68Gmb@{)=+m_IIqEXr7P4n5I?U{REfCs`Y^rlC*$Me_iK{{ zf9jC~IAD*0I zoBCZ?5fu5a9JjM$EBykp>HzxrhJI8&=O5`bVgKI+RokN{$bAt*KyJ`w>w>U*r4!oQ z)vu%Tz8~gbVY}o<3?4G%!rev0CGm*#E*d}W@(8EP^+dy-l}2BLi4Qd$Q)O4ZWo9dE z&0JVq>}5lIo^K;SYccjz0fb3ebB(oZ8p5IQzyY(3*{y9@=w5{#GMF(4N}d23X=Af_ zlGX$+wapgy#ulEVMp3sU)T!(r{eL&3{a+saBdL7_-vr zEg~k*X}P$S;d%c92M+l8&AKr0FxzG#h92aIo#`!YK0DCI$JoL`KD?xILk~7d&0#A1 z_}mgkMA-F-TI1m_(`U~f392J8N5j5(PgHkupTQ#=dOb}E)c(0$`RumHGN#=lngkEN zZqsgb-0!y)_nx{yj$2KY=tu7y@5BQUWd(B^x!$8?jG^_;E*(}3qhUE5Tfj3 zUu;>rU{cfvUOlE6R-1NpC)P3lTOd&YRJKY`l$T38G^EJKKy?Y)=DtTa&=HyRrn1m`>{5?m zFmLBkuN^XEbl8_02@004KPa(8;}F-`Qdd{!c5u0{Fg0y|$3Pfo@!BE~P_b`#MII2H z1fcTh2}8+7CS385TJC+ zHObUaI#}bJ#>}KLv+3j|cwUX|RkIzlre|r~8MZX@4UQ1PZ^aD9K4atay(TPK@|Lb0 zR-HEDn(K0!XUywR5=4gG@utdo%R8}_%U43Fo7t?R)r56sM-oMjmU7JUvaIt>nP*y4Q!WzwY=RQ6~! zoXc3IKenCTEMs@`@ug{wcl)2rTzh2ti%o3|PibxKEU)I&Z{Wc0=t82MmLSJ!)S{bk z!BNHUiV1N!VJ6itA?~06pA|7Dap}!T`uY_-gUy8<8`O$ZQB4$oeM}jFw}IGvGDUGUtSi+3$^*-DFV?R+$I85NM}w?cb` zY2EmsI^n>Y%S}tqsfLg(&3alDbNS4fGgJ;-nDnG2_tVmzJ5G6BRFvjFLNvGREL>wh zYUTaEllSf4|H%1aapu+^3IUOIwH7%w&G^~w?EIQ$7zizN{PrR3eVqNbevekKsy9q) z!w;j|A`NH&2$(kd>Kj9pZg}ak{FK*I5^K0h>!b9E)Aos_SSDlYiouuE`$mNN)Xg-Q{6Hp9~u;%Cx29n95&t znxYb@r6MYEy9*kK&hwJ7;@j{gcz5bAQd?x>OVoO}~bQ!-_8 zJ{p;odn6JvCy_{zyUbw5)i-vnXAHs|9!#i%ADno zn6A1fr_S0k-q=B8IHN^|GxlM~gzegM|7ZawGfM*l0=gEtChzK!o#c9OxGkTlSNk^K{;bPZ3 z^s=l@d55GrWp7pOzJ|3imE5{N`-|&M6BxcQm#8&Q|Ag~m!7+THSSGxI%g%H@glyio zd}?;!hwb~nFEe|hw(M~!%BbzvCpoZsU~la*g7wd62E~mz_JDl-8yo!1#CPOF&!7~_ zN`{XFQK1+aLg>jIwKB-u?(&D24zrzmC}jm{)?bqO)TKPd?fdoaK^-H_p+ki;1d*h- zQk`x4*=k+UNR+)j&0Ywys6an|X{A2)K>kNe+bJ>xX?O36j<=Ph3Ae(N14#aVA|x4Z z^JqY|j4 zet_7UUE**KO5qAlBRvKru_DeNU$hEq&gE~!3k4>Ag|;y^IbL%}d(iQZ$F_E(w{TkK zb<DC`$*ut_K+dvJhvMb z8U;CTZ7)6@w(#ygwwaq3Otzg(viJ=JZsYYd~QLE<7zeG`R@= zt2=1X*RXHOb|@g6VO9EQ?C3X0%V$HE(UO*WO~=(a+DDj>!TO^acJs3A0AS8RR}GrV zf9!ZpGjIC*CON-S)OFm3P>%zz$7_E_4}p6`@uL|}SC?LGG|(cpbpI?nPsj1dc&4C5 znp)%Mv^crX9(X~F)U8N2D7Bw^_lk0eCBiP2NvF%Ib%zw6jVlhL^niR}l9p_LK4L~rp)AeMXea3+qtU_ko6(Gy;ZXDr4!uF|NRvjWC|?aST`&>ZGT3Up8P@-jM#(93LJTM8ZLidzp0di(Wd2R%ADlAz9s zb$CHX$$TT7$kQ~YpP6y)C7^fLmyI2J^gvg7kqpAmF0TLfzk%$+Fv|tp)kxk!N6(h! z4CwO@T-u*J1h8HKbfM?2`*HKLqM`;A#UKf+Vm;vH*fI5A4=z~@FJf?%FwN?IL0|ul zmtDhIBH=SHyoSbTx_M0c_L<*4X!kuccjuuiMOE9qc;`5QnNbp18`Q>A?)veMD+$Lz z^Gd1||B@J`^BUQX*5R*WbZPN=W^EPK;%e@K&S=Y@*3nj%dm61Ks}NBG-%hMnGS7dE z;l+uA6Cjr6YxuVNJA*+1OT8h3xD0|n-g;2qzC|oGb67d3&&PNTp1LtZB%ORC@SlJ5mx5$Bh)twP9zEQ;DMIFZAL1?x`Px*EB` z&X*4Z*{{keuHd0t8MH$+*U#o=J?Fo_Q;K}+m zH97Lb^uA{#jB9b#b|yn-m@-Y_BDt~bl+mAYRrpKdLBQGabjnI>>~}7fqhA1P?G8Ub zzcqRKaC!3Xt~H302F!{X5STMA^*8kar=|`{0Tho*c!zcESHQ69?0EI`OKpbo=l+AN zt^xCAJgqrS8U!@e#ypOZg~pij*(q}b!Biy8Dk>kSH@gvA@Ud=lrPT`u z_i<0Ddci2ViFWnqin<}}ryu|}B7b2X&Ax(SY#cV`IqE|@iLchYAk9g7C9*&VM! zAB$p%^7AHqV|d{!upj}YxJh6Cso|qDK;fhmwvQuw*!dl5>+@>U!u#*N2b7o@&p=ka zsYx5VORx4*W{*K3J%0M~apT58`BUCqOGZ!$hUtnsH#@V<*Q-6M|MH4UBP^Wqn5r&+ zw#>7Qq&yLP=)mL$s}3Y7}jfe!Zyi>hd(7reLcsXlP2|NDbY%2D{K{xE@2pRP^>w z*p#VJp|;*bNCbl!u1dHu5y(#%XWOk{5)LqrB8Rb0t}y}zGm%J763Mr_uX-?=&7Nop z?PVj}qlYa!_~y)B_pW}rF<^g0jl$*r=ZA~XiPgLSr}&x2rk-LgXr}fdXw4;gksDFy zE#%ce5XbU8tqD&sSc2APH$zvch8Hql zpSVkUEf>FVaE5vml>vgQ@Ij-6N_frSe$SUv#Y+><4YK7An4Vl#St&V+?-9oS8(WM# z2+7E_hHD@>6Rra^eRYLW@9Xa{hSs~MS}Pun_DGy41n^>z5Cf4*iUQBGo=$(Rg|F5Ze3T}N4U8Zycx z`T4-s_exLw6#VjSkc)x>-A1Bu`G^X2xq@d7njIzlJoeK&{oU)z*1zjyp`oTqk3)ZcrDJ)VYbwluOJNM%VoCw^lO_!Q^XsYEP=E@Jg}C{M z%G<~13hFeH_x4`!=hsKi8o`)n%mNIM{Z?PtEP%rppFcP3t}y}hekVLC>hsPasgKuJ z@Yr2zWPfcZ`1aN;gS;gt1BUVP08Szppyc!3C;bjN@hRiGX=!f6L%73oT!E{WO~*W) zN`s)$w_HwFv!A@P- zX+MrTHW*1Z%qM2MjT9Qgbj;>*qK=U6`R8&vmW5R46)(bKEe>3> z2+3-g-k*m*+A~m86G$XjF&ZrVDb(GV!JEe%(_LKu&lMaG^R+%xhyjG+*0OI^Y;Kal zRQTtozCWM(^W*MrQtLRfmJYzbKfjXHHDtj5{OBYx-~Rj`Nn>?VYw1s&4o$aS_e_=j zrF+LuLLUFm&wuATPR^AbucnaC9Q<>6$^XCu{r_L~Uzr#G-yOySfp1uLUuRRbU2H&M zZ_MC2jRT*0of}o)-K?dGs!g4F$qQ9j3P`QrKW ztq-=)@fMy?5UxSdY=FoHb}t?&sbfm_^0aADAdG$<6_WaQLGc7)}OqpZvAB1DMg`z zssR!A_4#|MI~=3md=#A!xEvQAoWDC1$Uk#&z)-yG5fP~uNpC^o=)J*csSN-FYl$&n z0`c@5j)RH5dU_|Mqrn2%W3LJG5l1C}WTL&?);0mHq*qYf$p!2v8{nP+Tf0k$KERZU z8UflMU<=R#W2%Wu6DYK=Mpx_nK>kVa@wCCa2^eQ)T-%kbr+D`m{}~> zV*}aNsuy+d)&X+TKfB?(!6@ulRMaXAHYfzY;Rq{ep961Jg$a`k6nR*V2tRp>Zf$D+ zndb(ho~`A!@}_Vfcqh*LfHC(pJZZ}HxBS(~Cm;Z1IOV|p{e5cP?hs=YxVAVHl67RE_gG5nd-m@){po__silPQ_wa zIevbH8frm8uKWnsPfAnjfrP2Y3>zf~r|OyTWW1{0gSxvbaJ#}zOxfHI7N2S7{JLJt zxjYq#k7f%~a5eE4MPYqV`HcsWGGc&`IE1_v0Fc$;W73gdX&Ud&-0gzt zwgq$yNYXssdAW-W8oJMzIw;PJ`<;nPwkpQqY$ek(-rrS@xPR~7PqI-6gf@5febhfj zY^I)!h`K`M;uGUF_fV;l3RwYo%k=;HGXRnx)wUvJ)oZf%(4m=VE`DuYXm|=B21WCi z)`jhfNWMpry}^aqzuJ7EdZuJsoG3P}6}c8a6UDUfp+IGBZl0dY%l{3*-6eUn^pnu0 zj(V4MIvdWrK2u7OTNn1EdNvO;GBAN@o#rB`dxl140#wlvyqoBGYjVGl!UO_6VM=+) z1Hwsc?|P93n%#cb)AKBs7g`D4V+-xiQ}a*jQIsT!bIG&42t)7!zUJ%thSI0IdVKD_ zn(<@~P%X^<@0Xufoh2xF8umR4p)d3X;;@~~9cGvMEtCGy2HmUuYL4(liHLBZmo7ea z%6q2O$qr9vf?NXgo@v3lcJ(xrz3?C%W)dVS2p|1fGrS{O9@H7o7O-!1OyODZb#= zCNI}lL$>8jkbCQCC<%+9R3;(*M z=sXRcyH6d}%q*NuKugiHqggFtbS@PI<`v}9@$}m`!jn}?cYq+g+nHI2c-=2pb_8dg zc@x*p>n$%Qjypk3B-DZQYCd2VfXb#RUlRfrDne${RDKL0wNHGprOQ8Zh(qDs{tT4F z=~a{Cx^vX!1J#yfG#~yXlEd9PkB@yD;wPj>)4qw&D0p}5St%2x6pu`iWj`D4wi)Mn z9vX(-;VpY-#PVos4k!ae*-TZ5dq|%)k&M$vm&!}$f<(+aBa_*)T_MB~53Hmh5basc zloQZp{~aU}2@n(fFMOfA^d1{aOfuSZ1@vLa#7zvh>0U&|*K6WL5Fm64L4o#^>C@`U zM%ahEFX(7|eC3msY2oXC-4@}Vdi2bn>YBJ<1VGpE$LURFAn^`qy^#X|O^Ar2y^wkd zp>1w*P8R!}*e>7PlFmB!!l1ePa(^H&5O4R?CR(6V3BXg=`0*Ix1PGC&GaX=wzVab) zSdMRE;n~X{%>f0|2FtFqU?2E>f*p@0%H4`8bf${K5$a<}R!FhwLDuhJniMJ;*zBRt7UfuN@g0p`~1-GH0$ep#Zw@{{z*B?_n7 z?lfM>4r58Xk)92(4CPY`n!XgSS+lP$?QJ7UnP#1OPz`~8Z5PhLy9+i+DISSVQooKT zUZZg_Ne`na><@z3vz7E8)u4->4JFDfAlHPKQA@Lmp?04ago(2zeSP%;TT2J3{uY31 zKY2OP>b=e)3jox`KK`6}`hHq|=yu)y=oyo3&(=8Pamwaj;DSt*>6rWHr*Xpu$1@*@ zhk~5bK8sbEbHBD>rcvUxoR2YYp)81L*w$~cOQ~99-IblSzJcoRP$5>*R<-B+n}Kv> z7mw@0nO}ORX?A$VRa-omG*H{CBqC|63Vqb9r&IsjuB4@;>A28i+qVy#qVYDkc+25YZmzv;Y+6S0a@JWS zKw=hekuD#1$<#p;o2$%8aPhi_?#SZlR9~&xYAPz>ysoU~k6B6DsyH<+bQ~*P*g6tk z#};N>O!6y8**T75g*v@mxCWq_O)#uWB<$!qi?gz*?0#i0!*30}yUrre*LQljASHdZ ztUi-(oHmULFgE!%C(CXL}NO^0Wi* zIBS4(ACM>_!OooO*leuwCwRK)QA&vZK;}cY%`~#I)-%bHWm1vA;w@m;xa3za9AeFv z3u0`$X#m^JI{%po6WdMJPNX24rBLhIn&R5v^KY^7xF>#6AR8r680py{#(cl@q%WPd zKIcjMc+qT$DYfF0@s89pFW(DY{U9Lw(*xL>Or0Jz`HvPrC^=d+JT!9s+TJ#zShDxN zu`!HwRPw8Tc(LLHE-e!54juYx?75-L*^Qi(WNo{2=~7hLTIHdB98E-W4*)puMwjtB zdX@#;+_B`@dUDyz1KAf!U>)07c|-Aq1WhNE347BcWO~?}&=XYNLTBpy8uOR)iL32W zdPa9pLOC{YV1%`8zqYv`9=_ooo!?}rHKaYdeZ|yqJkbAb=&?DKFFUNW5Jj_b9j$m% zBCFK15yu2i?Kf@X4W!kG5u%c(ZiN zB#5j7`fOUIx|a(<*Qe`mP-;Xj@)RjNc_IrJh3?^-zaopmqlpFvC<|P2hEgT9x|#!tl?%U3CpY=f|D-<|q-DAds=^4js&~Liv&?*S zTGmA8=I1$S>a_?i$-=QFcmC$zam4Xz+M)myPWc_n;D{nZ$~%Et)&>cx=O{K?H`veQTV5A9f}!jk+D=odLt6i0>2TaZL0p z=>BcvILCt@MIBZeiA(DMy}BsEOjrEWZrhZmlp8~iXasR^eR_ZK6~+@GXB4lHiHa>I zefu!9he~-`Yz*QA<4svX;5)I`Ee$&+F9ecF~@Q8-O?=z7Q}3mFh$E zQ2!1?-Z-Oj=}5) z^&e6$XJS0Yz(iE|m;+UGLlE9+B%f_=9!KO9Wnf!OMe4ERvxWzhB1`k9^Bk#XqKI^MDop^xSwFN}pQdqrWsrHisn&G5?Lqz=^&Zb-o(2FA5SUZq-{M zM`ItQ<$)5uE7A3ZgL z_v>x2U-xfmeNIx}i&ypvN_5H7I3m=XD?D>YN2A%ZtLagRvVUGpl{FQGsnI~`!+F1N zyR-Fr5H4!i{0RDFNX>4Z6bFoVqmoR4U!+?uYo++pT@eJ|j~bsIC0^op^!L?O#4Q{x zmeM;`RwCQwiwCo6gu?DQ#q9d2a*060HYl`E7!N>nFipC0nHY@HQVuj^Kpn>I4*IgpkjUw|$!UA@18`C9a7 zmi>BC($klQN(Zi`TFrqgnk^#E$Co$qzaZ(+qjBe$F-jZS-`Fs{mBoX&fsUtF8kuW6 zGB)45)ZpZCy#WEcx33#-W4Xn^A~#H-LFmTtUQ_#bRaqMT(s6Ts<|un_<5(K zMMU@O-oqQMX#H$&{F85UMm#SXk@nN$o%6OA*VnZjx1<5--*ZUoZNn*g>JnlC~~3N8MRRxhXE|oJEJ^w{V2;%CVblSIVw{m zI`ADQot;b2jwA-EmlnWQPoF+rr~t=#b-OZZN+pDyIHdaZ zY}xA!(zV*RzcaY}M{@$pI&9FXt|MB?R5E*y8iE%#1b-4(47ABZ_e==Rv6wSQNKIny zI!eRB(E#I)C-ej?Mz9cKig$1VH3$(g4^8T}?R0nAaENYC*>lViKKZKU(G>m`0e|;x z()S~IpxSR|Mo)IB^(Ml9dlpj^{a=e!TVR+|39m?~CS53^aYy~Z-_pN2nqu6s_e#N_ zonN4zZ;VOJY?w9}_D$_y)35RUX^CrgX0cc&sH!%#myt=iZ8sYY9*z@!$bR;3qHE%y z>r~|}knIS**W@%x!^T5o;WDag)8h+1a+YEfe=mgCq?d9d?w=$hS%Gq(zG_vmSz^=S zvJ57w9Um6}9%84d#gCfT%1Osmh@2`wC}gm=NSE6 z^;5B>=Nz3I-q+s?x?y0yevK`1Bdx~XwvvAMsLIriy~m0}JMt^@o>x0*1*T+A@3|-T z^>m(JHezu>Zos*(!}Q| zj?_cpSf#f4UKJ;?Xzuj0|TwKzc0qvWO(4V`-St~#K3Obt7>#_?y5_gZNBxwyj^tbiv zo-hu*bv-OBthCmb{rU`(x?!rava)(v*D2!Y;gS5n8v|c*fke`YKYJq%|goj#)w$%;H93OeCFh z-z7e0qlj^cuyePbP@`=;dGcgZ5^F1ooKjX+*3h9ta}4W5834D|C3plIhdzCtnU$Tr z&VI?6W5-_PSK5Z2KAl(IrTXyU!!rhaeVfha60#bZ>seX`d~4(W=zLmY`q%xzW z;(odr<@I5@ssXE#D#!|GrR=ate$hbD1(;unimvg9CY#1uwe5M`EmdOm>1;EHd}pr) zgA1N+G<~tTepLICzLH~Q`#*YB72(jsPwnW*IG$+xwU=tEN6~S6X%c4jKA{+O6;(? zXuCRCYjAh{8r;WtDt8z#Z<}m&cJr}DDvRw?zU=b zY6~|MBC;(-tBup*b4xy3RJAE6?VC^O@8K;_ce~dM&Mpa}4_B?!qVxUTx<6 zdQo#Ygotwj?tI*OZpN~2*=5dJhqOA@j60r?FfwII&Af9ndhTgFWJ;Ix2M;2P)+_tm zDg0<=z(l2{bzxsK>*qjUp5JNIB*oS+$6T;w?{!sgj{g1pTAe-Tilz+74cS7YP=i?;~hYOvfe<3X)uAr+F~7A39hJ4mW4Z!sqozNlkT0(v-9Imzd*6 zs@^Xa6~vTfpKqwP(j`I8y-P~h(0^Z(y|Ib z@U=M0hBG$bt~TUwJaBrrqowr5tyi<%hEmSv_|pYP^5EYGQON-X!Vmq#HO`!w=;spu{Tot3OyY-{_0njUFQ z3l5GGOdK8bcMvu@(6H7O^*6KR+>8OG{psuiom|I-1$UnfXa)xvV6b zetgixcd^A`r#aB;I-9Fw&5`pEROCJ%M{rn4Ke~7+RJQiiojf^(f?GV%nMJVEM4OKb z>hjhU87{D%+VMozB)?(dK|wEzM%Apj)tBliKhdUvd3Kj=-R#!Nh`Bu-(wrncUolm$ zpme_w&=aw@fJ{{|;r<_F*z7?ccI3ORpO1HEOch6s8nvU-YYaD7f&*mB-+h>#)xJlo zZ*^LX@~TE;X4exx|E|!e^8!i-%2+Mi{nz?6(q(m_p{x-(Eh6m~7D74+&~u}lNV?l0 zwVgC*AH6cQ<15LJmo&~o}ZS(8QXWQnRU+3q^AXY-sKx@FZzQ#`eC_NvyN4-_F)PaH*U*dj&$BBr5^E zm?6!__frv1biq}j%@i%sWe2hm)JOO%jJE&zaet%F&e74hUz%jn>ne{M#Mn@mUW zAP|5s^v;6w9Kvww)Em-~J5KHY+<;`;;O_desnv3M)8o=#Nm`w(tvUPe|LV@NMhf>R z>w8R7@?CVjg=^`?{aRN(OsHuleUjd)SFKA%;+U@$pJT2Ybafy0 zh8!rTd`bp8JwLyqI}0k4mDD^Mz`H*5s-nU_z8|Ca(>9B%#Hg))K9B5 zYbri=X}^lIp@$D2ZgA;*=-IQXDVAM`@}Rv!=;psD`uzF9Q8GlTvlbNcX2+b$d51+! zMg2d1MQLoxg*carPY-;gUn+Sk03)6S6bpw&Yasajk2_y5c+JDf!-qx-$IR(wW?MT- zgQ&#X=UTr*Kc9U|5Dwi*Czz&$iY@-K4>S%QH1Rb(CzW$*zRZ~%K6_=#P-c$RYw0|f z)a_3a1K0dIvGQJGeN}#o-b(d}y7UfpBPoGg?R?U%kR`wmSUNAn7cuA$xcJ5yXUP-c}C zBnxT}l-eU%8ZzBCnhwsZWBr`-z2mbN5X^-57Hj|S&~9qaj!Zn^iU+T-Wxapr4*OY0 zta?QU0Ui1i6y;WBf+lNp=E!EkFBDNIdile{Q{G>K(L}bkBrm$fP99M(|v%h4bWca6tl5DJrpxydPzT`LuQ?^wEFYOQI?#kPE^g2%Ls;W z*36SB9Tb|qcDR0WTRw7eo~ZhL$4gU_ul1I_-!! z(Ge}osi2^F^kS1t>^kBzL6P>9z^2A?=FBlNItSIt6qVe+VA}lAFUy>1WrR}~ zN~)UgUNw)I@U--xIm!N>VUJ~uFc`A5eEMmQ?0xIH6UP1M6EiXBfbEc|Coqa?Q#gOQ zgzEM)XIBRNV_H@l&l^3R0HMO|f~T;vN|VDuhl zX0R&0*7!ru9xE$l@z~o1mbesYdSrLiUb{-kcj?C^(wEz^w@BtWEYYLf#Bjuk$Vi8p zG)_ozD0qQxWAL`mBr`&=8}WkTm%y!m8Oq}OZ9y^#2FqW#soOmoF}|zgw1OAp01$#X zPbQG>K&(3yR8T4Bz;?fNGB#Ov3;Vqwt@2&y@l4S;$(f7}3GmyC7T>*t)8i_J{cC5_ z>C=Uzr<1>I6H5O@9g$-tt$`jr>}V+3e~TtRy{dL)!C;~Lyj9LN7GfOwmz;E|xHlFz zI{B$pR9W+p7+`ykty`pQddAu*gx(H+e-PxbZq&<#k;S2|G9}E10D(!Am7DnswD8Vf zw`VJ7lMLuT<-IdTjDRIYnmDzf0?Qnq91rP$K6oY|23u#+8m(vVJ7fuy8t3n5FNSMA ztQk(Sc+x6 zc1IE2GF{aNA`Sg$bVP%yRlOqWqW9kGNbklv8$xa>TwJ}P$?K=B?>t_9xo*A->f{vd zViVY{7XB9t=YN#qlcQDK%2;em8vCQGjlMLVbu`dHaJ8?yeF^2oHcAy`<^Q;$UtAy& zKmEyZ;kuw+Q+}id_3p@aJ8sr3qN<(x@3-`T7}7=EjcTUfx@j2QXmu+!t`uzSdxn-D zm>G}q=pou&eg9|yY_b)g3LNq!GSdFwT1PXxQ{2B5U_^l!0^IjYKKUcV{k;;OA!uM-B>*`wko^ zDKeshH_606P~jJhQxG`8BYPMiIGuN)c35K0ucWgr4nP0H=Ie>nB#>#s_lq6wrxuN( z*ce!O7*HXormsBl$R22y&l|f}9u3V3`8Z#;W2J|{_*A}2thPCvMU%wovvFbYXEbyj zLUV?&g0_Lfxs_K+)<=Y%Kz93{R{8Rg*Xc_2UzMT%<;$1JwjI%jk8B~GWbSW_CZ;ULg~=^T9Q_#nBEj6 z7JT^MC#q|de1Cj?Cyvv*8_+B_0E+8rVv}7r=ZU_CO@~hIIu#zyCdR|La_X*NX-dGyZE{E$sHb0vT=kmvV~Gp8MPRR8TY@eV#K=6gBRRhjc?r}?KaX+ z=e7dYj33bcGR=1sGM`69eq4i|p^|F4efTsMG%)g4@13Wva$pnbpM4;g3132bLTwkH zlF0^gBN%7>Mr~0S7dVHSX~iF5S=aBS_yy)APs7^ z7yXRza+~x0S_gAyIq8>0trkSYVX-IU0z=ATW@;*0z-d|+HlF-C?3T)Ao)w67ERh*n zbxPu5gm6g9SEDey<|&0tlKKJ&kc{O;+nAZ0_SAhz=d@PA&LLwa)%uLM4uHep!jIQ} z_5vNkgh_8aW7}d;EW?7}QDz1{tidX>J;in_&`OAa^W$MRMfqcdtd{C6u;E(zzUmc; zfJ_nQ-+%c7H^5fviMV%+F_ewqFRF;ts%{Z&S}lglfLvq?0Tw7Qdz3@5*GgA^(?KkR zMyZggwJLq?pG6(BXyms`|5O&GPxb3JQ%yFf7Z(@*$CdUPYV>zNnbWyedaIxfcv$sh zd2)kPdZ5Ps`~7mLj5ozGXJOB`xw{PKP9VGct9NTp`}OZ;?JD9;wHWoUBXp?QfSn?G zAzf}<>sJqc6|RN3TZ>WgWiB`bv46cNlD!rfD4$Ez6pzrBva3i~FK`k;S67)5UcnoF zX@$@Qt+?BNR}p?*LT7e8O^W*^Y6215n0Jn2dxi&QXJ-p5T#>hok`;m@JBTzF8ani3 z;8HCi89@%89X_jrtDqyMZt^K(XTyMW_&%cSCzlbr%vX?hSRf!BJ5rYT7i}wZTRg*@miV62DUrEh{BLe33hK7c?%iut{9FM4Pq@IzHrEEAUDJhft?Df>`*?vdYqs~G# zR!2kHq%X;Zk1-EsLbLy`Gc11h?pwtfn*Ffe5q6P{2AH|?V1owA7#6V%RE*iM&1$i- z);3TL(m|3Wd7Sufv-7`6ELKV_o<#C>H1WqX`Dw7MW{|64J4$*Z|I?iIzj9dyqFizr zvgWkI@qF2nBWOi!2jy1 zv5K%wn*G;@AR!+F!&0(h#*Mu!qf~y?P0!PU`nlw}8}K!D|>lwv+Yoyh@KAZM3!!AQhx4POK!O}xJCv|XgmEGbH2!iqFUP8Nu5 zH}Js%Q3Io0XU~VWHK!92Txo!y`zFmv_BgjkvRp>boSB2=PtKW>Y-)3PDA9K-q?lgA zOB{s`wJOKd#AGG1Co?m%;qPRu)V4qv&Xx_HSER0{>H6!XaHtES-JBm82S(y+BRVy| zX(2~44y{Uj!V$KZe|*RP;t7-vuXKr%9X@uTKvD3kxh{Q3g|%$v`*HXY%==zfVOd>{ zx|#mp!spc=o(o4Z?Yy8v{gssB$V?!coM;sZelGN%i1(sOS4gME12XlDo}ts0@=QyH zwQb*C5bM8`Ry#YUKk*8DeiCRV?nVenpfWO+{lviL=^4#~(t*^u0UqfoA`++knw-Wg zwHj%SLxz6et`Gi#SLD>2EL6^qGPjVXi~46HHCd33TF5)SjXL{zW(Fo!KPZP36%}o5 z*=yjy683WWzvtzQ^521hg%prOeZ4O%T%9Ml$!q(?cuHX(JT z&#m)I(1doRL8@p;BYW5^zi5hZW`eBA&*0p-F>=xmOKb@noqkY-Xss?fNl*tp#$*U_ zPkgyyEjaL7P9?gK>J_2%UU6H$GkzZr>lS^Kh32HI`s~;=i)cAKLoSAdXc)6Mse-+; z_NM>q8*^iq&(DwN+?PVdpGQQ0?|(>s(tLz0af)j252VT2 z?QIBol6&^dnZHKKe!oC)S0v|V`SBDg3Ke%zUS%oVDo^SmouRsceC9W6BqGTO{rNBh z9_75*&Hu*r4;KD6h`r9tY_r1WR*c=#&g%AIg)%rND1t3wZ6sAdzKT(VuC7-kc%*;7 zXY22!FFeX=mK(07CNxS&?3(x=p$+XnhG6KIvX4T!7q@B&BCBbZmfCza=>)RdP5&V; zI&#E~2+>FtC%YcL6F2)WzIZZlZ5Y{s!&{grm)bK)DC1VrEc=Z|p7M$HlGvA@tP z*fv&;R^YL6BNYE#cXvrtd_qs4c8N#AW3`22u$Nd{qkmBbg0zcWi`=nx9WZwrvFX9? zc5T~EI;{2@J*tnc2v^V>bVe8);20Q$BPm%9QLG&nPU zE2j@%nB_!}u0q%*9MEpvx>e}JZ`E-}7an-1ZTIOOW|2|IsX)jb{rMUrjI6(e@$K)q zCwh(K@DeB`zv}UkD6U$#UazBIuuOf)$Y;x72yt=DK;Ga*SuOj~BfH8-pb%8d{kh!~ zRl1AE-MYzuV0Tu=vE6*b8Ok-mQ+qD zv30uJpfCn>MJbz0(zkWeExxh$bdHy~{PvsuWGd4qRQ^h8pL%I+)FbLjxF_tNdlgo? zN|1IBhYU1%B}!xr^EV1>^=;Fq_FKiPdi}X3bv;XwGcImXO9@;xORa5Fz2hvi^`D_d zh*HZI29kZC)|$;Os~XqX%KQ>-xQesOY4PCP z8V8cY8g#8OZ#~-FnMv3Cd@pSgZJAS|Lg(2*j4QRB(aI$UN7F3u*`BH#Fmm7f7^rL% zlBIAy25YxktF3+IE1HbY`RYGoGXZzhpa`;gH8N+v6s0R@u2IwuU5-+l{kI~;!X=5; z0-U_rQwXrxrn79bSRB@BxvORlXusp;JWx&z0E(kl2a|{hmQl1be?Fw^Njw-ZBl0L! ztdy$x3l53Y1n9G5M*!l+y8>B$4rAtU=*1#tS?Kn3UJcV#`R&Qfg|oW3D>^G`>*SS9 zSnD3eKNO~G`6TrB3T{!j=d;eNQvPd90j2L8_SJnASrM*7p}5-G&44YvdvcT5+XQk5 z`xKl*f8^oZw4!gq+m3~?EWJ0X?w^aM?6nO=7hTCP4^UM#e3`rKUOn&nn~mIKjt^?; zJ*??*ov?m8hn*PId4g42YXo@`+woRy71p&~q#>yg{sG8ogh#$fw3TvR5b67Y0L#i*vLDzbgr{i@YAnv~bKKAsE!1l8Q2X}7zUk#- z{4(W9syrSK!UsLktp-MPT+co9&&`^3nfEAaOK_87(=wxO@}6G11Y*bGPQ7f(rJLM> zA$@oHOe8P}#*$q5;9G@b4C*`JP}-{Pijbr0rtN<+`|l|4mk zKw0h~9zbX{4j&D;)Z;#xgb-kf5@}-#2cApu`%KrbGFssFil)bdpCL`fOT&9lz0SNS zZNfZDcx2T@!(*dB)E))Y^#s(XYW%D+9LX(rH3X5GbF)B1v?+FJu9i7q=G2P!AKTAXFNbEjb9kr51T54*Ba1{qsX)-)M;X zz}690LJn0HrzV3g*(psDYEa@NP;p|T>}wfvf0$69<_nMC=Z9@q=PW!x6mDoJ3X=MT zIY4|T(p^O#1kaT;gSYVi@or8{T+Y1=>Lex!&Fouo3bE7VelcI}1+m~(C^vRA*|7ulFdm!*Kmf_#)oa(TUBCezKixWtlaBGJ zqz94~#mL(SBWO%%uO9g1`lG~?xDAzspzN+YDvfZzCjSR-Hi{1qwUSfMcTd{zn#}0H z(W8fK*GNOm3O(0u4=1Q@*X>CagS}ZCZ3U;u7|^^Is~4>|wyfE4YOVHFud&W43t`af zCX1HPq%r`0%;5V3u5RkY%80(PN_n58*DY+i+30ppkF;4WHjjZuvVZuKM%R#y#4;9| zoW*mp4AW=A-QS~t7)VmW!n%Y2a7o=)H(S~?KdkQG^pv!1;m`mjaU|keNs5OwWEC)xbAH}wa2cp>dzkL z&05OYE`Q0-iFaO}?;P_=n&92;vH6gkq;iz-E6TI21_C$QEsi8<-Q>;gWaWu5)fFXO zmH{t43P^98%BRK18eK-*XmUJwI!havg6i4#vz)Mi#@*g;#(@3Trp?+wvMY9sCjPlN zdDl%&WCACZG2kZ^jpNr-uV2|ywk+h9U+ZUUhv|c;AV87eL=jWweLJ|z5tyLxhzM%u zqVVb^4m@u$GB!S5%h9U*5wSb_@#Bu_?IH$I+*Sbnv*&vh(xkBLhtK)9t5>1^ex~VP zVSB;8%J$Ha{UJ4Pn{2(_r8?)bvQ9=&`kRpMYu`x}HV^x0dHR5bf<68m3pK7Sf&(z+ z>@aOC%LEt)r}uyE!fQc6e28)vjp#@W@X8;~!lghMTsf}73hQR7ut(~hT>JHX1vOm- z2c>78fuTRNaF1!YdmwV{zMmF&vBc~T**6_KTR>Ox)FAZnV+z=wthULV|Zw2*^wR!y@S$E zWw!yL_%tirMNGD>oRj$;h!Xrv^p3HxIjx}r+H}c|m^a_unT@pl|BOJ#2pXW(F6g+q_iIhdOX%45fl|KE675WVXhEc<*{oUXAY-a1Jo5N=rfqp&20-TMn3>9EXLnxA zCzsf{y5S0@a{Or=j*MHXwngH)b9lR5<1T2)=BSKtB1VJv&AbmWsW$L z08BpW?YdXqBn=dqgiO^lFKEw%LV>ZCkzLeGN^xH7(C6f_V?7+ST31vXnEcDd&8J39 zWMbhpNxz5nvevE&QT6# zoMvLOcW#c5uEPPST?p?Yx7B2y>K@>FQdvlY6u|PIuC9khuU@#g48 zJL=iM`;%ei;^l{%b2+}S7{!3H z!!`QbRZ>kgjzmJY)TJ>D+mk>kMP#)+Oy)xbF`;dv^D@<7JDWH`sF@ifk3Ko@~yx zGLmf;6xHc|y~49I2E-6rc6GN~+i;40tv~~;P9;m&==a8(vDw!R#htIs#R6Z&&oAv>Q`VgedQX9npab#9To3yf?(us9PxiZbYybDJ zO+!DinToRp$`*NP6rX~!8{B+UH@YI6`ESBVNR)=39TsX8JR$E?Cwiv{3x2%bT!Dq2 z2T0WX$@PRcM{BoI=aMUZz7Kz9%yJNdjju&_l;A55?UpE(tQ(lVXTps+OWmjGSK2zL z%YXH0=B@Pn=N_-@8462y2EUQL`^(GOzn{p?9q+O|bJ5UY!|0mXGUk{{`NL0FMmZ|B z&iP*DHhQ#2&0lryEtm1fx=h8}jjHv_Vo6nq4;zP=5!dUd*92XPt(&5ixnj9k~RZ83kJ?+m<}_*FRlp`t4x#mZc0N`*K4>C>m%oDruFiiAbv3$68E zJ%3YO^|R6Lfw0ECe-7jT00*sSWv6OyW}rBqV6sm|hsyDzei$9zt2UJUCaKI{d8aE` zHA+5%(vCj_uLLzhV!8mVX6*Wn7gT@uK)g$P|3u}|a5tj*B3;?r2HQ>aLAl#qy<0@q z0YhpDP2{~+D=l?83?%?T)zyBOyxbi6NJRl2*h4S@faW`gt-a_`qtSEE1URV`wP9BO z`>P}?vhZT8n=F{3*NT&G+O$tSJXHD0XrGI$dD5pFenPS(4BQ?aDTZBau$vcD1M$Wi z9qKp!czRMB?M577YF|`4nvV77PT8vKCKFpS{DVUUmfcNxFMElhkN=DTPFd5<;I`|h zav=0o(VE?P`z25|sj8huw_W2n<1*)NN`3y#p160crks;z-8bfCBCDu4J_Lj>#bFr7>3f6v^_~ zfjaLB8KGZ}q;HYNwbyj?isQ&VObE!O6agR3yd(0Wy2;{f(7OSGPYT%xwDG*oCB?e6u_Luz6siq;o|;IPV;?B=VXpz zc*&^&lh@`6Tb1-6y~)V}FWhiTsy(2;u1$VjFPS!5Z(daR>?;}$@o3N)&`mVV4ePp7 zwj9;Q#l2cxa>6^GcBBxmxf$*%CqedF?m=n#on8T<+!(RysgDD%bX;%h=fQ&# zDRZc-q6|wJLMo9+1CiRFD{DQ^<6V32V;}q2f9{Uo@gBeTRrhm0_x=4|-|ITh^E$69 zbP%`PlyzAfWboh2!#j7>&K$MZk?tl-X#mGV_*l*ZRPv%)MeG)C`VfU%5<2;-5wyKh zLiSBuG}Z}Dd_@Lp(lfAc(@Ss;WDnIfz@g-9WVmDXpi3Y=*>oYHq({>k`$TGs?g*zK zdMZr^dH;;7b4bYw)szI7rS&3Gml=~BL4S#bZWJ!>5n1j`>do`zJV}5GsWe@H1&Ysk zSuPP35iW+he8`8U{^s2;9>mv$#@Xv|@r_KrVW%L#l7Pr!>jFqrdq|?QvA`{8P;7P? zWujs6KRXw13SphMPfJos+{YmJdR+unfPTaObLEdnL&R-Ov?PIhHk=+;2`bU+z<%PKBMsk{7Ndkz#Odv*&4wo0tnBTFvgKeDfrE1;}(Bgvbrt&BO!guED zZNv#2w0Q8tWe|T|81zHEfw_f|N7MOa=e;c_)-zPi7oG3NbYn%NaUAYxwYBk6$|U1K##-OWDw-pK0;zQK^l)^1d3Sm7X)^AEC^H-^ntNxB29~8` zv#QSCr6f%hbfnDd*V8h+HL17Sq9eeH_itZ`0+=DismPcK2n=ZGh&c3>$65L;kXVOecFAForhWp;rlPAe*K)V_t zL-hTsjL`fo4N-{Mli`AO0}Yw&skY_@Iuhu-MX!AIjDj=E&mk0;&3GT{@W(CZq23V7 z?JBhs<^`0uQUS%B#_8VwC9cIL3nvCt%7prZt1vIS$NE_g5@qs-Qi29^6l$+q|2!O~ z7{PLmU#o?(=K)Lekct$sDaXKK8GX!%l+PTWh3Sh$k-;1m3a=Eeng2#twYafRQNC~_ zF+fp>3B|K(ao%Vi1@B+x98q27oNuN0eSz=N2AgP?rQTgGwl^dcM|fav3qm-_f%zRN zH7Z8Izp_&H3tYCjxFMRc^kN_`YYvE=S+w?+mX5AxJhO8x-<0+a^9v=jxS4P6RXd84e7fnkRPpztaY&Xhld)*B8oFqb%2jwbSGR{D zEEgwafPxB5N4IXwQq5(%?lG9zJVxAc3SAt(8bSX;K8XqmBQ55UG%yt)GunUd#E%Id-qmtQV+;h?Ogsu z^RVJ8nC;>8`8*&b8Lb_FVUCXCUjmxe=+aEB8G9ToTRy57dn@S|ua2^KPdQK%1O+r6MsVEZ)Q13}a&WLDAyhr%V;^e)Of zpFNAM$UwTC;YyRvs|U%7-;xRmIw5@tCnohv=|wNwZ=&S2>NJib0M?*bOcb#3GU%h? zR{UvO19QuhXuWcw&V}wuso-v@xb%`Wp1mRY7d08a1e>2L${e*%zSrC8-{)iiOCZ$F zq|5DSYPNI&lZ`kunZ_y*K@54sql9IOFRN1r$})nI5*=k{1|vTDAcMRCQVE98qFq7n zF|*t1s#NOsNC5ja<3yIg|23L8znHl|P^l?jmvy7<0b`N=Q1K(rC{--4Tlx$i@d9XX zG0$r36`KwkSTW3d_c`@}WHt0ohkM#6?kLWHJq#vzX};KFIUSY>6~Vo_=kF$?7Bvw& zUyNt*0{0pcWRia2VGYS}dw-l;$nCBIBH9!-i8JlI6u-l=P0}pFd5st~ji2T-ZA?r2x<0W zq;92f#{4Y=R6gT;R{SGLck-u66_hnwisXeOvBh;A-cIr9ap=HxU6A4e8dndJ*>+^} z4pC2Nt_qqIJ#fvoJT|^)$Ai8S8XdMO1x}x6#XWVeV5d~B^4m8(wbfD_5FDH!voJaz6drN zCS^RbsCn&`w_AzZ)t^xENeX|fvtP-A>;Ki}-AHK=@z@CEcqpZ1n+kw<;5YIOJrl=5!pO|zSxpDF{AJ=3K$-aWN)daH zA=JgV?gJ^KFd6s_)sEh^T)615QBTaN1cp=%Np_xdQ4wd%h7!9i4GdP_5_8R)fq+(G z@>hS!t@f*LEwNRaN4)MX_x{k{;kOO9C!f@K&+zfPv4JvuyVBkcSH|Qw?~{(!K-W`| zMSG9KM`APd<-&=%EkG-(tn>3+-8*xY|V=$fugd=KL`(~`JwLp#B~d1BeN_6GxqCZYS>HKOGtx6Yp?9&ezc15N;aiz(dD_iTGhm1udM%0~A+p>jnAy57Ac zth-O&U|%$C+B73kbV%{PN$G@sw4uovxP;bc^%S4`+E~g`s8f!tuFWRGYtRRMI`s}3 z{qF3Y$~DQxue@F@V z%qDRjMi-k~*B7=_H9e5>#6K*5s4a4ofLb#lNV5Yg69= z^$YuEpipT}=Nd$EhJguzNE`Rqh_WQ5c1UMdF;X<1YP4bdEKgc?}ck6c0=>~*;VcxS| z`FIMS&w_FZBBT?dcAw5>iG8}ix6HUvj^cIe=nXV#<{dN&SQon^+xNw5OiLY4&%{Rf zg8s;Z#-|OmYWNVqwSB*gP$0IG?t~2-R71Kr6TLPp{Z(WGs4vD|xqDE=ar8pAKC?s- z>CA+O=qlIab`Ey!B|?Q3OjVBjjix& zr@)y-Wso1w>CF1+_cvW{8zBaFgt%rNvGoityafYaD4^8L-BsR_a&oB5<0uH5(O>Z) zaW3SZIn^EKm>LQ|1YQTsz<@c6@#O)Bd zGLUN%aDXSz4qzt5Ng~q{K0`uX|6}4^#TTe+c5TDcF5vK}1)=CkmZ(^rdMdj^oO<~T zpL3Ure@BioWCd8YgnL)~m_4ETQvA2LxvG73i+-{Lx~uBQ^Z!2k{{KHrX-K2?`aF^4 zpQrCEO?Uk48rshuY3q1Y{kU}xXj#D~aa6he@oyVYoDF(T^!CRNAHFlM?y2#{TK?uC zP0M<~C7pR_PuUgkN*|SlqCnEA1B!bAgQWZVaeW9&1R|uMc@X>uPh-H{j?MqiJ?M~Z zJ*L#{61-Ad#E|eOQ2lD&wu(jaDG{oTKx!1c@~J(3ld`e`1~>oLJ?wQLP{a_^BM}iU zuC9OCYMz={p?YNS7nb7OpJwUvQTV33?)h)=rjzd4w%o0uzj-5bOV=BJTX)cSGMWYH z-COjEil6^kiAXMg{L_iw=(Zw2@XVr}U0wamLv{`QrRMoM3;)#usHx@b`&WhU+K*mn z@)mC0Ra_epAXI$0dBZfHrGU@xhuyxfpRylG{CyQ~mo5#>&(7n$IG}A*+)(srBzcPe zrnb-R|BKDh9-5@uw(Z-C^PVjMqRt~PqqGOjqN6)95}lK1bNL@hN~tH70m?)V8KJm| zILjI#4uTOk%qu2A6*Kt2@iJAu82}(yNg7xTSo;WD+pUv4=$NNt7K&fg+B6pq*<}y@*5eMtI2Vd=jkpIM;p3(Dggiwj!6Zw zT?X*ZxtJ?GfYFBx(rlqaIf6xjEqWc=LEi9jFHWJ`!JAbuu&$pKCysY1xpj@+q}};R z8ZzUpf@Ep6QOf5t-3{8c>q#CV5>z61NB3(%J?5@fZ?^kONs;0UpJ^hM(}sguChRy?~WZqh&(IV$a)sd(YO9#8B2iVOkCcW-fRHz5)Rq-CN? zA!jA^1{0b(j*U8$^F_c=O0~l5RB5x7Yu?X?b09Y_RAN8U0npl#Gqm4}FG7Yv=3Tx1 z1~VKwu6LIiDjsYA4urZnqH)tEhkGW!_ambY>d{5@76iEq1w^m9VFzOM9+o3HR%>fZ zshpzHzjBHeA4}y&vq#o6$2?+;TdC=f5nPo_M z#QgGDhmS~2d%CH7(qX|H(B6EYN(BHRDHXwai}g3tdd9<~CZnMQ%Dd%&zkHd15l5#e z?y>^!Tf{(F5hlb;Lti73K^hoBY9a5EUU)HQ=ZL9%N8Frv^W72@f2<~~lYNgD3@IdW zjGZan1$a=4uOG+y(3eLMQ;Pp7iJc_9`3X2=OBC0S>8iNKYYqA%8Ej^=r}ug0e4cJE z@7OImbsF6ddzrI_qAswonLty(^HT1-e|GUR+vaj=5g7$gx2=ix(67pM98i(b1_^d4 zw!^r;B#tQsAQovQ$2ZtC5B>pPDBe zAecyMU9~zzy?93}UmZiIv#rdH*XTIz9H-%Q!~U3UAr2K+lv>jizvq1fmBcz` z1${?ev4~QZ%p%3>GpmV??vHw=C6-@j|1it=cqR4X=Z}XHmdyUrWmn}tejRMG&imH` zZEZWOT=;06ZRoa^m+Csr9=mO<%fOuIv0?Mi+B~#BdPcAP!(YeF?4#3m!oDc8f$cTU zn4Pr$(?7GVWslZ6v1S%VT|TsksZ%G=`qv&uw^{eydnN9}+Kxf>{rUaU4aw3F}`i9 zRvAmuzu}aW40h1PC?-tts9sp4%{M**gq;qq%z;P)UK83Vzc+u*;lzn>;M_S8s(J8M z-hEcK=2|qZ5mI?Sv?o1XV_70lVnA%Yfx&WfbI0!W1gI?|me7DZlJSW^rp#Y|+gXXz zh3@_9M5TK%GT{Q1p9s{q#5-{jX}5vpgZ1UwOjpe0%v=EHyFU^BfyF8;J>{5i+_Kk@ z3bHK!N=T@YPlo&N&k!olmut;K=%9*W;dbJk-^h+HZ?EM)&FNgFj{p9e+Jj0y!?kwM z&f#x#N02g_g@tg;wI!)y=%Kju8Qm9La?}`}X-m`q|kN z!4YADb?eg-Nc46LSE5(*2*>-V0MP+oB59|+bs6Fx$hi%-Gwj@kw%MYejS8#}2+R_i zQ8v9)>27zQ$9q5LWON=C4mEIJeuo9(@vKe^UL)YFr%#{0!rT%mxaHh_c2|*UcpGO` z@i*Q_h=MIZS$N5d6opyLm!byN(Kj&o&eQ@rW~R#|N>-m|pFPS(Vi&sGtMFBp17R=7 zeVk8NUW|TX)dZQ8i(~xDfsMyUL4j0J>25b3UL)jz%pVn$1A+N>kd8_h-w<*5P9B6e z##UVIsKjK4KqwZuqDH{*W;ESHZAX<~tFzpY-U2ixtLMyDyh-PvhUO7Apf}W6GUdr;?xCXztk#U_HTbTCEZCGy8 zyLk&heu(88Dn0NoX*FpMp*|5hzw2U4-rF&9Q8~>ybMM9-O8xc`hvpvJ-8lcnCY%gs z#yq7BY{eD`P@jc^A(qe~v)OyOc&fuToS7cvut@)I==AA!&D-=_cRC`sYnjzCl?fJ;xxy!vg^5Ar**uB8bLMjXzF?XCRQlU*k#nbsa&tt|Y}y=9PE^&-+DGP+O|$u& zgfMngWtA>wt?JyF3$rjdxb=4+Svux@LpzVI37Z~__c+u}nH-0Le9v%!Z`03~#Ed_w zq(1i?&>v{FUSQeZsfQ?5k1>8N4^k*9MR#H^t0(^u5J>4a{6d0!>h`SabIWZuI(HvJLWL)un`wB>e6Lo5`m)Lf9{FaoYl?t z_iWNc|M?TbWSzd%75DQeDc0DxD4Y@&@!0rkR$|R^;8X9+x{BXP0cbw+0Db?~0##=dj?%3fq$)J?`>=DxL%rHXHrt zrV%cL1(}kS#yc6kFdVcK;wYg6KC8ihelxQ92N^g*N>)WX%e^Xe7Mc0TjGw3-`i-!{hC~Dp31Q^DZR-1a7ih~!jM$9)tyX(W{+j;l|GxLn{!;z#z9Tb=WN*_o7(QEM&rg_#8pO3e%)_s=v<8qKNseyt6TEu4)#MVsd^Y)!*mmHG;a){YSUCHJ~m!R8}*%x@a zFm3Nq{yLWFLO>#X5v3c9M{Redgf$U^H_6+D1LZ31+Ux6k%pU&M89AxrAo*Xsv*g8v zu0nZigIs~P`f#=bun}#gtv1EA-Z9PyfSeA=Z=lkyoB=I29eUe3-suy0inK=(^7uby z!x}-~W2ZHx7ERA|jpCWV;d{2AGgmve>(t4#^iF>-81o9lzHMfoZmGvt^sOWljC)s2sCc)(2a*%B2|(f1^6R{#cd}7bk|4jwu|oyK1z))bLs5q47?3aTOVwxaYQ@3QuTAv{##-;G2Ixl)7H4C&odXmm zs!|dAlbZo4d_x9qcj*LjH=xm;6s;T|lHyQ7bSvzVr@VS_TfZu@x9tpY8|)gV`!XRu zo-#-DXX-<6UxjIBuVmyeY`KZPH|!STl9H0BDmqszOj(?2p}+Vf@00l`M`lFOQyQo1 zKg8VJoSEkQJnmQVEAk&Y&lVnAu&<1#EE8%X9|i>l>D*BKt6JiK`xkG#Ar09Q|N7*I zjkh!OvsqWHxuS+|+hXs{i7B%qseJ8E9|erKrfft|+r91JC{5tng`|Ja?w&_2`);|# zcPgRN*Odr>TIlZ^LuU`@`z`hE>Sl@upk~p3$OrWh7grEW$3cfqB6noYMM6Q{*)PW0 zg#t{lFJ2TVZqw{dL-VG*tFh7|;~0MEBt#^>w4?TfA91Y`5@~^BXiv7{DiuU=e}To< zTd$C2676eXXzoB!_*eyi*RB!bf1Q*~&6CS3JORTh3;KyqIgQh+H zWp^+HxR?WBLrwIMsdJA#QW6n|Mvj${v;itCFU*3dK4L1P10Xgz^O9ohjv;3XR)ygz@(7q1=X1O`#+{kzrPska=T++JgyX0Ht>Zw0ud2 z*4H_)(_J&|TAWv#-+1F~Qk#UZ0WF6=te<$V-t5&3{dhC#?ZV!9ji(BQYf}1b&KIxb z)?4DUN+L#l_j+XB?)$fg*4p`}hw9d^ILVfwvftZIJ7m=d|AZFjeFt0*uVHq{%XLrs_JqCd*3<|g(0z`${(E0L6La~6c^|tx;`R)eKK|7ugjT#YWsT2x zjNs;^9ooNmx|36A2R{)o7j0F(^FxQtKK!E0waq@N3NBN|&Gph<)^ZcdxZ5NHvWSVQ zp5)Fjb)XB0w`XsYK#ry}&`BSQ}qX(-SyHIr1 z?DgxgCD=a_=uHc!V!_DI+C^$9Jhr8{Bo2Q#gRsMd$8$ObYN3azi$O$~sPx4U>}J}u zXy@dXM{JF|@qRu|+`-Uq&i!jG&hjM*mA_{mNcO!6G<|c;9RD|iu1xBkMvSo zef`ucUS3_B@@y*~Ol@RNB33R#O^{dY-_us{t?yYIAHOb81}eLgockwMg>Doh?cGa? z6~CkA->*wMKhf`+BBZ}Dbki&Z=M6j+aE#iEw!5ty3#H7?vGLMUnJM92*Xhq@I@NfZ zK`Ij!?zx7QH#28w1QRun{~5f}j3@lAS9;0N%o4Cp8Ua5lTL5&%u}dYgvM(O%SF@#u zP%zho0*K^Gv(qnMQ_1_?!xlLfl0z|fb%Or{$;)Zx66bDmlU=)9%D!8UN=;4G&j#nV zR|*gIH5pv+$7?=#!_+4X?7ArsEl$Km5Rc-on-bvCBc9S=&Ted;i%nxMoQH zLg@uKy!@_=8%N(ipE*uDEh=Y_lvaf311HH^WC{2!0)|Jnu13^EVlUsbrOsu<{BxzxoaUz6Qu1-YJhjdfbXuOgS5l@Z5J<1VuHpOCJ z{l0c7jtEUS{_)3q+%Iw-GSf9GC;T4)^*p_+6jDO;$}HtTsAXa~*O2_3E}tWv&kiK- z2Vzl86n?kJzV2+7d6Sf`a#P*!f;Lja)arF}_|lg(CrUG*YK*VU0|$?tny?7-^{bXC z4p_O;KXrYmM?<#mCuD!B5b8^={RYM`U=9s>m4savCk&6IF#fn4(>9 z!Jr0sNsJjW!iW$@=9kckfJCJ_G_?N4+fWOi3JMx`ny^%;5S$C_#xLL@p!7)AQ0QsA zSEZac?1}7cYXNMN_mVIC|af z45WS=4sPDGY15W1_d(WhEALH}PenKOoVz28e!Gc_X-L@n?P<2Uw#l&1ds`{KXy^(S zoH+f@Y0}C^NK4mDG0ldRJ>Gj9x_*O}G6IF(mZ$Y@@ZQ8o z^Nfkg10;f5G+J-c}J;HEiq z=OO}6x8DP~xQHnB(>@$Z8 zHekC1oH3{t`HPH=U4LJ(a&-EHdN~@`_k}$8PMdW^?{ZAEl3;Fmjg?#I*LF>d($9=R zPr~KkFZ8qRo?VMtyldAkfl@L{XnG5_(4FC-qqtz`ifO|&{n6EfRF(j5g?x&kt%XT# z!9C_qGul==R?R^n5 zJNjT!_KD51L91)zCtPD`p3K8IvXnA)mCeI>jT$!&56XW1`oSAIj<U1@;;5{Cmu4?T7Pre-918+bk2NBRmTJCL!yg<(az52wL4jwO%IrW z{J%{xSUwZBa@!gzi%^vjG52~?0qYE-F%IKlw9T=&aX#qt6@w+MS<9yE$;;kgXf2i!sy( zWCN{M=P$&TbRTzm##(ux4zXuJFh`fHy3Stk#*oW1SVokl7+X88${hUrF6%0b&i90CMNXVJ?5pYK%b}Y=Wl!`ETNN1@ zWY;J1vKG9Zb&qsXiGp6Il^Hu*{2HpqT1GyLnkavUyePF!C!9lD~gUqG0 z9e3^XcAx#xv0*{S9nK!}tf~kzW?K##4mO|-w0i|2+OK^@UxT>PLPz+h%6 zNloOl75{#U+PzTFBP(gYN+^MT7?q4FUe54_H3u+zXz^tTeb{j!%^ShRK=2_lkdT+3beE0L!I9W3Qs5J!59N) z=2emkj=Fzeh9Ax;BPn`lGDi0kg=2Wos3Mi=G#1!bKNvA>S{9m`ksY6*9^!n7NOloD zYmaiQ0PQlIHpM}7Zk_WSymPF|Fr^{5#Gd&~vrC`M7lLNiQJt-4n8hK$pz^2sVMzGomMyd-K{p>V4#2*`3V(`gM={rVbZA#ru2y9;n*2S zQ))#&XE>v+(g;B#I|@L0d%5y_4)rg*a>LpDe!b$ek+(oS7jY1dI&%S35D?IVKDgT{ zsmyc9!M!^n3?fr#;oF+}rl#c%>0j;b4%F;oxy)*Uhayt+Wq{&i(gZ=!|DNwEytt3#`w%N|N5axRRJI@D) z6juyb&g(u5x2D&t*TuYS$hiHxlbjhQZCajPu1yYr1`k<(Srn)%$5s|oO-L;__Wopn z410B*78C4(3-^6k{`n#sJWq+1?Te4E)r-;*97bGqHnke`==&kTH4&K~o7SIoC5Mmr zv~}&%1FN#tO=lhIud)cQ!x1k27{*DB*7?{s8LbCfW&P}KM6OH@rY7qjq|DC!_rk(v z{39B9w>*h-N&NFa&sF~$3Qs<%Xh|EzS2q4#xKn52uW0&T(+7NL%CiC#b`@Pt?d^2y z$0sE%r#ly2LLZeWF+-RVQzTPjcs(L_c{e9cKx46ND%z}vd;xt%4m{8$)um0-LXp7i zp#IN@JfiRe(o1XhiN@7QG{w!gX1Lln@~340@<%h273#eQ!p;{yV5j2sV~raK=c9n5 za3W$j2L^?LY|5fV##+m0aVDUOs)fp6Y-LS=2%KRN4BD>$TN!$GvvM5q>W-w6qW(U5 zbLQ=hEySVEE2C-pPOf?KN;^i!K~YRBNf>2h^wg}e;)%7ChQUqmQo`==1@XG^LO;VM z1?Purk$HxMS2Q)@DyZ$6b2r)!F@tdyOAKE8B+yZ@P?N4U@$w~hgXt3f&-)?A)iq0PD|bzm7y`aHy3vD+rvL`Uyk7> zZ6Li=$`v!MglfGMUq?-?wv~#=Rwq$aRU4|%GxPi2#y>TDX8nXe{4Be;Q>&NR+y`tC z;D}op`68CT@n^8It<=JX>UKOus?n|^>0Qv0813rNsgnrbKC_EC?05>tDF&!uh!KNz z>p#5Gn{n3lePyIj;$PO~ACzMd>Ru@9)B*W!uedwFL+~HsYldDBJ!a&LCxWIy&crZ% zh_kidt;4yfE!W@9csZ@wEf});D%E_oK^&@;H2lpe0s1mPihD1Egx||@5c>cU{DfY@ zozu7DhBYvn2KBz#zq6W|yI7~Q*(8&UPSw9P`7*m#1HF0vbr%!YAFF4=5uKod{zX-<%u6hIJrmR*-nR5ci_@PYsZ zbYGKPWruYePQ@jZ(4NG;uhDPN96|wCs;T@e;|4iiYm$GU;5x^5TDReuNGD7|fk=bN zgz+qSJ$k}IxWw-Bq8DQjs*G8R3}5Z~rZS&oeAjS6S`+;04W@{TnD7AJa7#?<+vLBe zr1<5tQogY-|09IOWJ<&)P0BnJt4FQKrvJ&|nhYf+!%;;vLiK!-KL(>WqZX*sOHr?@ z1w_MuJp!H*PILP7H7ek?g~Kk#s?LwhH#QgVE-aGT{UD~*)P`8YGYx1dY?U#B`wj*M zwL8`Gw*pe(@K9gId^b9(>6=_Dd+<7r%o{kVg#1KpSK}X@lG%NxrxECM>kFD~{6Hhq zo#4FYN}tW~PF&qQ1O_G6mcRe~lf~D4<7phHHhz9`%9?-hLo)-01+Q`&ekcOGW#jFN z?^;)Vfu@@~8(oZtXddXuWCwD%a85Kwy}@%q%9_H7_io;)efz^E){oCuJT~ve?jQSZ z5^no`6Q0ZNqZ}2-9L{$9a%IYHun0=MEnBt(1_tihm6ZNkEMLE!?Y;{pHJ*w_FaXx2 z>{CJV><$w^#6K>itoblTMv^FjgYJHw{sYEz-m~G$mX$ZkgGkEH`BYv*opK|+x!rf- z%)Szfa`R^dn1-Hz&U?i5bULy0kVs*C{hpD;_)s2>bi*6rE{xGfGHssKZ%uxLL1*Vd zw%^sS*l}jqYGwuqW#DfivDZ6G9|C1qC6X^r5Khx&j7%y9{sq;X$C$s&Br#tCZhCTg z*^;Z(6^n6SJ*F8&BqSv@N0pJ47$~z|DB^6N4;ww&1Z;=Wr}AE9eXrFB?j;&{gd78i zEes9bwozg&OS*WYg}E}QCk}(n+Sgp1GYHa@fXtVSuV=*soP|hNKOiX@w(`eKtN?d{ zkryJnEn|FHU$SJ)TA_B`9hZ>Ind{2J_=$-$x}kn=;kF$+8f$3GdLDD0(iQK*A2KSm zG!|{Puv|HaCCeew@DH+>@Msb}fR_L2;N7S#&%^ceFH2(GNsLIEX(pWBR(ZbZ45$%O zZe?j1FJ|TF$M4c($y)Ean3h+-vc8`oKgw`Q>H)*dxQbM>-+M%g*<%onV%Ex3$9tNE zARz-7pbiv(kx?>Ifv^p0I!uW9@?r!v&@6dXMxqmegG$BX5z(p!-)GyIxPutn*nN6`!6svWtNqUdu1&os{lH z+7=8)1%Yki5%}r-Y_BC`m)FK^N}zE32~2k0;FBzF284=bB#*1E6n4Uq3;lqg*44{W z5)=N<&O85pr!l!>CWKf?t+iQ`&dZy+V|+K3B%^rkS4WL{=s!iy3zY-Uzh6N+KbFEG zAQk_Y`#+kN#M=M>!uZ`#$CmThxLp-Ruqv@U<(^-S5Qrg}=UK}wc@^?v=9RV$PG0>H zMCf49UbLdBi}IEZK=Ln0A2HFC!Dc6~gtFTNxTc_4h#v$xwv(jR7w%gpHGRsPg9bb#?}(f?C>v z(z(yuXg@zc+K4@IE5!wV7If9&^rw6zN`)3*jW$_`S2$GkLWWifz&WK>F%|CD1M53# z5q3J~g)c^A%w!_Fqk8}$Rh5h82gdZ?T*d|wOPj;#_t|yw0lZo1)DoYa2hq+`n>1;H z+e?eilVb&>zyn80L*|&={&c-!4ELoa3x;$WG}U*&WNuK9tr<4}LRP8ta`+E8-PUjD zPQ(3QYm2BDO$ZbOb^n-7ql7f!gaxe~Z);mfXDy@V?N0Y-zR?EN#Drr{g5Kj8eCkfe zC8GaI<;>lC^^;vpnZ;Km z&e4(RUKh*F_gf7zDlK~(mluXa+G7b=*J)B9JX3Xv&o4uyVrAPbwoR$L}KdhhCIlFLj{r4-vKr~5uOj}V#D<}#i3xU zRn5j_Ub)Yvd)sDy?_Rpgt;59=wwvbbudF@%>PoHOwQ4`!w(r2LSdB&wwW?Hq+^XHz z?vFI@Jzd#nM#F|TtMv1a)o5R%ZCjmF`$kmOw;JQQz%#FL@9tjBJ*Pc3vVL+mdt2$T zxyK5AtFtO^d5`Rg1jWJbd;D-XIO}{#8B(2fjbK&4%+`u5v^i}k)zwd*L0X0fPFB4g z5c3VR+nh!eT*NYAnyZZpF=cVkx})E6B%AfJW!#9py^+@|$WJ`#$Hay?w;uJ@5fu?0 zJp-d=DWj-y^IhXKCF^UI1Q7M6vR*_EMl6fp z9Ot2Uub0hXI(_Aq2M<6t))t_??{>}7$a-(zWs;NQ?gS^)BXx}O#oN8s?R8Z>iZO(1 z3qVI(ceAL>f$b-w!-u$Up0^_~@FK*OoJxe~K3Ep>!CP_%C@v5%hi7yFm&UaPwhM#aLJ!9jIkP}Nn}D(m^~ z{G9|5r?Wu8=C^DPf8G=OGnE49s;5(HZWhC?x*mJJ=uI}a#hsv9WvaXedzEB(oGTB} zKwsb2B%NVeJPJm-Hu2a)hOctenccec`uZE9tASXX- z#dWP-_Qd5SQ@L0n?REo#2HjEOT*GGbc{Erph%G^f-ykUTAW_ToRSdzny2|-^tC#JDOd3|)O|BPC9MPt$3RqjBA8BFw6n&7EDM0QpbUIf=x+UhLg#B%K#KD2Ib4qWq~UJak7NaTzTp(&W0&Dy*UcqGx8vW>IN4E4uc_7K6r$h9gVf29fb0D43>O?Ciam*valC!O<-b((*Cu`XL$Y_L z4S#vHUZzvmIVCh6Oytb78^kAEa~}|_L^dLlW0v^$j-!6eOGBH7v3Mz6#Hq6!qEKki znC$TV*tUu($8;lb$5{x&Qht!k(batZz<3~jXusVICTQME9#7p){;#TstS}Q&h$Vdq z%h~89PBil|XP76_pjzdx#qY%iUpy{(BZCODNK0Fl^~pl*M@h%Xfh2wx$Q3+0a%8IP zEy~&>-}58z#uk%FY32J7RCO|4m)q(-*!WEj9-WR_RBY^EdQagHEN=5vmIR_AH*lb;|J%A>6P;rhpTACMa2 z5&zF+BAf%eC(r(VBOzh%hluIxd1>#L-|HbDhV!{wcAB*-|H@D*8yeMEM4OxG8bTJ3 zx^+v{fAs?A&r3gQ?qOCA-G9a9vY~luOKcRDnO0tPO}7G)i0eHjUOk{P>82O=z_Z=5 z6En{0tgP|%E5+VHK?4!7L*>jh>)?OVkdV2-tANC#7^v)hv^iV z;a-)$y6S0sVN}ZO;kLHMIF3lEBdO8K-)h!(ze$jSdiX&4$U6<#lZSu$C)%R^{`3Oj z6x)``lGFdPshC9Vyl;}>&fwtS+=ij+hPC}Cuj$s_#xW;~QWm<(@r zC4KD95HQmBG<^6b6&aPT)fBJmZyu2c=JT?a5luMHZ*m3*3CLPJ-uxT6wl<gV6}*x*&WAeaKzGK2I6-FQ)O}rP^FRq z0~r}0|3Dc;c%xjWDw)Z+dufkCwKI>1!B&39%O^Z)-MDW&CCY`sb3la$i0JQVyd9wl zT2{fA>Fvi!u}~^|)h3VBJi1XlEqQ0h<&6h8$-s#VFiS{o4hGCD;}h%=V>J`fIXZ2?{AeSf+`qZ5V~K$~Pr8_dsaG9vJSyCxZa zFlu@GW+uYZO2N}?!8oE2FQF$(uNGb zXZ@u`(mII;Ev_3T`iABj8GVRf z|IXYFD?~8>I7A^Uld-D&ZBAv(@S|~a%g}Em24iyg11FQ`@9ms&*>J3#-F!G!G)aqy z&GAW}%H?#UCvhqfQsy;n4xT#bJT6?VlFIQ7&{cg&{TDYj#{zIUqwvO|+>ckU{}A4* zPLJ0CKp&t7zo(9Qb({i(>rYH9VUdzoWyUH+gla7ZXIy`SOz0k94703vMZM$xt=94T78ftES@K6S*NZUz9(+pN2oGO|DE zFYuck`uZ)spom+70t1_R6d^Qv%o4(3ZXvw%GAI)A*u)dlk0@9MvvoBO4xc}p_#sRV zk{~zrjvYEM|2J0V67u|;HFG6rLwYE*6(XLQUXLWL0hh=-XY1RY1yV`fWDAx- z5z4hJP;&}x)ZQK;Stx<8;N84#xQZ@nUaJa-Y^%$gR^M_#s^c(gqnn&VMEPrrEXF)} z+V0wm^5r#|UVNPOVwteb+M(~1RyC@uN^YJRkUDv3BwHJ4Sa12|S&e2eO=kw6+6uEt z1$%o9*=-!3kdRi|i zmq^1oe8gQ^C@Onx)74fNl3JuURAw_5C9tODwKm(`?wVv85FK=#==HLwoHOTerF)0) zKh8D5X{$Po+Xf;dsS(mu-_JbsHw%OFc86LsSFza;<|ob%O>Cbddm}Aspmd^h4bgO3 zmF}=udF=&@>O00IUXUA{Er$~Ik#vkBnc1Me-4KYHl{sZb^gu}qD}MHMw%U08jkM4r ztA2c&2O^H(V%wIo_s&C>GLlkp#C!6+W?lMQO)zXV%81_qbNQB`jOEA<^iuo%doeX{ zx3EEuq9!`IH&#v~#->~#zEocyHJ%y~)EM9QDN|aA;V088+xz-PWr&Oj_<9^O$NtHT zDy~*9w4Y;CWaL|p`;8uE@YO65`pq_vgA@$1SIF zyh`(a?B*&y$sC|vZoQRhU+h}F4%XkFF3j+k(Ck+UQAP6_KJ~ZjZAb#^G9IE-r}z(w zY;2CZ;dkE2KnHOf0_@uv*Skoz=ld(=Wy$sce7$IftbEINBi1mV$a1Y!G}@DT&Dq>+ zQZKQYpHfuO2{X7T>D@GtTrmwoV;s_FW5L0|S#RO^SB~r|{S0qCXptOFt$m?%y#nX= zt`+dsN3i48X(Kp~>hyfGZ@_AoeYC1m4ixb$H=O$_5^<_GaE_twk&6!>Iid|^(ULt+W0e5v82@wSms=RgK{>+poq-~E?WJs`rSp66(z%%W0y~x zJ{T>~(5NsmIwiUHt)+NUYOw(+KFL%G10A$jOD(s=4#%Ha-q%_yd}cT^swa({O_Jbe zG8^R@fMWxdj_kF+ht&)bG$1OBgT{E1<*S)MImz1@nzA=ew{~Zu;@SeN4(VyryXL5T zhMIimub8lyJG@2i&xihvp=uMi9Adha)8^IE2_0L4ls)jLj75LECUlKuR2WK@9`acn z!Rw;8n%ih5CM9h!`9QQ;xkd3IYA3^HI!5vS_|3z}$&)L3(z&Z-;LEk54gM+hu;LN2 zfe#pviM27ZTzb>_qMWHlmi-HJQ@gzCty!y$>e=ovxUo52*dYc}r-se@^!UJ~zxvdz z)?wT^!xjCsLg|LAm%V>j+n+L}5f?niU=){I&6gT>dv3Ke^Y8VmIxq-HMZ5p`J;Sk} zI&S(SFNTuT#%~zrKq&Dy*~^jt^Vgf_7{$9z-aa|zXx}0`dwX*Sj!}7j&i4-{Qix2L z+m~6Zv1^nIWwJ%ib)?VZLkyUp)lD8D2UhZSxZ?V|LRXk?&>k~a%&Vi06(|qJEEbnD zjQIhBWmxL?TGyY5CxmabSU$EfwCGP)SX)z5uRuqNU9joRn-yrN+S<0P4vy1x(Z%6uJWG?=Aq#M~&W6HT7D{0@2FYR>*F(m*s(PWkWapOM9eX z6QMa#&9w_9jJW17GH6SECBF06oL3_a=WZ_GgS>@Jj;~|}N%Hn$0GO@J6reVcq}Gx{2f$| zREUY?P8bNOW==C%r!s($gg4}9UrcI!Yc=Quv@*-@A!Lqj2TN^<1fqyZEWzP=9>~Zs z=I5%WPX_Y!t5wE7uA!R?`7^|YmDA31=RlPY7@R>M1xCSD2MH!kZZmpr8E&a(Kq&}n z<4|P38mWBeD;}Ub;sZO|O96aB*JC(D1Oq_Yr@a;7*?`r)7s=J1Q%-he%{qgZ6B7G^ z(u*|=c>J0__Q&2<#0zip_IjzmL}%dQ>3gy#R-@_P^A>=TT94jSMT=+Q_fUEOhWC3l z4e9$!_l0-r$ka%QViLh)SB1+s#)PejYokcPD z;asBPJLqf+TkIIc!7Kw^WCXoO*M>EaQ@+Og&cZ$N>n;E+dPg+ex_0kQ33Iu+UxOBs zR0B!$8H%MHMP`?bJ$kE;u0N`H)AtUAer=xvW+f>7l%f{pUv3jmwx2L8vM1$-Gr4W@ z0>~vPF>#2hBqQH~!c+uIyvkUUNd!~)>;Bh2J-7?$R!rXwe%t`t!>6M-Tu0QY9kEW$XmaVqsyc` z(1rRM5yc{0v+8(Wx45$i!6#o=d^I)yVT&7@&z&)}d)kl%OPj z;`!tNTfY}qtKUGmcbxxB3HcWjVKzsb;?A@OlS{~a`T7m?qdB8^y*be2Px3aAlrQ{M zNhzuM+ovIUS#cE+;U>uDZ#&V=lrqUj#C-rELYb-RcreE!72L=u$oJlq6|q3+PrtK zDe&WwBgWrGo$yCoF>JR*ai>O#o6{Zg^-Lpi0-N~#?Wi-o&p}wyKnhMSR@7oNiE{W> zckB7{i%`tT`Hf^jn?y@Gqu$>Q?&da@n2-^umwzf{&?&D7#dURDNPG4r@pSh9N@Lgj z;8RgyAbXrl$pujH+_{AutDFLKbC2S9re=7nHHmd2(hM;q|Dit^Wo!Fj{u(o#3PT&l zH5ZxGQ+&j}V=2ew%>t?D4cR@9p`VxXZ#A9YX9183X*t(lL(KMLQ54o$op2?1~mlICGN=bqj_QE`+9r8Bc9932Nni)k(UxjQGZo&P32L;LzO+9UM1q90ni|(L~j= z^of*|l=!R6*iM-`)^Xlxj!X`{Qf5+&jaisae}oK4A&Gc@uYFcl7I*+^zH2}Hzz$_c zZ|(?F_K~x0cAqB1cEqxtPaBc?%3Lur3k1&(#vMI$sBQc9V&l18{F~TfQ4-dxes6Ah zMyYm-Xw{`=hy#U^2O9>AmQl$0m>y2RKa-`w!i}9;z_H9aa3Q3!(xq6LpJZ{2W3pGn z8m)8ZhzTPtXwk59X?u+XRPQn^3VxRyowXa6tNbke);Iq7tbzt++%4bN5aptrKO6+o zdqpfb|Ez`!E1Qx+bjjkP$R;4JD(C8eW}{MBz^8#A~r0b2xTlO*_v%sK6=PC zcaxypTDl{-CC)v+N|V!nf6}MVe5c~0W#T>uA^N12SO?G#ax=dj1O}{90gF20jN=c@ z|9#kzzv3zltHahz{c4j!hRly{)-Q3oAh5?GBiBXmrs)sgTx5(*L_fuOBm;R%yRU9XgY=WGJeE}&AHxcF0&txYCew-pB5A|DlB$ks3ZAo4#!lp7ny8J#8l2dPO<#~Nz( z&OLDh84t4pPOq){l-~s>$O%;B<2pC>{r(sWw)LJ`Z62$>^^38lFzk3+Hu1<|s0U{3 zci_<6ie0GmV33-6L>xKNA+7ZYQw0%f_I9ME&%9II3XAg#O%W!v0ZRmr9ak|M)?_xN z2j6WbcjQXcl1||k9y#P`hmIW^dRygLbs~-Qj>B7-%>fxefpGyQQX(5#Cdqf*{UH40 zkgB)i7>ekipq^f<5n+p0<~Y!pZUr2dfL!nc?Jp^_kkH?JhFc7mJQ!2h zM>-H&B45;830tT5TyI-<3=_3j(oH?|(`r7Qd7Q(jUN*bDU8hbq>y;OD(XDt106I8W ze@xTvK~QHi80GyU7K+H4cZ&{!Ilsp45}g4B!T&F3rBEl+;uG{$;C#l&a95yuT zgS+WbuhGMYzg%E!7GpbV)a}u=ef|K}v;oevw&O+D@M&2#$d#O}TlsmbDH<8&^RB-< z;oxHsecmp*%rWGW-DI!*S36n7hTSTe`NsfIQ&|#?h#BmG1J@hZRnvm&G%EfD zPYb`{qet(|t@ecBJ6}^vm#qc%CBEf$*wrDeL7$AG^Y)_FxJZw>(?pOvC(6{oH0XA}oLT^;ffBznu8Z$ee?1-6)cA%Svn{u~44?!A6F&jIJTl zsK9La4^n7%rjTzSEdf#La?|T{*baA-aXb)@2$rnJ`2iLB6(TR=(z4R0MXH=Nov@yc z<3yum6D?Y}1Vm4+Z3;P2Zxn;5jKHM12+@-i)=#VJTiS3Wm(_mNZE@#4vl|~@IgMi~ zDvUFaXJnhCC@%vhoZ8&X+mCU5h^!>-DWh@}RtXU$>-TNc4KN0o{pjqL>~@5iAkoQJrcuB#L$$K6ySwque zDQ-}Q-ubdB#I_eQ_$4Uo{$n;>rp`=$UOvIrw&8KB*oE;+5?B8G81@(r4jKXj0S?uZ z`6h3lX~1Gr(U0ttcEG`!^j&BYx|1(0z#r7;6-}c$8%FsSyWiV=ckK|B>?miTa@3_<_VlNW0J%YY(w0rsB1qBPhMASov8W2?f9CsD?|GJ^!1L1>h*=P zmZ4_otBsfLr4jpP>k%L`e8F?jk^rFRTpu4Au;k#hrR}$|?3^9UOa9dY)XN?-=80$O zNCRcGU!1(MrF!Jy!!}qLu0A`E;*LirgT_8C>jwEkON>|4*=RD^dpHtJQkT?yKgyO&aWLk`~O`f&&x9F^gBModK zEv@%!JgyhLXyvK&BsGtQ@AZouzC8HN*<^2+anQwTY8F$kO}giGOwBmx_@iG#vE9*n z3(YQbRK`V1VFAfDrNuw(`y@Ewyl3bhShGAaDrFkcZIet&*rp`Aq^k{g1o#giQE8b( z5~F$CYQU19={h6&b$R$HbStF29(F5Uk`Z0_MkCDq|C@{morbj2!l?w7A62ii3U>jx zt@s+|kytDzZ|Asr+RjxpGiB+oCmEj0{FZC*_4j-wQdt_D4tML3+Cfk6)0!I; z6dChBn-)K;fi3vACO0D-#MK(Ys-nrZKrpaYv-H0oBr(eyCIB=lls~GaQ2$k97m#_-- zB1aVkmtQ3rTnZN^B&u|HRatd%!8gW99_U*9>x!$ac2Bg0w@vzJ*4ogdOBRXDdW|B8 z1;1wAM{h2yV-=<6@#rB*SIeY#wwgoil?QJjTK?}ceF+8m#^|0@{vsBVO7N*0(vi;g zP=>|t^8&VQE8_4scaUG5x$93eow~KE1a_ZIpoCfNxC7(WDY1*F8%C<+NsH-bEEDaf zvlX>U4_Kg?SL{r*m*<|mec&jaaTi&UXHvsKLQuu~o)Z#pSXc8MZUNK8^fP+Z2 z!9U(bJ(-QG!rB6Gxd#UJ8PSwe=0Ud)FX+WC+kJxy74xttmC?TDqJm%>4+@ge*ki`b zzj&O19SjH8a4UlNJAQxG3bPkvWE)J%0qovhu$vOiLm{hRRWLPuMIZ>~TARY&*vud3 zv!|PC#FU%WA6xPX;yLo2{lsNOc76{RyFO-zkidM<);qv<2g7*~#3cyA-P{Y{%LW92 zK3&UE0^K^~DE8OFzoeug{nyS;we^yweY{5@g*vl9R&qHA0+U@mmJc~JM#F-Mc1 zw@L?fF-}l!ua5F9iBtoFq&@4H1Ctdyr=^GiOmOh{ziSKYo7Bks-CF@(O}yTp`CIE; z0Rp2Da~~6xoIeEHBr5Yd62+~HztRWTDhY=9ZIq1^gnE7=?3thDw*JVGYM(s`P2W9d zMip~1Pcj5RW~+(Xw&-~=thwKpKhp&NdzCq&oANZcfYs(64)lf|d$w!=XAl+4lp^-q z;rp{3NUi?XUj4`ZukRl@L!lJE`@7St6p_7uaHEg6g~#&0I^PZ*rQCe;NRs+IJfo?V zNWs+1O>7GREs7p@8Qa-7?eJUQm*{*qnuzY7Ty*@#+6WC~Z1v%+7|?+;i^`X%CL}d! zm>x;4(<)JyMhWqk64KI#7ld+z}hb=qz3wrNz%iU|QRW5R@@ zV8Do&#WV(tsGx#@pnw8n95aYnf=VzWDxhE-9TgJ_CPa`?F@S)9q>}El8|`Lh?mhM0 zQ}@)Zf7R(a^_`ia`xoDLhqc#Un;6k0{Yf+f80=zQyah0|EOz9rjt&?!aEdXWXkJ!P zUTJezPu>R+@9(1A`^3$gcuYtR3289&KWMkDS*d(kG9WfSsN9FMGiKGR`in@5{616= z72ueRvl{EJvGbDQhRrhoTYAM@*@?z)Rd~^0&_Bz-|vp!D#+po0Gbu<+5db2?zvaGp>NwoOe~@O5;9kFH zk!5h%khTU*o=2-k*t*?z6T)s!ryR=VHmhIt7gV-t+2+VzB9=fpt$h!~^y>wl$v-)&$Qkg)D-r?wQWFTI@o|rB|0yCb6?vnFdv-GI6HX zE`%yBz;56f{L6g?s zv7?~QNShyHwx719+?=zHC z&~I5*^ccr(c}4+9;%AImzU{M+QTo}bhx|owyh^=x@tJ=RjKL0RfHF08kVfXZ9tppq zB}8PrvvEC`iJF?tJJm34Igw@m#QithMp#D_1=rs#=jk>6_^+o(*@(l)R!sFmNsI4g z5w7|B`@^GuCMcm`B`sP{=xqCK(`Nk! zRY6%>b{@Im_s>TVR(KBLCSQl_62$Sri^`Y%?Vfuk(Li%JL|Jne2oN%4$TpptdKtnU zOlW+2U%2h_ZZl>mw2%SNf^Z`Ou|i+f&Z7r5gA%yymMM`--tZ5_@7#;#g0i35>cat< z0{O~oOQk39FWid?paaNEA_k_gT*zc;Nr1L2Au{!NIIx_w_V{?oQ9AvnBpu1fQ`DJt;R9{h6$2Z6~7e+ zPExywz&k@QIH)_`8Z)w2-IGbQ0bfj-#bC)CEX1SJ((eF1?YZO4colT8|8v~IX4PdJ z_cSn|YRPly-U1)7myCn5GqzMWxtGcW>k($wZcGs>iVJLX`r1S|6ZEIvXnTK7vq760 zpwYiPPt{D}5r)!cV&bA})gXZZBZb_I6yQ+mj>$bGR}*{qHB((oOC3C8`!W%E6+sed z6&o=(iC+WuO)1Zag*;``epIDgAc;@uwvZbvztId^paT#^iFYDjT5Kf28%M2y4-FG1NNI zYh?4X{E5GzU!%6KqJeEH z0`vYw*@qkssgEM(64eBm?eMUa>bx~mMPM(^7AY*$Q(*FpiCU%p+2)bxI6IP7+r@{z z9La=dNtrU+slH%3>-O-aiq3)1qiriC(0jyD_jdrMbv6&0f1e!miD9hjR30nd>UygFP0^&Zp{lv0 zwEg+d{}h>8-83r~YW>aEpG!ZjG@Q|@g8a+Hu2Id@r%b-mELCM`75~^U|HWSV+n)@K zlFC>gKo^*21ex<9GzylLD3|iTEJS)?N!BP|;pK(PMG8Z7_>35zFtUS*iAmBC)ivy& zXwjfWcitXEt|zFg8B*qezWedveCR16D}rZtOo{e_-{k<_TxX5i5q<)exP?|JNl!mS^aJS76VC{1 zTN!x2l);W*3s54DPYOR;E4iWS!Cht4Lhxxy%K$UATZm=8Kb zE&*%4O&whgkyKv7qe8VLsjup5dd+|byVL&$>a(}9ZLB3VaC>HprK!j7nqqG3qRQ3$ z1^wVnU1H*iN?%+KBpXlu7PC~8q$wE-dsn7;aM7sOLI^>-FeF4IN2KD&W}*q?vP=ym zo6OB=okf(B2(zjy^|BQOk5yM=8qd{KlF>at9V=c(ASik9;|fgZVt~Q<9K3KJ{UV}4 zmNX5KDyF=1-h7$yE<-MM{lSI%(XA)Fo34?{PAcW0``v1mYI9hiUkD~4?jxxtic~in z7tBd2{>kz6PPDJR9x7)RjeIW9N+|A6qiz`+VD|A|73G!F!I|%(t-93J>#yop>q;T} zyHO&U55Fl9)jLmuYI#l#mijzH&ax{unuPUsi&X~ zl;0gsQ1*RE`7V+n=Ja#zdzDSo(Fnhu0wGZ9nA+>PylB9uZUa?EP*?***m%mg@Q@%_ zI?J(+h5304)2fmc?Sq#~{5k%BMVuyC*y+1LLfW}eX~ZpyQrsr z0`z$t{+*_KJ7CM-)~L3t$0i`rH1s$vpT>ceKLn%FyN2-4Y8WBa?EIK@L`9OcnF$jJFJYKE)FFj@&VKtI12 zm<4gBV{P+yjyt@)?WsPrv^;t&McK-#d`vIdW*dZ69hfDvG0L<$l7T|%aAWBnEG-VT z2jLaX6NrPP7T^IYcQ?1iM-4Xa(7JWyQheZ&i)0T3W)T!12ECry1Fd|qp2nqO1JBBG z|Cm+p7`O~Ni?$_5_eac!sJ3bX+-h38S|2@f#N7CPOicCe=5bZM25+11%6s~w)NO__ zBz7PU-uxZb_^;;Xs8A))S$X>}Z}l2TXuWCMK@3_eUy6g}eF7t_4fi^{fWK8LCNXWv z5Y>SoYQv4uu5i6#K2Inw#(l`h{`C+L<80;2uDZ#yvW5M@qn)ibTZ`n1Xc;p%E=Chp zn|l)mUtkt+K>1QCT%DP<)!G=i!#f67FmcS7I*WFnl+GaUm=A3tRUAIkb8_)mmzKU0 z#*YuqYZ-t<&#$1@aX}QtjY~=AD4*$QgfU3>{Tyt7m~1ZGdQU2zHYttrRH^wAdi@dE zi6VV(Au-!$8ZBycziR-pkbph*b+CbAN4cWLKbM{nji`g0e`{grnDz*0BCpK5XIvKx z*z#!_PH1H*F8v25yWiUtynDzc;gR>!G^X z)pU7oe#>)h5Ah9B=k1T9Cdnt^S7!u!rlsE-K2r6#^|G51!5tok;-1U}jv6DOEK|nc zP!k=tRBeu;D>2CAG}Tb2msi&izuVmXB<2X2sLiTlDf9xkiLVki2_i{Ns(R6TO1yCS zouq8jSS^UvaOjNfEv3-`6j&53nR8$L?Vpf2q-TxZw5c#YSN2fTL-$reKD#D=X zMG<_Ru8Z|U-)%^=BSLD$1CpU?&0lR(Z}^iBLjr6DHuWMbeuvMoeySYNvI zaj#58ZGoeO@#kJ#gyj<<4{5Zb8#{BFI*BxFr4bM)v5wqFZn`rWMzD!mEpzoAvpCh_ zQmpj4T zUgER)D|zFGN#oSBIy~;a^vYJ*gnwsyfrq7@b(|>n$~N`aa>Pv%z@3~MPTf0H-EeDK zDCdzK=rW!nqSmjqRX^JA#!{4-49Dh*x{gLWb-pvI55bY4RkSA{Thw@&30rzpR*pD# z2mvDCYQ-aIT;8oZ-WVmxgt6crAU4C?d2hPlrmb&nF#lJS-W~Bbd$&Vs@M8e;&@ZRF=%)I2G4}`8oBKAE9&`w&O8;>tyS&y zfl@MMtVbvfAzr^vPEoz4D@Kgby@mLn_$273K7&qJM-CXxr5B8nN)<>g>zbQ~gGnZ7!Es4DmsL8DgP^@dpGm zgZTsHpHT~CP1H!-UZ}EK&q(%N@-i<9DbdG`qH_)8c&Gr_^w3cqS61m}8*l>|Rp8R) z0vS1evydqjagEeIu=6^;C0$=cv4fXxpw4rgc?F^|g1&ZYb=A{U2&Q)9GvSjcs-}+k z>^}2UJatt-xwul&uW{gdgNUnK*u|L-hi=%okw8zF(mmPxUeT8<*KrL=`)rAKp~sUm zCLA(SdGC@4;p$&Vv4D-{->?Nlxr7>P(Kr9%Z|u+e2n_bRf9uxzo3CBn6Di}IMrA|P z-$6Ujea%Uqf(eFcNG5zSZ=re-y?k9g!0-{Y3z0(po+ksc18=;^@a~8 zVjwj4r+{2Yl5x^qgfuS!F8!jbxWR57YjG zy8TVq7>T6eE)kZ<)aN@?RO7Cd8uI?EiVD6#5pq1?=agUrL-P9}_wR>V-Xo6o5G6uL z6es8Rr-DXj?ejo2;HBpce5J?8&Eb|qrNS$HJkT6XH({wRLs|#jJ278oX_xz56}Ble zk4Gn_Ui{AejEH)4*}WL6A+5ck9cgTt1ksVWd|QYpy&?BkwUnBRl_riRkEQ%5+>q)c zTw*1xARUX+Ky7(U3c{W#HRk1Nw#rd#|gKZc`k8|RFzDmUVEUPF`5MVBWUI1KYFwI?$_IF&Rk z`$D$r@lT{d*%jaHQLEbKOKb%KC?yOR$5d!d)cU%nUI-3u$w9Dg4BvD0b5KK;2Po8S zs7@Xkn8o&CDs%(@LtqxbMrm1XWkR1uWiYNp>f7QuY1sc=GSBX4<$D<~D^QCt+l@Pr zl>GA{N-PtY1u)dXYjAn(xAU<&-VVYY`qx7``r&h?AY9B*xH2Pm?6`4V3DX0IvT{q$ zMYCF&=umNgBur(xQ&WU6$#C*=GK{dBkGN%az&x68YFd znT&TJ7Bk{t_VpKDZziNb^GVX}ev6eRj^(drOc9w%caZrm6a}K7K2-3jSa#I7aY0jm zIWT(6nAiD_6n`*r7g4lS#v`Ub&YIv?d;RKS%h_jLv=)9|mKb!^E@#5|DQ(Qd?<{#5#Epp=v2??CravDsL9PD7q`lB(uteHc zyD{rb6GZxm0gSCIec`H<3gt>57An6_98K=?O&psvnum5o(ib({Z)mOVcIaAr{U+UB z#yrTMAJ5T(aY7h>96omZc&GRo>nhm$gCL;S5)W4JB>W}HGpM0e)l)~lR{Q0}Itzj> zP1K-vEiFZFgYXO6>s=C%qwLWNG?fI#%E@tm%e90pahGmn}A!csfO9k9_EqeI6Xe zvd{O}t!c^S6gHpX_hf!sH+{y81CwW#Gu%ns{fJL^0stS*tiqm(dfU-ZisBU{^~pit zJiaS{qJh5tr)#=S$N1M3&dY~`X3J1E=jdOjogaJpOz}sv2Aq2yY4hGCL1PO0Oynoz z%~d*&TzmN4m==_Mh@i^6Ycfl2kNcs>F|oM#kT*b(*I=usa~I&w;8^%&dMNHqWs_LC z>wkCp&k`pRcYcHrHpw%8`aSyFwSSN34+~-oQz2`zR~y*>K_M*4XD68925jZ7D~WeiarGOqQr-hcf&5=!K7tAYHB>~ zeN6Pzro#+wniljP$dLQKH_THVux3k)uNj&~$hj~m_p~b!8V#Fpl$ZqCQu za+%$I+}$9@8D-L_yEx+|BZ)=giTb(D;y-J_Di~g~j_R)Z!E*{8ho}Sz!3dC5mS8pa zv%>3SkJE5E8Ga;0CwqFdWn^;g^@atdu)seJGpyT?++4?=NhcTL$VNjZXU~^X7@fk* z`$-j0=du9g**}cJ#{NiY$o zMrV{s{N}e%P>tVgAHzCvnbi}}k_OeugmEtFU26K4V=ktG{THnDkxMrehx5Ei7?E4; z{&8qiN?o?Q>VH? z5xztvg|$7ThgyC@(CTX9YT)F4d^i*ml%Oz?R&(%l;U81-rQQSCl74cdlmV*MX`Lyt1x;QTimEY@ zfSS}(rT}!O!hEBbF~T(z%te`i1Ym4&wE-g3+kv*t#UoXzn#Y_0RCQMH%%sNBtC8r2 z@uXOrMwV+qbtovwPAuw|CYlxwrE;umZ+MaS;^oly(?pXW^arc2*v12W!`|pYBPz~s zm%}yEuggqQg)FDI`s2!LN;`t|zkoYF)LH$uN$vHF&50uE_4?g4s*I;#f|=kL$L34R z#&6*Rm)^Q}Zw2*nh>JAME^MCkN!0L|%~Y-3PY(AC%o(-%Jhob}Nu_%ta?C7)i8L){ z>M6n;iimqB!8!m&-)7*LnfNW%tZ}u|?W2Y=@s(ogs8ORl9df7~!9yrx_QUw;X@g+| zwjVN&?k|WS$HEk*%DN-MF;By@K|P2;jH5fAXB6>bm_X*cL}Zir#3SqHeU?RIpAaZ@ zMBgssEiErXUxMedKPYRki^bTd-pLFCT#6WS1?@Q_`O`&OlsVJ<4mf{T$hsQ6e{RHk zC^f>7iZ7hqQ#Uzl=;5KwYdLP*;jeo?K9&_5)+nDifHoeJDTY8QqMxsC+;+{L$MG+U%EY&=g$Y5KH$Xt4O zKa%dFR=y0fX!p+qESBB5Ek*<%r>|_UHs zOY(%gRcqL^Wi$nky~ns@s#6K{;$}}9ixoD1XI}1yYd5`(-%I=6q-*<8J#|kWKQ6VU z!3Kp%z4soW)UgN;kvihkLZDpV%%2-=^$=(rEfXiMuS)*l&3_)%s`ysF4MKGaToX%r zLMi93tn}8pTU+@;!*2ic?o7{kG7x0_0E7)V063?iR#MLFD0{Egyct~fQuoMXn&&>u zE2FTcsl_}NWt&_q-c!GYOlF}}`Nz9w4*@*9V;IsGt-8xS9dx&TjA}caw>PfLu;#US zn`s{Dxv!W{5?I?zX zJ>Om#>}WTBU}%PRI( z*&5htAf6K{)N^*lrEXIGrU$x+8vdacj|~L2i2H`3g=)Hn)#+c`MZDYP`l3x|SwWSS zOgiV1+59LtfMI=htiFj!{)V<8NW*Zjt=DIQ$w!eAKimdP^#Lm|(q&yNR)8|;FF(8C ztPPktl4S^%AyV_{cO^qn&C{ubGhilWz{)Zd6L&xTf(1P`St;{Ao#4@ zeHdZ7vdo?;0u)3-e@p$uZQYwJ;1{z3#qgZCn7yz#cOkw@nm#+4)A20sgp4F%=sH4t zxE|WWeuTvofR`*mE8?N=%3(}y;xdH;xW6yP`>;$wM^(6xSrhX*=%Ai0BqQM^1;>P9 z5}}agP&znqQHBvBwDLA3#nACbol?)Lz{e|T-n@BnI%O355A@vTx0b7L#k~>u&g%fZ zj5U-21ml$*cLGmeU2go9t3QK*o%YqK9Q()J#XjdY-#j;PbnUGv@0%}nD8H(c*0l!L*AEz8)A85DS~j+;cLw#f zb~*CK%{_a$cE1Vr9UL8#($e02JLdfH;=;o8#IZ{!6sE24cb)^mN2abntY^XVOGdB} z*JHS@hPuk!%j>FsWG6UHOprf;wnK)D0P%B(GY4UGqpKzD!-w-T41{)znXsjVNMJWh=BPvY>&pey zFIHy_`@8FJ%5^HC#5ub?kZmY(LUZmVIEM=CnxDsft)VTw@7=oxM8u@5XZMQ94yvJZ zu^O!R^qvC5$Sj~g0f!74KE-@ku+-}lbHP|ZO>32*gd8i`&bjewLvHOphoz9A7) z@}thN^;*mqnn3H;4H*m*-&gspJrlv02UdR3kwnOPBk@yqB_{veeA>6> z0kJ7((vIGS8~@y(zlwsNVtW^_~vL?d6cJC%#XBeBX#y&Xd;^!>zt&1kT|))wZ6 z?e9nQ^-r8Q!CLQIGpw-7o?$z;Z^z?}D#>O%ry8a!vZvp&S|Tb6hveRtbf~nFxw`?C zD!D?Om;W+q_wkNHaz!qV(pLJ*Td}<&8*vYM3iAPd$67ncJ zRNf^tBHZT3c)u&j6q;S7u=TbM;pgJV<0h>5c4wMyr*PM0B zdSWQAj_6yXUisf*I?4G>4~%ZmVraE$)!6k**47b1AuYUjT@LcMUj5qDLu-JEfoqx) zA{5;B-RBOTdD|#5}CeQBwcQ`xF$WXbOOYftKGjSN+6v4!rqPd;k0?37_>UeJRDkiyk&(d%Mj#Cfzc=0_JD^^DmNa z+1x}$$opSM+dXTGxk(Y-Jw5(;ZE^5wMB318ITgTfHI%DLc_~&9GIvtpll0!LfOdvu z(2u_S3~utvKT*b*g7fIcrl~iaQXdIVg3T zcov(R!imD?l)Q?P#}EhFH584c-ID(m0(1AF5uY?=U-4kobGky1ntD{`?ga-27k(wo z1FXn`A^WD!&)hp)0I zW(lk{pZX|Bb(3}47R1CMB9Yx5`fjl^VG>_0G=hlwtPvSx7CuPAa98?a}iL#`zR-_cC3V7tO)EP8j_>nJ15wR<|A2uL!KKDatbr2Rj>=@ajITHhAv3;H z*F8+B^;o463k@|X>QMZp10qMx)m1m5P;MP!+MP}XLhUcTG4_aEVZS>qr+LD;^k^k$ z%{%Ea_Hnv^h56SmWqCc^0-#i4h)NzpXA*>=pj$&t{FwLoPisJr^WkGyF z=xlB#yL>qDucINsE)yP}Z@uqpVpKds^{_pv%1fm_o9woT{$ciz^L^D8P&fc2ro)X4 zLK}bAAG|>dIitR)eyp(JrbQP?T8Rt4(p?ZvDpBxGy(pF2y(rbc=tywz965p;NqwNj zkx@<6-#HHmHLKzZSk+o~r793LF z`VgMW0nSo{KEeDxya#T*2Q_?ZV!gNu6e<^Y-gDPojljJRA9Ag_>HS=26czf0zV;^; z{!XiWHWsvZ#w~iDC2D^D^z}_8Aqi;Igg^*K#Rpb~by%ZDcL6`rFWpjI?0!!u0WBEh zVFl3r>MDLzmhC&|&he4)YU6ToL;F%4M*oOv|KnisKMtXlH%U~fU1}!ybR)6(){mNo ztCq&7_hE&qe^LC8UsdULssHZDBwqHjrP4OTEPf0v1(jq>?2pfCjD|r&a^{}8HB7GS zR$f_p^mWbZlS?sA{|Dmw5CTTeSvW8m*4KFtQReXU=IQFDmYP};m%=B~SgCi`{+GTr z%l8Ge5j)j>vX+(>IV2wJ6x=E#d)Rz;cRhXlm@H7T?4TgKg+Fgnq2C&U*+wxG%X?3$ zS)LS6ay}FqU=2TywUGh>+8H9h0@Gyq4V7K=xT;C^j~q!wFdkOa zfP^k0j0$W1$9&qsBD{z((uJ5UP-?dj``N|XR5V>v| z$un-gyYIiyYqaW$UD~f1z2Tl9C1I~=NOv#gFid~r@4sMC{hXFFAFH&BTmuuZsRNfBq$8}*(tb_u=K36fEt&3@&>vJJ zru5U7tKMPNS;z&B4%xK1Ebo0y^^la0co_?xY_>g9RRiis;JI8a_~KD^G$CH}W=fkQ zX#fEIy1OW*Z$+K$XVqqX6ncL{?$;~-2h4aAvQ*a8T)T}_)$oa(7yh9-+5SbpVj@K6 zW|dy_yJo-ieUOkKtu0YeQ9|FMD`UZe1&Q8OF6UkR=(topE>(Y+L}4Y|+W6K^3n?AQ z$oo=pm!5V+;Gqd5U=^s-hlCmx>&;0+;b=guf)DyRJFbffJV@3*nt)`A}X{KRjzj#vMi;{DXpjlKVW zA~64jQ=P!V>(`AkspOg)mhXo36tCv=>S4YvCef(`%pTwROW%Ja2S0CIq4=-vE|RER zk@72f1WPxcTA#>(O4W`E7c40%Dahvl4s>ElIYgJ`j}DIpQ<%|8#oLaqvu5=E!R7mg z(!K#@M8s1IW3kf|*QBaxGDuoIPOiw9FD*re^G?kEd0k4N>-u!m(g2$#Q55oz`j&u!t(SMCer#sUhf~{?9B0k{0ejm1$qE5>}!L>i1lgA?TO~ z(OWW{-T>szpj7Fs(*=W};m+D{5~+t%J(uQOcty}g>9I`c_1;9dB9X97?TGV8Ss8uu z^W2?*qK=F`3PcI0)rtx8AR;i6HgDc+r+a!o(4RCKR$3W4#vuW)8^5y+d?0jH&ETw~tix>*eD7%k16x*4Bev$E{dVD3cT#7yMN*skYY7^9DB8-FobM>_D%<&C@Go z_tXf;uFB&F=DWbUGIo7Qp}8lP5mG_s;DNsat`*Ut6c`X7^j(HkcY#1?c>|6E1U)|X z6z3R;>V658xox+s^6$W~Uqz5%FPM+_u~Y2(k#XA!6aiOrDDm;5k?GjO7#Ow}?4+RK~Q+s}{9>Rm@|U zSbQYfX^TZR@I}@!iamm8z$lu{i%HtGIdnlnSSq8@M!LR7Vc`3Vyh~@-`TIA3A0>(g zVe2TOCdBstxr!9o1F+GiK^8~ko+&2{4zlnS-`zo|+3b~%b{d1;>mvIS_L@x0r_-!K zhsHnG?Q9iYcfyoTEP&i~GGf{n^dk1~_@B_S=Y(5hYdV$J7}(sRc6d(DNCXC&xNxH} zz$zp;$Hq*kremCq{8S&BvCp@zyJk97TcC|83H^nXHe{$tp-(qJH`$)#4(B&51f6BA zm}xH_(5>}Pi+TFXyo~QAMdx}7_~lhDH>&X1&2_#jU(NX3Q-l78J5uqEZnDlHqP+`r zx5rPO%-dM+qUg-twkDOLs8vSVXyHtIp-kxEDntEA3I%F<4r?(4`3xx^R zo4@6Y#W9}_&aTCFf!w6jddc6b9 zi8DXi<<=HbD@y12pGkG4fb+qIU1S7w0FD^mCtLUvjr;Weu&0dTiwsOUcH%@elYwPO z60U9Bv}bF*Q7o)_&I667*>g>uwDRDX;wiT~p=W%NzwIjwHDV~CKQA#>t3i*FcRI?z7BRc4gf+(av+!N%)RowKCb!D%@U$Z}6Th2BC6k%X&)+|C&{NuGN2 z4#wMpWsllzm{IAW=#E0lK=`&jK<&425K&y9b%}i-g3r7&sEo`LPWUXX{2RM8hDl^| zQ^qu0ms^=d%MBQ9x@Put+Yg)8mH<937a)O>27?!wxon}Q!7aTTcJtjjpy@^X;r9kKjUC--Y>DfO8sT5YqaPW5C9)6c`$dV|G41HJ>Lv@I z+e1Uh2p+3>j&4(|DfAIvsuJ-+@e)mN)gqkVh#y3DP! zrq@|Y7!muL*V{ObD=w_OxoHId0s8gO!Es*X+9JKOLZ^IRwgJ}G$l`tHuz}CBV~YC+ zS+u@BO1a2AUeNq|Ap!kuX&b>yI;9<@+(@}K9kG}>hFTfH(={(K-oZ)5^N*|V?^(dnX0fz=Zf7|ZX zb+>F=#JYT)E`)>_w90yTY&m6foZO5<`^^$AINKA|!LFkyqp>kUf8zYfgDvL%C<*CP z2k0|z{(Kq{DR?-mwEGEUqI9WzS* z_RQGcvrnjJ2y@7&X@LMQjFnLZ^&W99xMM~>j*n+!U*f7$pMHD;ePA_B(fXEh8qg?Lsq zc_*>Mq=ZJrP3;ye7}oM)bEO|@^6Lec!d_L9t5WHBwf%mz{1>g)t@bVZ-cd|O%Drho zr1YsdIGKH1Ro(c#(dBRVWMp#aNYRWCE(+3V52oLX?*i&;0iy`B%6P|=wXN$5%g<2eW6mz*Y)g#{; zIWa4zH?Mu`LfE{Mg%Rn?UDFRPbsIVO&WWqKOOA!ETdDW{{do4PU0tW>MaQ;hznZ(_ z?$FnHF$?b)oV^{>_~zz80T;7e`%P+SSGSKx{GQ2cdZj#_lsjte$fGx##%{1^JLHS| z?U_24R_bgVkk}@D)aZnl)7IE7GiKYzFU_w{+zHV)68s72{W3kwCXV9_wJst? zdnrHZ8% zi?SXx3yX+=H-@(N#Wn+bQFEbU8k5daSB3dHe$0A6UL2u^Jz33#{@g;n&o>e*WB1Fd9J>9x9` zL7_Z*#F4RWByt-M(2DgFPzNp9;4`+dP&QuEfd07N>>7??H|DNgk#c5wvhxz?jLUC6 zoqBXmjmU9i`%|ws?kmT$+(ngei|PGYYet{eEdPfn1tHNwR1rR=zHk<(`oD)h9@VrgB?R!c$@p*2|5$DKl%nd*%4G~5vM&n z##V?p7mIBqU6F)j_Xw!sp}i z|2AHq8EgHhhMrSft<4dSYp>M90qWTPp<#=egn}`D{;^i|P80UEYB%jt0aX`w_$2H) z8tVb&q&eSi$iRi882s&Y;mDEJ6KZ%Ja3Ay6n%FO2mR#;oFPP`Jt++U-?zj@W(?drjKu4`}6U#uKHOg!&~S~ zDC-eM3k@+;eCxp{KW)4)HEQ-&!>(OrI+Y;z>1%|7Uv$5?;C|8GgBy)q{B1Ce?0_vr zKB5ZnxW7Z4DtZ03MgVyGCVyu_#=>J-|DKt-stt<%H`tDZ` zZIPW@yYxvw?BPRGJf=WXNEqFq{b%heo@4NGdnT;&5Suk78Ha5+|j7Px-M{6^fS|fQDB_Kn@1|XDTm}p0W53 zB(kzeEFmjQ=)Bm9<%uduhbAEA3Npu#7m=*8U<8Ut5Qv+0`AaWZooRj0h9k8VaghGeA07(vo1 z;R1XcM;*`=W2Os~Gy-O0zXE5pekd+c#1(YCpXtgx3i(bkVozrc>Sli_ki3eg(& zk2000Kb3BKTzPM%Ca{0Cftze@vLzq-+?_UUn!l4YrM1c`_wyL54+BYSdcy4*;cFZo z;8@RO33zQUsKpZN1&@6&2Q)!hvbLvV(s4x*W#F*aTkM;CbeFB;mh*20rg%hsE zi12}TZr^r;sz95~fXUl?#*wE?p=T1wj_ct%9GIqG)2#AR~i^ECqTV zvW!0@_fkjEwKhj>j9v#j_>hh}!6|<7Rmv@^&KVj3qH)%|HleBNSO?CuSh3IuAz~U9 z9MZPY_(Dwi5#5grzX6_8N#aGwh;?as!~0eWZ=_;1tw%dd3x5HG2s&F;I z^I{U9hlyhm3MwDc(!vH-zMfo|lpLfp4VD_x$6zJBPKDYIxW>gNxY~`LU|C zHn6`O8n!8f?VY&~c%q^o*2}+5rIm05=7J4p)DU57e`Z>q+4Pf3s~ELRbI@H56o0-?kasY8wU02r2;gs_iv{0eg-Gwm6;eD)BGfdB?E0Z z=PRB*gz$4q!a*|VKj9BNyY8ue072{sg>N^qLULW@Gl~@mM>r6i*cGlnjog8RH-Ul8 z_Y8w2nZq@^(o6k<+Q^nU1|2$FW<#EDt7=X$9V|DH+PLUtW0@8MFEF?l+sK&4QpS-u zIwin!Tnu$1bBT%z>2dWSkQGFBXJz8{z$Vr@d*@`kJ)lO^`R%*DTY4$WS2EZMXH@1u zvpR58CY72hCS|RToId?Ul!&+z=q3+yp1FO!)>u^PE!CBY{fdFtsw+G%g3Zcq5UR)d z?zgBu9aUG^H9LX8%|*G&7mZxH0i|Hn&Hx?lSDf9d)lW!EvH#q&ZMyou$n#|TeuY>e z#Z_n$2^rt0y-)jgdjf(H7l=Pony5rTP0#UQn%3HQeG51Op&Xn>a#DucfgV84B)yhw=se$iN`u_tY!!Zpq z9?yyKiKHMAIwo5oWoP6N>y;v9L~pxlebR}XsfKpeMrFQY9>P!_i2YqV5ma1SQXx@6q!(24*459pUHH zEblyY$H=}lMg0Taf(BreAKmiKSDpKUUQ6epDjZJ{8PqZ17*mR0p{*RVJcihDDLJi( zZ&Pmj2zAA6^tO`&TkV0u#!Z;u4rnJbOI>`R6@8mloHGq=2Q8M_i&v_9 zHI3l~b*9!Y6DMiig$jFr`JDd!uhnq-vhR zz4WdGG%nQlx+##ZE(3o+5(H((T2aJVFn9N9@>mhbpl+IuL|W@ZKAma08BrWaIxfwD zKu@vcl-gD*!>xEW-Xi*hTgr7ouRyC}_I7RixsOzqF?=z!#oG3Wj!Q+K|JdR#TksUVIX19M{w`R}APYwY9N%mUEdJIv?k|74-(wl}9w5 z5c`5i4)XZh&W$}3&#`HTKE9CwV3Q~BySZGkGVs!+ODNm~T*L|bzA&!pQNC-pZq#Gb zzbDh)K@--yPK`bEY^<%pH#TK?pv(EDT|cf4w! zN4J>JAgB(%A-Z&>rqrcwD06q2Qc+RI;QN}Ik+Oz}+G;ERld|dG|D;*H zT0rv@0_A4ziDyz9A zZh0%y#SNg+Q=9J1y^|cKnCzV}~1WI9}>xp>HsAzw;K-K4BsJ9^s~3yUQfqZt1_#T0pj_n757;-IWPrX_R# z)Rf;a_U86dl{;5>j?o%qK9KkOJ~rUp-92Z}g!#DQqiaym8WS&O!+#@UGc+_D=F@#K zru%;BA68uR{GHiobfKfA8-*`nRI2bsoGv~5HVvTpBHg%zttJE$7@s>V_-`@l9rz`< zXL9A5P8_@Z0 zF~2G3nkTF9qgVv%&%F=!kL57YMQ&TVL||z3z#b#YWHB|QqL#_Jh#0cO_8pg|&?IL08WOr=nSA;Eexz9*CAvWqEi57!EQG@P??25Dc|V{#I7;VCty0k4Noa_lv^Rq)bTR@juEs9Br<(`K^hh z&z0z+mzHn@{)A83bgNKeCCB9K&>{AJ^y69$G1VlY2B0RNFKZ#$fzat=DeQB-&+b%H zcnl~XZc(j*i?u=#R_CvT`&#WxUn%##r@PdN$yT}M9qEm8(;m-92wdvN^|lR}K&?*3 zHIj0{SANtK;@pbYjgq?)AY&ps?*qH8tYH7 z45v)BZGA;BOXVb;T#u#xLnk>k(WE@ zy*8bW&wj6}xN@k%KcC<2Az8j+SzHg3D70F&amRsC)}Wd)_X;eaOM@;G(anvH8!}s8 zQx zpL>6BBW0IanKJwdn)G)PCx`5J01nVI&cp3sko4V(1mf+f``#TEQhDQ`0OW>iFgq?O zwww@YSW9PYf9pKL6R>}zPxn(q+5tBytssZKsP80{ryu-gI{v6_*`9_9MMC9y8FQ=E z(_3L@4l-&Qf(&nD!1deG1_6g-alN+v4~!yAVpnvh6@Z&Cd0VdK2%q?bguTBF@a{yE zvt@i6coxn$cwgSo=Lu~}et|wsW3WzEq+|AO9<$f4~E}tQL;DybbkC3?x$XWiGIBwdsyP3y(7~|wj2C;ucV}g?u_Lv06j%K8{&^Rj`zd#7WEYaN-Otw%|A5YFmL*(RA%Z-S zA0%6AGJT%0)>GifT_fUuBt>sSpl$W?jTYndXh>Jh_Xo--9*ppq-)DZPq9L&s<|NUX z^kSBs%tU#*eHLTWjNj%mSAc*pNW0r&W@b$ZpZ7TPxkzqr*{M}$ERi=a;YOkek~uUj z$KmwaKJHdVS4*MDC?B4C=9em-t(Bocw3lF<1Z(FPoCp?ai-|eWmxX=*&_csfzz_dgIbGfoIcmNolzIYmtkyMGwIVZ^BHB7*?|u`)sN zZOE3)x!cbnd~!4K61Ie{E5lVw+q|{)V|1~wg&)6b-@5g!dCL_Zy#{!+ef(nuSt?hM zX2}Y=N-8(=#ic`Nj4XD$;=3QF4CRvRiH~DP-tQt3>Uo=PmVG`kf0x>Q=$LRyzjTT-G^|`i#nvh8 zSX7j8GnBnU*Hu{*r1h6_orEga$sP;8kL5AP@y#5<>~{7Bikh{#Zijk}+dfB1TRCD-2& zDbh6!*ZbF}whK_(Y3an{^GklEk|ira+D-72yIAgtkL^*}k5Y@_iAmn!MEjC=0m^_T`bIG6;2 z;LJ&D{pxsf-8(L`q0k_)(Q)?e?cKLVB0?ok{>*lTqHKpNJLY*P1FLzL%VYl@DEGmW z@UXBy6Q{x*_+xJCwrw{?8aCvyd~G-J3j{ZcgfB_`He~IlZubfD^4*EtmFvnS5DkJVP8aJc^b}>M9Qj2VO9bT3ze&VtRuW4%5|eg1d-HO&Q5MGE9bFH5 zK55ISOrh2w8+7wl#689&-q_kWnX!0@&3{pZ-qiTH)wd)ptk11}E^*5rZr_>ZUXVy! z9_)88Ao=!Eq%_Bj^a_?>nTiHNC>x7Id9b+8FR+UH+1WL#P}*>8NjSNg`y27&XmEpO z*=+^Fv^H#ZYzZD^Q=~-fsTD^)B)F0eG~s%Ej}{PvJ#*s7kz0L1$X1uNRNbX`6}=xj z#_R(Dq0m)gUi{hB$mnLGUvkcE6qxvFA!Ap0y`LNR03!wy)1@jFXBmdQDEl}2u!9Sv5^SM9;B@5yD=1s*uM{sv{0c~`#p@a3hEX5-cxeRyy3A_nQ$*=> zmfih3)z-pK{)z@=_oDWmmr$9LIgvQt+Y@<~e`@};Kfb+AC>@~I1ZBWp-+0pYDYV&h zoy6x{XU21*W}oZiNlPC(OPkJEI0O8>pmI!`sn?Dn3Xgs@)rUH&JXGf&Zj0u>S$5Ny z$usCx2S)AYZDzyK!hdgYL3xyCQ)Dk#FC?;*9v=7>0jz<@yBZ3Q?yBW{=G`M@%=U6; zHqSBTDtTgK`+V@+lCfrSm36DHn^km0WB9i;-us-$_ur zzS7Ty9iwX@u63}tl1boM1;iS%(DN0p-L<9O^|0zCT`3 zb^*zZ&5?QJ1A7c@w#ogME%hi5DDS^_$^A#uIsR?;bM{DvVY8(UlY>O@@?P|MDTB~~ zJ2Ue;O~YTVH7)|-Z8!IpLgA_QQspoG?MRDn>eRQ-M={5LP729q=B35J`)TjH4Qu!` zF769(Znw7~6k*<=0KH_)2;NCO)jRp&{!8M;9!p>w|2gFhrNul6wYOh$qxYJO_SuSj z$|5_@w74o-DUp%Rc^NVj)Wqqy@)qm=KO7Fy{pU3umN$7DBAx1QLW$W2+|6KM*`(W@ zymLg%`_d^U>=Bm-1@(3*hnj-Qw3k1xyu(^CyXDQs&{%clR!cEkaWn)keQvt{Y$)YPd5KbiGPMU_E4uC!!~t?g^t+#*sw+2ms7^O zo+zBEcj+w$NLPAhBetCJ_pW^uiVFJwir%+>Q38EebRjaOh|CK`*r@yvXeI?R=N%HL z&-BCAh9a(f5)GF;OO{c7`rJPImW`(&;8(M=_v4 zofD)rPk!$eQxCm!6Gy(m2AR8!r|NE_Sy~Pc_jQ|FTIzGzSf5|&4ielnHS&g zoj+u#_tz_p)(^O<^FDjwS>R4AQqoy}cw*~;Crz8^Um4PM`_xlWLubJHN8IDCGR6FD zk#e-?5>ymZ7)o}YjF!XU_;wmtx-iO_$YrVK40_a9xc5ccf48fsR>{P*E|D#z=cLnF z_q_AT_tM($!RR+8Wlz6eQ4wFR!f}hjupgo81ZC)2Vw_VF&{Dj)so}#|o!_S-dMV5? zfu%w5>FRhGv8ZA7b+Ctb5e@*ix061yXpjrxqwYL$VU}}###ubYfTj~yya+VVub?np zxpM50h&mdJuv13R;uZodm1Fclqz?Os>9woP} zaj&EuHiBLRf*WxhAn(=JUBkFa&jwM3=urMy%Pbpxazdo!J!KW4b1VO}$sB3=$Y6=_ zeth))`hocT`1fZ@piA|~zd`B$3#I-q*8Wed{k9S>bUp)_OtR6;#7N*m^zxrkofTTk zqV5+yl#wywfC681slvdCO^-#{jE*pUQ#3 zr%s&$JJQKW0yi@7ZnD)U=-G9fGWv^NoYCvhu8l>Y=GjoQ_0#lw!|4z=N||l2H`ZZ) zG~1NgUHbKfN}(ueih!)u=i)`O6#*wvio8TujqH8b%IQM_0xUtWe53L6FJO~J0%AF= zOwns;`s(!3nDTL6kN0kF`l{VMgAr9sf6MZ#&|}VMuY{hnN*SvOQxp~(V3w{v z1Go%D@v^MsHOrR$BoNLnX_O#j`5Do%qQ?6y7Fzc_JKNB4i!jrF|L}DZ>v!=G9th@r z81(Mk=sp>xAdb?vtGz+ zOg72R5eXz%0oLecKID}Pqf&_VAQOoOq7Lx21&ph0xMFX0?1fi{_Z@egzqtJ7JyJ6o zyn*!^6bTQYPwE%*-v%8bLH9l{$NVA>IaMQFyREsI4%5b^I6SF5pI?l>m0{A-$n(4; zzgLE#x*@B)h=mH&G(}cFC4t;BU%m?NG2ZJmEPV@qeU*QnXegfOE+gXX+&n9UwrMX7 zA>qPsOGl>*3Uy)tK*rB-llEMll955i7F%Hy33*)7y%QnjdhX<9sGhxDD{~58aM`Yx z+?*>=gXFG&2H9aPQqEFDsk(^H${UFt)W33)wM7!Dj zgpvv>1~GhX&Oh_Z=*MWC%X@!<{k4f2uRKQn)cAN!jyz!mHvxIPW^W->$Z~?fzNWHu4=uJ(vmB{A=B)J!h z@PX5h!Ii{f8DT-<0CvU)xnc*y?<2YF&+%DK8jBRN1OSYztxNpKvIqLSeQY8BW&iIR zuq1Pwqgten0Q;-lrG_v~u8G`_bPVYKt=~S{{rl&$*W2OENsqQda{|PD%jf0zOtJ)u z)K1!$f^JVt)NH-o=CQpA2q9sVpt3@9p01r|39%z;awBu|^puptfXFt9ea(D$!kvYz zaREgHF*7nUC;&7dLaM~aXMm^R2o?-@)a}{Cz>}x|1t#b!oIOfEj-erfa&8GNCdw>g z@r`eJ1)q(ryXZBEXElrzpY==HkM#g(=)An`t_+H-CEOL_vJ5VnCe9`dXu&@qmX{zU zqALF5t&bVo3?d7W!4&S@&bb(Vnr@v-{=g{>W%G~M>`~SJHjpX7RXT%jh6WJ&wA;rY zVrcj%J9`>mZ3i63(82>}w?+5Mf@u+|eFZyN&C@-!i3tgpaDd3b48&qo(z9T0Vo(X- z3%cw}Jum+T0^1QhXYvK6 zhJ|nwfS-Z~{}xl89bn90mJ~SZcyR`mEg`LfAVUO<_<*Zo6QrYqTb3p4D(`ON@4Zc{ zB!c=KR_>HF=#lZ!izw|bf?bCilPubRb$YvQ8$KVz*}lxOjaR(&!dCCM_Zpss+HUEhoDq3lRlEgVG!HLuVGanl;*E$D)!26Fdga)-livRvzS%snG3Yc>CESY~8fZo*Vbs-y>8at}HJ8D8}sgJ7|P3 z*ZzrN3lxP!6%5%JY_E@zHWuhOV%o$^eYVHCRlEL*#fiTJ%aZZxNbD}-`+>y`3sd7+ zvyGueL3593X?h$A!I2i2IvQMmzs0lCT+juVIHlD3}wTRANIJ80Z6agZ97 zZ31>jSos)}bV#)0@bu2>8wy@EG9p7JvNC*SlQ|KI6W|wTHe8WS2s9qj)xnvR=-r-K z!xJ2=oKxb9rEcqqd3kxp`-50a2X<0EK(!kux&!IoGFgvDGgulDJ?JYRxv?3tS{h&o z=j|pX4N1S1J@>Wgc&{w;wThU$24$;-%q)KYK0~^pH7~u-R#uGQW`QF70mQiYjaP91 ziKwjz`m2xEL^`$)94)DPB7T6=P~+pNtY!CUtm58#cd*Xx*rK|-@Jip}PKA&6*<~SG zlhdDQZf#Y@25B$>Jd0;>OrpfEPXIEs5`N~&v+d?%&Ue8g%g+0$hf&8NG!1_LM7E{5 zzJ(>D^lNBKn&0j`f=JB2wAcB9Mf4S1%Qlbj2@72~3y>M0-rJ5YQ2m$C+8fwLUBY8w zrnZG7tw54k5R9MkX#DA#-LO&Rew8*B`A&`#E-4rWl)5GKuG%jgY-9pPDBRs)ma!UljV)Zb@$NUUdN#bm*-fNGlqxk2+N1Y zM&e7fWHd9I=4O zeAmJ_5f#6A{h1hriSG2KsTY48b8_9-eeFWtD?6y{@5gCIyYt_AEx7_v9&^7S#KOKZ z{wc}~QJgQg^2=6?psB}|8ngB_W2YO&$QzWeGli1T9QO`uoc8t#4}NVNlBL=US#@tA z1OEpZ)oc`|BK1>fITM!X$OUiz>=A3H0d>QxB*!NJ;3XW|z3oDo8cPu+fS(l}MknwIb znN8CIvv^Ijfqp3vsi?aRCj!)TIhQc+KgXf;qnU|GKB{)X;4+l1iOMn2#~JyZ`nmLm z20hzrUjay}6>7DP&^6I(U>Ml#B^Ztv+b%Ifusx9N1Ot{ZnhtWFDCj_V!ft^u{|y+1 z!&m`ZLIk1>^y_Xvmj8J_-2VQB`{_f~b5&_jDh8qpp0sq3(yIqQ5;EK8o zDd@>d=74%p3@SlEso`9879^lCi{F!ml3r9pu3m^8+}~-vT_`54d}QOm4=f{ydWHZf zHY<--V;sw8l=s_5UPUnsn7yWPx!f2x^JkwRrh=scB@K%g$F>d`?^d)()GXj#LjJVG zQshJzM-2DF{71h|E`~7k^jKMr7d_^u|7ziDc%8*?TBirq(-$MU@L7W`CrgSvO4!Z8 zQ$7UKaG$;J25$bf(H_NvV3__!y5=2R_fUJknLAkB#xaiP<1^_V{$ledta<(>SuHEYfgrAczmL&tO5@r+Iw}bsX_c zHIdw4o&?|vc~3Xugm20NM0VbZVw%-}QC-cpMICW+m@g;7$CW3Hx0zkW)*MU+-*pqb&1@bd_1>%%_GP^Eza;+;)ftVii3 z>KohE{jw)Z@CM&Fl^K0hZuO}gtuh;KPT8(`W<(ZHvt4n+Mal|6ePH^*Z6^pQoh@BA z9D12dG;m}?OP<-~VQbB~bLX0>c*gI%#U4>sRb%{$O(TtGfw@PdCC3QkNe11J5%Q7o z9-+>cRbD@&kePK2(n|uIHlae&tC6c7yZPqSFJhbi z4RV20C(sh}s?qPe!~q`-iA&E%H_t5idLHsI%-$kMw+@i3i^ApR04^ zY3g|<8B~RBL&uN0whA`!%^D;7UNxkhd4~Fx$OYv3vkIh&wyk$B1Di?7Rde4QmD%o{ zu~HhFFpPpnhyUF^piVoJ?q4rZ>9lTAY^%&vL_t6r_3xA1ec|`i^Gvt#%nwBz`ze}t zX-=;*X{7sNXzuw_VFYw$8d?B3`L5w)b=C*$D{qs%5emXd!eqauD|H+abd6~{Dx?p= zWvF2U7WcS=*242VBk`aQLo1WDe>8&ttAAZ7@yGwPIti9A#@#`OixKkXe}z0TD(7Dz zuf%8@&)C){$V;X!u1Kna>x$)*qoax8cizU+*;t&bjM?MWtFwofI*!UR zwlW%J{LBYeC#aJ+Ru^M4jHtv4vR7L4ClMntOMe4zWqz(}eRk#OC&OXetl$YKL4yTG>$XkTdCWk0gU=oDWPk_Ci>zM_{<#~v zOjMu&rUua?^?Tf0ln!)D8At+u2!)JV#BLq3G+l^$9}yy{oD?>!>?VN z`LsmH3GVgE$>o{u1-uk(6=oe2_ zrgq|(En3&+7T)h9cGJ%`8Ca6l2gAb@ks}pH^s#U=s^vR~AVh^Dazj;N4kE2u+x7wg z@x`c%IreT}ia&@Il2DCtDIC^w7)n6%oC^1A%KT~eXIPt2!*Xxg{~j~D^W~4&lJoSM z?BW?zS*Z2{$7`}?ugA03RaMMAWoWhVbxCfDaj)p+)1u?OFwT%eHg{%4yiXz}1&2Y{ zUsPhRS2XcyohFajl{{vz-;epzowu%{c+7;9@$0B0F=Rh{xVz+I#<`pW{e7!9Y->!VWjO^TCMX8ED0r$5UF$Lt5sPh*f`%wHIyja}p!at1(@4m2?2i7_tJ4ffvUT1KC zi;Gz0d=l?M>W2E>7Yv+>7-xXnvc|m(fY>h>o@`Jk+GpQL+50K`^4O)#v#;+rI;K%+P zbd7s0X-80pz|6`3iz(33Wn^Srg~fhkJ(?ZV=;x4xfFBV?B{+shO3I5Sf-~Z;IeIyi zI${#HwmYK`cCffofV6-U0^3mScxY~7f*qM71X2WnZ!gW>M7l<$%zFHsi8;hP{QF{u zsbP@zM@0)EI02S+oe&iLcEnv!spDOcZN1|KB1NJB;$T9xJsGZjZ)b}zfT+QL2z?VhZU(3$n_ z6$Y5lT*}tnw}598KTQYd!SKvtEo5xFm0K(T~BlWLcl|;+fuM%K|8s)N%f@@sLL;nS)ch_LV2CfwIvyC)8G= zcLmV`!w74iKbHWCR{oOgVnA&BCssVCy*y%!EWg&ddFh!HYLSo=bS?sReK^Ak2DOh+ zrl6x8Ij9Bw0*(a5IA`d4L^k zpwBCnT}?tvmM)e|SXMs2216P22ztHlggFM+cuz-#XF$UY{FKL)!cbpV{*VDq<%lvF zZ@u><@yK!gVE8=Hv>gD>*Mo+jR}*V;B`aT ziEAaDxejXOXTmj>>K0WUtn!Vy9@72Pd+=9YewOTOb+CFe)1FDjdr+FYv3L4wR=qE6 zCcq7%H3j>Lb}juzcLFiOg5Z_1woTqzYX^pM&dBr z%$Cf+>qhbEdR797L+v=9iQRld-{a=K^*)v$>tL8iQj?Q&5$0mh&j5lo|4<~6@|h?0 zM9^0Oc~Fu`|IwWK8qNHtLniLW9}+vUloQx811(?k(6PmmP0sgvSxXp<;U*sW}kF)5W_S$T2_dSuMBR{0w$(7}G#n(w|8dy{M*+flYCC`cuKCQwE zvn@`(?62(Z3b)O?rf~1~+Ti6fiVE39!Y#~#^ObGB?MQ@HQy**;TU2TwIVf(DRJLso zh3zfAh1|j|oh(Deq^+ac;Q2oNi?P(5i^wFw9|gY<#W92tv9hmy{5-|#6Y`Vu(+|@XKb@WI5LHfnT#-+_dhdtD z$=sFa)Y^T>2S#8JsBanf(+4C5B{r>}ruEeZX$P&!JMrB!lsQ{r8c%K9y}-|q^I`T~POm}O zSE09(JazPy5Z6LdqWVR(3Sa+XOh|%sg(-W8amZcO3;sw9S1rzIqkv)_Uj}a z{=e@Te&*vdL;EaSgC+9xzk}`MbpMGRpkcTxaI6Lo4y6I%3EWRgPD@jq=6V!gw2g>O z@x&XqAGctREe};eSLol)C?83Jh0+)Z!12!emX@B_eHd3!oBOnMNRvi&*yxm)L+F5NNF+Z%U(KfU7NN*eiH zW_B(veUqR36>OCZ?JgUBt|^LkDT!{gQmQNbQ49P&MX!wtm*5Joep9GhmfZ&zMem zQ^g+d>iYVtaFu>zs1h@RTCiLb?XR+KYo4s3VWNn5Y+T%w$TWeSb(^Q*SX)w3VluIb zntJNM^p1`0GnU0CtIZ;=my*2%Dkg#l^oly;#1q7hR=?*Nlv?|H&=yu8YMtP#Ry5v@YpNX8<^Bw!2B zb8)dK@W3mtz)PjcQu?oMzx~q3-1)|aWp|g#C(&9LZWF{m?;eLIZ8z`8 zRvfz=au5t%Wp5Fy0UwI_+qZ8`61!73&7oqNnP9OU7pUUr=V$3>o4UFDX8OF#KB&E4 z?qQ4J%LiM{VygMECQT--jDpk3&M!&HSJ@K)>9|r*U=FI>8NTX+#U<~4ys2)H;^d86 zxq9`S{dF!uK~?SB5fx6}bPNn$`>lbMynUUNgUJO)rR0$#Ma?_ny;tgN7uRoA`j#a5D)30PnGA+FP4Ll{6`kF1Fc!LCeL1zrB?RjTp!;O(M2d@P zyeq|WgTIL%&yRa$6R~u5?=btbmJB_~lAYh)swN%?{ese(VRVp*ELfR-R*LrF%o{UI zgiI_?Z=c2h9*=7LnL`CV0|S=L>z*!$C{@jH-yC^8YCN)JJQrNvs%Xt2AcIS$opIhQ(p4DxjCR0u{6t7>OdfYArxmecB8|f6BWC$WS z-uHk3#hDc$al=+d=Fa(BxKFF7sIH&Rqrnst+gu+9IlvS(aKEybRi?>a*%GynCaWT> z%`xP6RVyiYA#Mo@*m?>T7xhf3+VVZoE8b(qh2ZOOTF?$pQ(h;&Z4WeF4D)~E*y*_} zJZGb7fo%YS`DW8Gv`6@kCX|p`!}S|CMjvs?Z#_vnem9&IWdA}`V=t;d7-nH%uKK-* zfPh|`IyQW;FUD*hIeGZ6_%s{8r@`Nr@m$R5!A4>g9HI&SK!HndxV3XnXO@8JgPZ>K zBFDa;&Xw6FF{asFCM~uHVyhb7&T|*i)(Yl!6<*JxP>_R996v6e-nN8=ceLEYY)3XT zy)5N7({C@oa8Z^Rt|T=v<=R867N(*;U%?;5Y7; z>ROrS|32@V!Dw5c2340iAdd)4=hso zV9x6rf_4}`IvpE^rfg-3#@&@1VVv5vM+56>*$RC-A-*0PyY|65v&|Hb$9460m?%A# z$CN&QAb{g>`sEU9f0$ZH^MNn+?eOpp$#;BPeDxS5+Z>#0b#- zV9J^Nzn;Z+xw??8t-Td7YVxwO+eEHCIDZT6Z`luuS5x0Tvz8-mrUfmjBc@H}gGSC8 zU7m@Io$J^J_p-4$Xz#aMsj82nci@Bj{xrsmhO|BUY|PhJ=QKv0Og2c3yW_kfJ1!Ts zB2@}zSd__-!IGNTOi6h#k3*4lm_R7r?OyEYfSWP=`EO`h`e0*7B1=lNgP|MY_(Q4GjtX6*g0 zBp$t%QN0I}26Xuu6cY%YFt>IwrkwW2v3CUj#g!V)W)IXgQS?vse?bDLy}Fr}_R}XG zFTnllLXOKREC1MMwS*M$wK=5;rraw#-j7TpmN|%?)4^-zU1)aqw*b~M6? zg!g-EDt9D94vNz4T?qm>;x zS5;Lt>@8w59MpKL7i^EW*Bbi(yQIh+LGM8ypL%~kBmpv zw_`(vMO5ghUMX)~=%f4Zc{rKZ@+x!Tsm30p%g$u~Y}h(1U|UdY0@q`wGG5 z`00FEDKmB&>ISEpPCu0S`4?Yr92Z8W^YQkcJa~C%V}pS0`o$^G3}zOUs=h$hr%^JY zBpf*c)T%j^TXAEX#zQ-0!n)Pb+sfyo`kY}Ui{Cj$O(08*Zq=vWmT8m=e^W~CN z&{6~)5>mYe4{P>)pkisHWc)YbNUu~;!w54?{z;oDc=#=Rhxk>gPHAYoL*xsh;LY=# zoqR8bzkJ{Cut-!Lo-kKJ`^a>(#EsdrQgUEi^`046t1Fxoeco+DFrcqJ-4D==A7RkX zYFk+^yF<*j=EwX(FVvZInLTVPES*8 zAGvk3B@Q*btwAzT6v}K1Gdxb;!D7#8Nd(WP6wVOdfbc*uZMXsF(6~?Ll zb*kcCd-3-52pSZ5iq-Z@Xf<4`43L)@iwfQtW)UB#d#T?aWUB8uwk~nqnc}8YD=q<> zVYP(yA3#)WNu`Udg+;P0wH2+P`pY#T6r>f5m|YLq(B#A1#!)+Y*S>wy4f_ePm$69T zaV{RF_Pu<^pOzoIjXo5;7!6+&vh=LY)YH?mXzT9xw|al%MZQD9wvy`s9d3)aUB^WmAv&Ad462>~;#%t#G~ zJ$dPetQpw~K-oFQk%D1&LXlmI7})=G@#bw$r2{GQQK1h4_C+RxfduQLEWdEN{kcVP zh9=%KRQ>>68f{B+y3DV(qy|$`8;4hf_#kETXfG%|s;iZS*U+68sWqm{1tF(CmdcXz z00;F`1>@ZcWQ9}rQa^H)nKuCLIyMaUn)DlVcW7GueG4yEz_c@XTVEbKEWXD_q8Jj z_xj7-eI>_LF~yjcSn}{#qd1+b9w|GoWXroIu_tJ@!#YnJPHme_8{*|?c^@S(Kaz2! zJ4K)FoTUEQFy6<<2L@Z^nZ0<9SlF<+Gdvfq)QgOe)6gXrE~b}#Jp0@vm|_A-oQ=-Y z1@IWQ#HTv;htvG!%O+&f+)%J)2(ECB_|Ls&a9TJ6IAU}n^!Hu26J4+e^O-|d!f__k z@8=cE%0%VqAiIK=(h=@Y4R6I5x=AI-kcVlLLYE=xZ6x*uFbNipM9Fe7`0`t=tKkdu zFT8bbsBVv%z(w}{JK?|HfWgC2tw z-r`)?i7k(WRf0Ly9e+B=6>%rq0%>-2U6G&`*!k(%?^bEpPRqvpRb_2$6qY_5KYmP2k!&gL{SMH3p1PM6P5_|LPj<9Tx}a!t~kp{8Lw#lDfJu4ms=s+yR3qU^DVA z=HpctIbN@-zjf=DcX9U%$S%x_qr=HR90y`EGfx}uZbZ;xD*$0V|j~(J{PgmSXKq3bDy|KO>dt8`Lz!&CUIteuaXQUvTDPVbPb0;SW$^Y~Ti=XDW?!>QZeJ^#YMw-bf#k~Rd z?{mwhfsb)5Q`hgXr(U;zOw3LinqGxPt=jjQCba60&%XUKYNF&QsaxE#M*KpH>^;|% z(w5QrBh0n^mi>Kw28M>%E5*vgV}>UPkf04tRWlCB{J=B!B|ZE9d$eFJ6N?0!NX)4nkz&?-LIBTSm$kuu7Ddmi=4h+yLTjpnxjt97KGa410)#y|$()eEh3PurLR74b+v6zAR}ow)J74*sP%tJY&Jj*VlLY zn|JSF3d-531LuOvf6nDHxLSL=RT4WAuBm=&B#XO#em|b<+P>*mBbM;x^y#s0#{)YR zvi<>(HnRUoNn3a95Jzr?Z%oaP$IwR*oEYaqjFZy@GeVS`{2#?!|9yaRt8)aR0ayHa zfSDa5_`53dUAY!u?FKmo4 zq5OvlB_pHc?CrCz%l}#?^aox-E4Plqbtc_3by7y~w1aZY_FSiG&vEWfsYESf8Ar+P z4S`JDf1a8vWJ2H3dr%VOiCq$U;&~lrKY&88^WG=hG9}~7LMu~NTKe5w*CKM}J(I$d zqaIYJ!UZnDDWKPk2o5oKo6!yN`Guk`HBO~PxEg!I<8e0lQS?9Mq}9SeM{BfIL-pzG_+vP-ag(fpz$%i^p zqrfC9>4E|P@y7>Qqdv>A(jP4tJyOu+T;>iUzdPlK>p4r{A?osteI`dO64%`z7nV;Y z2fgX}<>)Mvc0EU=xYHuVfa)4Yi8WBX@XALvftL7i80xI2V7cRlN1in6PyVWR-r2$? z7PI2!M`y0$y0;H#PgrI-<90%4B`>#o_wIa+mM@P8v*X7BSYa{%yWdGf zMKJE?zEm_+pr47~ybE{lpQE!#?q1d}q$@Z8%!Nk>>uo?(Hn83iUu1> zDlSFVGO)0ipH&Rnymrk>((D4!fp{pz`v~wSrWm7h1Nb0w@#_7FqQ0I_q z{V5?`zK|B*)V1O@lDmSF%p;5lAX#WI;fzMimn)!J^78R%=Cvwe;g@s2_`fId-g8kM z*3BSbpq(XqA={O5B`y01Rq>Jfqih%tQ)f-B;2*I2d$VDq|1TtVrP{iezOhIGU}{)J zTK}B5l+bbj0M+QURf6Cw-dyg2BgoM5^s4g1ZCOd-Vyi#!pI`Q1)vqS`U>1x<$5$bt z9z%gTTiMi(?|nHz{3cRV_ouyk&kh_OJu*q=VD=&}_kqk} zhhAE!O7lQ(dK}7~*2Wjk^+7$}tE?+~P0l2rJ~q1U<&}-@afqP3?nlw8!$?~-+f*}c z9l@!Mfm7!fRjG}2U)Q;OF!l0(pM>FQFmHe)4fOTZM2Vg0c%4nQ+(54a%zJjcLD?t# z_VcnDUdO!0dq;cT)!YbQ?^Lw@nJ+v=qfg62ZKqJRN#{Ul$J#jC0*NE`N`W>1Z~=~V zn;pSOv$&&PP(Yyb2&*%h6y&sU)k-|y@W13{NQP+L56~u(vW)F|ZR|O=yn`~d+so$t z>S)(yW|P_P*Y{6!U0&ejLa#u)nbCz}xMP7UgYSzC4_3$u78Vwa?^H#5e;gf>u=;{c z72QrMe4Z!ys7`YA4&4FR;BaP{F7`5&qYTLs6xw-aLesCd&~e{n zMy0BkH>~+j&%c_^Hum~$H#Z5OYdG3xl$7d#{sU)FHl7-L4=XANUlQdsba%ZvRgtPc zu(jyam!RLrrEs$dvozq+;D8WrP0B!m?w+? zf(Z(E{5QEU){Y(wc!Uk}vtKe?oAGqeJ8#q2uIce%VatvkHB%fBmD_ql>%P3$^*5u` z3T{&zI?!m-XGai(J8@i~^FYN+cu)Aw@0f8lI$Gc~bX3oYf z&#Hy@6OU|vW45tkl;{+yMTV=BkS9QgqtIdb?}IsU>{yOrz}mQf@xSG6QAWox=|RB? zj&Bpd1}pq8aMA?~$&tvW`k$`?W7Z4|i3I^g_icjvz1_m~P_|Wk8GZAsi(gTc>3C8F z0ruX#d-&}F8s zPbnPlz{S1NR0@*S zK-X5l{HZ}f;o(DOHqD~fC*pTK$1sE(toLYeVKd0uod|p%UQK@wNLSncLO^(R++A^r z)#Yid@5ns;Uo!tHB?!#a>+W4A2&WR2q9OtV14BZl(QH9N(p0cD>j?7t_U+pv&OB8s z53ADLQ#0QSwMdbpPGd=$&*v>;QR-sr&{rlY@63@y8?vD}L)E1%nrZNaeemf=;e z1W-~Wh1TcR_8;-v_7=zsN2cN71N~|I^xRK?<-w(|4D$-bktS|#Zm7jH5)QL22|KEg?gLfu%bLns*hT*c+A3seW*v{)#MtZ z>I=-$=o*3punJOlzW6}s739%35@ev$}s42ptuZTAG%+V>(l1Z*T9)lvRa$%I1w&|MK8H;N7}Oc!U44FNBPb zvs2MQ9N=++`y66hfr0bLwp``$LSVYSpfkRX|4`?uhEBMsuS{Xn9NW}-c!w`grVxiD zTR>b;*fphWY-IlRP`==^MEkkT195eS)Y4BrZr>kimZSAN>aTTTDl%xbA=*Q;`5x+4 zL&E{Mf4oao=MvJJhf%VRWcrqi0Rdb%A}FkJM7m4TtUqsQ@S_s-0vDEJAI4~fGcIu3 z@3(!jgsq1lxrr0PY|t}^L`qyTFa5R%(^(sZ(_E(D-fFpk2A{Is4*}LMj66o1JUwg$4xEzlRla^e+W%|v zv;3lLyNcT5vnoSX$%L}8M6kh*T0G-@2UrCJD8^LpP?XazjiL?fG@k~;DkMKQgNpCp z-0j$JnTJ(dn&ZMi6$BCm1V|gXOMR$i_i{Hjfujh5D^q}-^F3x;A+_T1Wt6I}%}AYO zae!7Z{_e9k@&_Q`-5Q^+SFD?4>6G_*fApS&D>3)|{UP!SqJYn$B++fWF+(xt$O3LZ z-Bm#diQ(@$tVR9jVf1GRr)Z=_DD^v(r#d}tvwfuAari+dEl(U88$5%o zx`g&TE7ZwoJ!a{tl@k&Zr$;~N6)IvdE;&26=fxG)uH{;<%u9;l^Y*yu^fdyyss(Zv zUHEVP!q5cuDhSdtnSYOSxYn^gIl~>TW z3X>U>3<(Stz*ln@V8rtYzZ3WD58?|NEk0zMg+v;vb^E_3fpYdNY;BK@3**Nn?zZs{ zp3xk}A7|2_ZHo2Wa5_OgI5U$kp&5NSqJfbvv0^e9In5Sj4~&Q#<6Nxrv_T*qpZx+%4+X25JVx0M&*!b!SsTWG;$Hj16RV@%xFx}< zUTrukdT?+M#NPKKwlBE${CPYe!(rTauwJ8+4d@MjRWH|n1FDe(m{?m1?@Bp}#;v|k z6Hvoo$Z0&&P=UYVxIyPP>h@C4V2B;&ECj6)9-6)KrvCn6^!hrMx6lcu9$qkRc@!>Ng3r9ysd|7#((iH>?Dx(V}D|z}L#kz`mT08R?igu7Vd{TXbe$5f3UJwh> zBTiaLv5^OjV-M=ok65KI9;e;Di=90g6Es(9s1B0NJW=+xJ-K-D?-e;)3p{b2;50#% zf|9QxI~R?PQRG8zj3t`T>6WZ=C@lPnoObx|VOg?jlK`}E!dN)zO;b!m!|8+$v(~K(I$&>f zP-78hY~q^r{|mqNSJ7#Z%FaF#s;&wD4Fx&)zh5h|`XmlNdZcOx5;aGDiwxZ_` zXK{0IXA_VC37IMdteJP&A|)N9?n7CqJz>SVoMBJVIq7j~b{9JDrPw@d6%d4~m-6N8E9W>D#POcf zpZ^5H6jd49aG7Ld>*>qzy=2nG$nbg3zXXSyrAh~nf=Wnf#JEt1SE*1dugko(kQ}pZ-~~y8 z+q5zTRZK)sKxk-E)g;sJ8O}=^YdZ6_A#;jya!=^bnLNwQ%*;ffeZ(D$-`ZSKSwW$| zdWa$;Bcq|AQKg2m5v=`S>9fnogz>^J?#Usngdx=KP%K~pkoB}MnX$KZ6*$CKaVOeC z!U6;LoMpDfMy-LoO3H0yK5!UkwmVRtc|{m2Jx*tT!Ah(&n?;^EMd3+5>eS`kxEZye zpSL%y>4OoSWP&d&nirvB2BdnHqvhi@qato?Tia;>byQ6AP}VkPOWEtAh?9Thsojcs zW65ovsDEy$SwYkXmn9uObqffz@eg@w>wi=wwx=VvC z$fv5M1dMN8@Zi6=(msrSi}JRq1&Il1nE$b#^;MGi9r=1hMc3tUYCMK#p+pYxqkL0C z{^1V)4tIm(C0ZI9nxI%~q(De5tRt~6c@veIso?o#r#Z8B9LBlZi$F)gd8K?PoJ8@E z>f$GJvtTGO66^rB_dVbhzRNC07c40$smIZBdy`nB)GKtb_jgS}I>Eut-Vpx)1^T&r z?dbdy_Tm6y4=4&qlMC?NuB{nk&8v5+A0Y47l zR|K7!!LOcupFh0=O^Eb8vI7{?fwVX92#D!9HjEZN za&lzvLI36XcB3o|42eMzQBkCLn$eY)k$DA3Dpb@PB>%#Q8XMQI!whMfm(PPMfCLm<(p3FK37N5QZ16XHl_&jC;DL}m$;E{W=z zW4>h{a}ki`@1~=SAp6r^sSU0Ar+6m|;+$tu#o6MG3x(v*o zF*>#SSL0k-D!%aKY)V|iY52AwL;}GAbd#@Wg6Miun*Bxe6=X;#eQYD?ZeA%sDYxs@ zZL*i*IR<~w>?B#Hh2j>Tl$IXS*~f)OnymStV){PPac1m$mIHohuPY?wRv#4J{-tPe z^WMG9C6`nqYlR(W#=d?v)$_V08U?V3#*`0h1}ruLeTYLsaBT)fO)XGt0YBFnE^D9+ z+M>+q{RRmG2YKIq3GjzL;|TuPp)Tt{`@^^4q&NZ#%!nW%z_BHajYwjCetxa-yX*-W z6$1*|tAhB;utwXa8WZqm$k2r_?JzT@zf%y>hbEM3R7{Ql$Of(__1XNJu2+dU%|0vk zGThJj0NF!c4seT3o@Igt6?i?i=m+IfFr8{i-Q~CW;;T$b*!8Y`u!xbqM~o=0hno2V zyf7|^&;MOHbJsNO^bQtXM~$)ko!hr_6(bH^)vemJhm|$;OvX2rEeMTvb3c)F(sf^G zO-!PrAoHy_)?c_Mf0K?qdMG|7_p&Eg!+@4g*r?$=3Img(2@F&tN1iBg-~=6VZAN@1 z%9kTY!p@yOeT|r$irJnrz6FkS*iU^`RM}X5aLT|So-nJN0Vp|zmrrAagi#KBb3{aP zq4Z8L1bzs*AI-`Xpddi>pZH0W#gHb>s>^#JMWNx2HO*?nkf|G_sEo<_ni^A3wOaM; zuHbR^isoEt{f1usNC?^GjT5z2m>8)za<4c-$hj#B%LozyV+;@eDV0AJ`6!}ZXZI~N z4(NK|L!Ws}O|2QXxv);}%)jrVoksbkjTmzY-&d&@&ryg00FqB3s@arLDoR2c9_U~Up zcMqvA8Qe4_)Rcq z`1gt1{=fnN4062KkyMFEFO&=xqXRxTVw0Hp(VLDzuNn-zx7iVm(FrN3+cUZfD9v6J zg<7Gk!!JmLSDZPm(~9~7bX&IY>zA%9S%v!tG38`>ExIT`gdaaK*6fp(k|JW2UdyWm zBiWcb-OwpVsHq6FC#DU66&#`@9qnMHLm3suLq5Kv`_-S}yd8=J5Md|2y&FYk0zic= znrXc4atue>>rZz7drA4oRV!2Q!5=Vd)ep{FE~au7gA*h!4f)!dnnFUbx*zw+S`_+GiJQ_K#}QQ7BGr3d_o;zrQZOBD@%1-xCOO7UGM#kD%uATAi@%vfaY^@iJ0oMN z^Xn@5wfT*y^+5-^V_rdJTv(2qSjkSETcyElBeAiU{PY zIXFt=ja3TAc5Hx|GFl(Cn2!*~qn~4~n_LBok!nma;$~jmo_H}6x}*_5>2%-HU!)zi zxmD4+Ke#Bv^c7#wk4OwB25s9hO(s`#Nk?|3tlqH9x_^nw0&ky%!=^NOCm5{zczNr8 z6!YKP?~|{cj-g~|doyk}o;KM8*=&#t?S;_jQP{9~+HKwFQ_Rn%LR)oXY7C^Qgznk9 zzP`~yS3)9$$p#AGj`C(7@i%MZh|ic4^sA`roZ7}y5~|z&@!B&4>gFzkthPe?^EK-^mkfS`I}T$; zhWh?M!H5c>`Mw_}oT!5yRW%gcNLUr)SJ|?^y5L;D$>q=(HXny)EG<(>-e5u{2R+O_ zbFr`8Q(&VxQihIDZ6t&W)}rbIAPW7BzBx2v1Z?^j3r)}Wp7EjIUwvC8R82qedg$3c zlwa&ZIhZT#5VcNjX2eR3we49T^vTPyC~mW<63-1D6hHpzU;T(rP*_-UqT8N5ds+@D zSfGv92rRBOWCDwx&BZ^SRz^o))3#-UZKekRi54MxAUW!w z(!mkWP&Tp>*#VpzcmaHCT_Y6s16c-gq^r#wxR1uV;4l)n} zka!R17M`UmQ%agdKZKZwiliQP2l976qKYJ`0L*nHP3xuv_Rk1|>r;7bUUGx=*s0Mf zWYo}uqOuc+E83=G$Bw;i1!NBmEm?g+NTy>%?nk_cwOTZ5o!+p5WJtCI6p1qP77NZuGmRira5#9ETFHf99c~@^+a8J)U1k&M_<98g6cc_fT}= zKM@gtNEJHE6S4&!1ObEk<1a_nP6KJZqH7gZcXID=V1HMd<@2oElqoS@GUrPmvCrwbaZ6ox$injP1n(CAWNQt z^(6{u*HPachbf!sqm_OirT+hOl)fVxC;#MPx$%`h!~1mJw^2Zm2Y-6^Mez*>*aCMx zvq)TOmi26*RoX@kT@G&X9hW^gMF(0za4PKB+U;}&6_DN;X@i5_%~ z;h=-cXNsP6LU{p824JdgiS^~T-!iQnz@54Mi)moCcB3QeUW(+g1~FhUPg#UoM;)a? zj%apwah?(Lj?^j^5qJ2WywxSqAHVFxS1EKtBsRwed)c>^BJe|*;+mcIagXMO$0D9= zKKXrX1#1h+zu=sFh7S(vOVE*uVbd(nWY4ePyl=8c!)tPloFAj~_n9Y^jVjyZE=A5* zULFBgL{(J^xd2zM89&K#Be{B!AB1uB(lI`m#H++O@YAT**;+7h$iPy$c;69YJFdNZ z_Z~i+2m6<3=eMJ%T;Q@GhPT#S5QG$iz$5|vSwRNv+Iu?Ju8rZQ;@>9ekpUm<70f_w zL(Kw4>~}6%R-mPw$i&I2132tt*!Ru#=}W9P=$moBa7EolPv38|MWgiQ@|V;zo~X_3Q^4N^z(i~!Kw;<|%|F|Oog4X< z{qhA}>3UnBhf7IGfqEv=S$fcmtr6vU0}8hZh{uM`NP$!-FaHLP7`+N?QY#GXs(EtY zU~nvH8;hj#Jg)C{1_r~dwy(A~0B20GOUnQf>IDJiV12fJ*&P7f>o;v`6(^S&dgL{_ zKa+wHv@wO$YgM9Oe*DjqD=jO7GvI@Xk$Ws;^$_6$pl+(QdKXDGYrtXqh^k%l3|tWX ziyxg9wT(?D8?)hRx$QJq!|%cJni}MHJn1u}7{b?-p+II-Q)?FSVo`<`Abtr)@&J>V zoc}#0+088B%>C4w?#`2r5keETkHn~t$g6a>zJ-8?l5-ts+Kajm4utvd`-|$!@}>Rx z7pzo(?ZTAv-^}O;l1ihi?mYDT&Ok@^eQEK- zQl!LZpMVoUiF6tT!!fT|URU#7u)0~?d4l4o1nC9q$$adSNSYlDsbLC zbMk;AK*1J(rQoJcdN@Dpsg(s# z?gFgh$Kj5p`fPxCEopS2sDq1on#T5b$to9-EyzQ~{_}YCXdF!vJD)u}sF?2H?&hW# zagaku=s8NkLwkkrA;_jhTlKetJ=cnA4m1SEdd%UAW^rw(&q`(D&tYnG1M<1&wbKwC ziNdG#O2cuh->An1+U?u((B0xh|BO~gsf8i=G_-lM(ZMd750pbL-p{fz|tO`m> z2Nt7^qS$=e4OobnYxmYDXKo74sxi7)`@e)ngSOIcDg2K8%*=pnL3Uptb?U)l34$R&^~hv|Dgm8W+XtHsB4~RMVa4Do1UwLFX9R8O79FN87C$#eamY+pU>-Yjq^IM^LlHtqn78;!(#%qHG2wBs&fzMcENcSbQ*Gx;v^Bt(N4iV+EdYMhMjF^*?og)7GBSfdA#o30gOJ8W z`>-1h)9a9@~Kl^>mcc&qfDuquieoE&O)BGoU$vdMUVj?etu$kS?B zJ&X!`1cFEhi@&CXx|;MhVCYwum0%W}U?E`RmuA>gMJd~>r<_H57ou$!mEQeEV*Z7w z&7fge-zSy~!%n<;b7~L_K}4l<*=Z!InlQ-zBueK z$WflH;)h2kbvlxEpA0WBmjRu545vRuV@(zO7ciOUGWY!zYPi508ITnWR*UWnF_%^hi!n$-BmoIgJq2SP! z!??4)oG4(df!kxM5!yXa$o&Zn0B*&0*D-T*a}>zHHW)cMO#ob@e~jZOyl2nn_OY?0 zxb0|ULA0a=2L`wXJ%<#IY&ixo&{C_dtp%?CqM`yU#ca3+ywVn%I$`3oxzAX_DDDM@ zS)-$)sDv@$N-9b;=#l>lM)L36`3URG0QBH)02L{Q0utWoTV>P|gjn>Sjy*K1L|&b3 zR7B8cQ1gf+@PeRn4bEHr&k}pb*EKb5=!(OayMF%|78T`zmMu^noNm(9MdpKO4j+!i zc4xrdQOk89+kdd6Cl6l-AGra2L}-|zfT?-+j-HM#c#&LWXlRILCR`WE5Lj7V>(wMC zi>g*wIc|*GI>;jR9(^WIh4R&ita`;|#)zl4A|oTCqNXqviTHy@BP1?92Jj3308R&5 zi>E_k8cfHx-$nI3&oS@3sKh&8=nz*hUt>7R*jDP}gJs=-s?iZdv2!Cj`cz&s zJeZl88PX*!ya8?i@ZQ;>-i=8)J3G6D zW$>pB4O?vUTAL8EaldgN-ss$uPg|bnctw8Z`{1c7Xu|GoerzYK!mcuMjEoEKZ5)1$9-~ZxbU2vuU{(?d|x?zFU_}^dcSj-9j`zw~03()g_e-(U!w3`0= z<69|0=t%$lDeGLI7XSBGre_wYIsg6D1IhoNeJ$3njs-JDD1ZLvr#F!KKg**R{^|d2 z^$(D!FvfdvE*lliWD)kaP##19cJvPjXcrzKrC8|zHN`h+(awDd<}aXgyY$rZqi+H8 z-5))R0SNMc!=H6K(yU%zAuP6O^<(I|SF|%bU0uTLDS}gno&@VmHaZn=+sAM?eAm+m z3QA*PJ$ojXWU?Xh z+a~JrO&8W(Izn~)o70}q` zCt!pbElvvMe!xPyPX3H(GPGvFc}B>pCN@#V_P;M2gnsqw zsw%$8-EV?nmu02^M!|{XopeW`dG_qt&}=-%v({PpiO?vEq9jaF|0#xAF(UT;WlXq+X^$ z4}7@mvFL6htX#aHb=h*p&Av^!`J0RC2Gtwa-~OP9PKWmF3dLG<{M zW^Lu+;l!o|uyBEZB0)o5iCjZfRrNkH0c2rzrL!)NTLWs|yxEImg);2=jT;aFafC`Z zdS1wka#1VbGt;5`;^{d1K>FK{ptA+e4Zfi?pA1MDCFXb&k3Ky*QSj?XtS8icv-x40o{xYS|AL-aF| z0~V=yKz(~vR!AE-@Z{4$|HZ3@T8kt^MIZP6I(gUq8{9%;;);T2ZC@Pl0fS_lN6j4! z$1NtYU=8EcN=X$1mBuU4uO`6<`5HKSI5pv3qGAxNUmrvCXb-lki%AQFl)xn2}h=q6<92~5@{yAWO7&N*btw`{_PAz?Bh{0gw+b}^LlXsv; zVj$rcQe(wML+HLPYN#f8QCO7}D|603V;v+n$XMFlJztBufr#8=h%!&y9jm%Mt4*>V zynFi=Yd{Wyu2_64l97>76f@DdSOoL8{FZlpU%z>S1JI88>0YuL4m_tvZ#--^?VS%$ z0i@$0fq@#Iz5`i7X0MJ+z}shJ6?uHs4&yd=-4qXE6o5!*Ow}L7%+uPnBOgy(%`_~~ zy4se_O&6j%vA%8phxkB<>(8H28(20_9+I@3o)`b z+i5u45tW@?=~l^0AY*s}&U~t;+O{O(P>qB5bB1SES98kTA5|i|A~-B8zV3fztFO=^ z6aEM&CccfVn&<7LO?n?=QOglZmig=x9D;cW4!*6a8PD3LxSF17b{v;r|M6*DTn7MQ zy?qgn^Ktu#{@DCaI1F+7ww9t@S1(@{G4;6dNzNeXu^wFv&9W<)l0^@tao{JaeN2SM zVx=O8r0U{gUtV2|jj!qqS|`OMa=a{mG)C9};Dl4i50vvq#+FmcMiztKes+xbk$z)$ zzj;_{YAU>y$-5&%ldIs{@OXZgeExtPR7hAFeh2lb2&eFIbAP=Qiq=sb+EQw4JvhdV zUGGHRsWTZe{C)=PUd*1~WbR_8L<)LUZRicE%~fL__Ve#a7asK(2B!EyTj%l$w&=Ip zZV4A!ykR+`9UhY%cNrfQ{00sGhI=iYE2pj9#Ey^R$&K3yzFGw*hi-O?c0Hs%u*)a< zsoo7-Zo_7I;t*5(j5^!%b@40YY{2xSZ5_m`*T2__DKY3! z6=pC$c@o0{`!ib6<1RoO@zk*c^;dArJal4?A6QerEF|B{Ge)?7k>a0JUE+NON#Xvk z*`SwqXZ~^S2toj|k5~vJ4(UhOAkKk5o?S8?b;&);AU7Sk2f^Z>f2kEd z=5rg8Y6K{}uYd2L9a`NDGlJrK>)a4fK-K*Oy=U>)wn$omhCsmM1Gj|eDF7zuq*1d2 ziPF95I1hm@SsO6Gz#$mh{^2Xg%O!At$E5t#lMnzZD&*C!_)2`l^bSZVVljDVkkcV} zlT!@j_&wj@_L7k*elh{Y>(&z|1pa(XY;1P80U|Tdk^#-ETZv2gqGP^PF+8(;+}+&` zBu~%o2J!=J(LVnKd~$em(lHnaD=<7>3ak_VgvKUMRL^&(J;e2577sY{pI^1C9>q?_d~5t%mpXk@dHKiWZ;uKCtE#Rfy}<@1g8)u~SVuww(Hl;#<6UY|8YI zi=G1rpIazzY>r8=sFp*Fx9~9pGK`f$uK`IIgilM-EWf%ToXMbe^9z2^Hi_b<9Zc>_ z#}hnk_6VUQk2;7Y*Y9xD`^DO8bl}u0?e~#>Xa&Eidrz>?Q-;KJ{k{q_L%|P3TFQ1P z(Uq9uZiqw(a4}&c!E^d+HaQ-wn4$PAb7#fJ##pNIkA-lA& zX+G{p^P2;BPB!3^m#VzqkH+{63ZJw_16VFjqRYI`{A5oo7`z2XgQnsTXuxVPu1vdk zUaN5brHOIc!>`Y=&%mwT!GwcH7rOJv<@#}Gj84C#5@i&8K9dt2bc^e_p=OHu#^gTM5~4{6z{$G1s-7@hRKMD=dgx; z6*!Nr5Gw`P=7E&!=-c|;==Fw+OGR{3Y+QzNfDnFI1O}7AiIy#}(exSaG6&u} zv74TjJkti!jk-z9i#-I}e6CzkKXgdD#gE2vo8hHNYYAo%*=PBwIIYMycL+NTcPg~5 zW~We$;!O#}=Ie+hof>DDZ_ap(e=k6UZ;bZB6p&7f)nP6)htV}i*YmZ0Yx&qZk4>B7 zgR5;9cVRmcQ#4vLJU%sDKpuo_dfVXV-}wMtq3>9}Bt5b^Xh?mmx9)j+yGbj@SoIeN zq6LWjD^zi?=j&JSh04D;5N~Hq(Q#>s*we>W} zoz47Gl?Xl%)kWIfRCw>>M^bh09UJ|yV6A^yi;-KJ+KI+P7%k1WJOC&%vsSM*!EyynwS0G^|bgKQ&oy(m;R@@rins|CGOH2oUZ743y!A|WJe zm;)roRmYO@W!J7KO*buc!QbOW4k{NV@@GY^ZUJIGVS0}K?Gb`DzxS&{-Fslgs>%fr= zXW;l4>%)*^_1>#c2f=|wg9^{v?5Q>trl^vd&Y8`n3xm10eUT}U=rZI9l8$u1+7ZB zRn-_t&6DQJUP@Q`e zbM|)}8bh>fNYwAq3B7)fd1S6$e(-~52JYHpnLHQepuDUOS#=#eKM4R-^HgdlbIQ!@ z>>aN=%x9aE;=jMmM8Xd3K_%qS6DDD3@L@Pe?vMngUcS2&Jz}*%ugU+)69gbUP)Pdu zKXJjpIFP+6cWNRLak`A}I$zW4uAUyfUYhGd{QPg4kB#V!`Wv%#ijh=A`+`XC#j4}g zPL02qo^7Gp$9@Y`GQVZ5yVtB8%>}FQ_C9U*TC@^rXP2`H4pt6G9NWR-<1-HfeHD8H zV5Sf9B+#(^uS^20@qd!s(|5kn<_^R@-Mpi3+~`sn(*i(&^h3b=GIo}Iow>9Lp0!r5 zXusk?>jR$W#LFdQf9a!KjTds3m#+YpLHpLBsP!pq7uS9H*st+%!O`iC3oFG$zwC5M z-y52|d6~+(;Q>*Mr=2|ZMhH*m=N&=toW=yfEtmM?iZ-1LyF>(S)AsQiV{j0luK%uS zu9O#^a0z8)`_EheVfIZ;jZ3;dJ_^#>!|$zFf|GEF)x|S-PtG?D4Gxx=mj9Ka5_g4j z-;b`YEp{%rikd4efjq-FD}K9hhEw9y1|`o0Ct)`Xs1{-E-Vh~^v5h3+qbZkc#~%*zkRGct)4m zWA^zx^^2_B&uiOjpY6A7Y+S9@9F1UUZ%aE z%e)9Cc$l9^50O34i1*8%#XUc8X1d?8-+p$hO1Q?8`*rY5l>#8fHGkR_>b4d+Ex(mU ztAXN&-MYe4;4g0PeP)+O&%Wz^?Tb4Ge6NpE-vb7)CWis~z;0eu0f9qJFDoii-v^r+ z7_zCC6fAO7czd@B3aWcf>&r%jytQQ1TRS~H&56l`a;uH2(YIGe9#oP20@54d;#n+3 ztsHD@eCxiT!P?jl*(^K1E07R6)~i8%*frg>VIechSd+pK1-S#}kR!u>{*%^XYaGXU z1eYvX0@9`4lj4%+x2*TUKx8ifD06(0{8g4{Y#I|0k+I^EjE9 zxKB9oyQYytXa&*)OKHS#86pJet#;jC(Aqn5YF1R^{rCSqeP;pNBzz zG}EsR+ykxjU;xJ%@9_+_DV8rZCsRrw70|hF3*WIW?!zuFE{G5ngY7(}pU@Htj&_{= z&;wr$GN_**=J=TAt&bXw%r}{!-)=#z>yCVh$EpSRXj+oRN{_Xn&e0m*r0MPLhv3w= z|ERRfV=WXr1f;%O!s@=C<}e!%OT_qcbm0r*=$PMVG5-fG~&gy_I5)uT#^b`DR=~C%A8gX3ZaB#ci(Dtw~)1RWX*&enHgt z6k{}YBTg>6BWI=ZfH@Z@Ehu)4$M$uo+fIQ3!9P#CCD{ufM!ghSGojl%1;{w zIG~KdJ9oPty>D9E3WtS+zhyVGh~YEI7A@gINVt~!B4J;^0BmBB2VRD%iSxrb3^xaG zk?p|+ZT_lwJd0@zZI1gd%QOv`S@r085$LNU17j_W%JyATKS!o2&@2eTY^MHC-fcHx zW7~mlZjt2Lw5hyOu;o5-IWQ70`|&KJqJm15W=$9Z@R9K+-vgoA~pYt z1V|jYHbeSfc=KYkkvs|L)6WY2&1mw?ISvFzIo68~RlrGb**wgvXlbL6H1chfp8R^l zZ)4aFmN(eg0e(YPEgtF zJi!8W05hS&txpdMc}GWB1Kjnq!Xq#mdX^92UUmkC4i&m18M>aFQ*iDh$EI-saG8k- zXcz*Ozr=XqM#s=lDP)|=moRQq1>T$Gns`)MSsCA&dif5c!iF*9r$7&68$R9HYIMAU zCZh6IUlmiret;3zX@Q)7ytAdQ0cBxC1V!dmptaE4I>)4Sv$Ck_Smi@?>$?yz&0nvr zOnUEVc?5)5LqN;nx%Ll_qCFxI2!6~f`>H@*fq*PjY!|%2!aY+yg(j%sjFCLJUPN@1 zxdao9fS;)jOAJ?Ed?UQ?L(1lD>g!kmc+n-GOmq03TfPa^1iBN<8y*1jx;;I7xe?+{ zhQVD-!#A_hq!2L3Nj30V#VKR>Kw96%Cf!t;#|ZbV4_n|(J~X={38tQQ! z(k^^?MK>u8g(;2QWBnaBQMnwAxZ;$GP6_TQ9~&!cPs2{l$wkmnhtB|PAySsVe;N;K z6F{qa%%vj2ABFa{PwEgN0V^gc0Vot3Mgq=mxdA;oY1yPSH?$-;sCd2zX zpa9RxlueWfQEO!72*t|s=qyvyOJ2NuN`N~#_r;%8r*He=u+0i!-0f;%;bu?c8zS#$enu6jA9VHCfd~u zJ7%`MLzHkyBq&B|hAhV8@I_kq^1 zRs@tC%>59+);_QnZsV@bE4#dmk6}&AR<7%)s)z6+j|`WXSVLud29uC6Vww`M4W7pv zFC;s~JBKx zBfo#M4)qs7NL=qT9%G@-t9S1R?=4I02h$ey)EzHWVZGFAS&v~5u)vo4^CYH8s1KRH zK3S2Iw}MU)_hRsSDiz?WOtVvW-zO;04Zrk=N4ZnEd?o6_u|0g{j{-YqvpLOc!&&Ny zt=57fNL`0z@2R;Jk0K*KU^jbW0ziaow6~otpIO|B<+^JZBzK@#(4AD7$J3^pjvFUZi>_*PoHI5V0)W>3_`;6@qLI8rOF0 zmtClwrAF3^4E|cNnjcz5*TW71gVJ~?e%O657aM8fYY$%o;jQ4Kf2G+Prb5j8DyY-F zP_q_UjCzCPfd1)LGt67Q( zpv5nhg}s0v$bxf6WH3zQ!1@^dSA}2}=Oiy)Kp!mf*d=~nA%zdE&aj|NnmJ$olw{-{ zoc(q#HhzSf}cCpG&dh}m~Jt9h+es({+rG_A9Q%*M6yT*`Y|f*o1$gwiy&rx zsygUX*7S+Iu1!{Bmleb31*>ET9Nwn-* zOQEa`_;bSqAQjHg*g38RhggvpNxQY}T_MWGEHObC$x>N#-jmqIGJ=qLL2@bmV_XM) z{(|K>Z{D#(H6qi9Q!8DEw|oSZ^KMA}X_RQ+!Ft_DE}Tsri?`kw;rC1BqcdEuhnZ;H z>L*8W5F+ZIk+C*rG}w>FPdD@ZfvNl2BzQUwzWE;&_B&YP0jK5$Byad9 z`AWo8ry*aWok(a3>`^JgCFIulkMM{Hi@415)M!uicx>rR-{@Rw+zrv5tv$lp$vJH# zs$+C*bKp||hy8Yu$8!w;X$Ub3IEb4(u0aO%OWT6atm&erCc0u==@TiJFd0X?Sm$vC zFKU+Sh~Z+36NAhMddzOiU?7>KnjrAwIPIwbcc zkZkj^t3fX`WcsD&z;f4mvzs;F>7o8YR7ivUoO+f@P)EO1(-&Za|G7PH&@7;4-;|5C z!aZ-$aFQkpPzP#kd=Jx6lW6e->`7ghn8-a?=o033LY$f^&lGU$L;>QfhQ;HWzlgF3 zgZS@lX6XK~$P@7K^o7p%p-7tRKP`JJ9}(?Bzc&2RN7RH+Yk>5*&RCs{vcv9J%*7UY zTVQ=0Ej@i?(2L4S-2ci?yI_FZ14)1P(=uk!&WlxM)lL?)o5+I^UcxBUV7_8*ZZ7@1 zl6^&vYYHL<)@+yFh1v|&q1FtApG!Bn?mVS3&<~XP)fb1;t%bS{zU+c7B8()<=1iy} zS@yln7|)Z{fhaUw&XvUz^eE8hW-IhrLZ_T9BJRPo=n{ZrYqUJt05`o>eyrH46Df0+ z-G!_jsm~8KTt(QkX>f!QZ~@rY51ndUdgeCaAII1_K(SqG6NE6%s6-nh^f%bnRyIBZ zWq5O7`XlKqrg9rGoJ_zVpPdB)5O1K`MYa6CamnXTyQl}QKf#D}@y^h~5XnECBxRDq z$%`9wHQgcn2bH~ws^@;cs;V+T@r%e*i>C=^5a#k4>l=<1e08@+=^z{IG07YYR# z`NqP?9SX(Qs*z%d4Yo2D@-cOA_bWjQT2UZao9Gw7sVoOwz)wu(Oy@=IL#~9xgBB&< z9!MSG7WBM0DHwG`ZabH;Rt9{~XXn{$pV>ov=6TIv&E*alB%>v^BB7=ULN4xSfuU&C zf#0*cF)H}q%P;Vne!`XB_sNOAd~Kz=h}q|i8oNAfdAqyE*#?QdsAcs!bR1B~!HG9v zvc25w^^46Po%IA@B?hjW0`#>F^xBO>Pr(B|?bj^v)VP8X64_CVz&bZ8C*E>Hh@W84 zO(vCqGmXs4G3}4E6yMbcvwERYO`*`Q6$(r;+NzIRhRT1arQlvi0TLAkd0cv-`V8wY zOhc)ib5#HnNJ{$R{8faX&zWUC0|TdW4U(Sx+%-EOh46&=Vr2zPl@Wo0*Qad|nEbFK z#p@3H?Y{i8%m;Tvc9ARa2!xv+90>|e6wH%C*PA0-z#Cg{(dmDLYV@yrs0raad>{d9 z{siM}%hIl4moqw55i2!$|H+HA0Dw|y8ogZ_p_w81F3>vr*7GmQhYufCSAUAq15pFd z7!B0<4Kkib4KvMF3pUlii8o4@th~=_>*p#U4WVkk?%j8i%(O=?^FPlyR$(ObKL;lZ zMwa$h6Ds|dmX^&5sR2tUaTL$}q>p$FQBski(MkF`IB2MR_}w~@15s&aM($^ruWU)v zUD|pd+Xe1&Jez-cuz?;4(IDH^kdSZ#=ON_ZpJ7KZ97cJv+;5Wl9{g%JZ3L_XMEsi2 zYA30utGW+VaN5Ez85+gk0cP*(OS$Sa8wYzi$Q)v@<0k4PqIF=Y4XubU+Ewd!R=jO| z_;1JwWWCgI%(mn&8|D&ZG~I8it3xhdoWBG=1UF8rP=?V0JM+uYoj-pbRc>Suvb&!cNpXZg zUr!D4lcWS7MfI=yk8mVf*FAoWm6M&h9Jx24gxa_1=nj@csGO9*sG45g0da92^?L3{nYtKl3QkP*=K{ zXDA4;1ixf$bfL$kE1YaM{vz8c&^PwrWZ{DMFc3yXamY{@ZJWU-Vdx+4xH^?d9z11d z<;$0J2~l&-M}z$|;aM|JrBq~JzB_N8mXW@b#LkkoTc*14_wVmeD{8s`%yvZrXaq$u zid2mWz{KGUYeHX#IE{Tv?vc1QI_h+ozTE8LQH;JAdyVO)S%Gkg+0qyn#6W&#M2c*5 zJ+7A*l>O%tXV&oE5N<$RO8LYRIAbcKN=5Nv$avBQ>n7>1-~T*RP> z9gjMx=C7|C{1(h|tZ%G&Y*T5>ajl$QPII^SQny3JbGU?@rlrEm7wl?#Sch>S2g?Qb zYl?Zz(?Ed(F^Z=@Gm2DdMFQ+VQ<&RIWv0Aee=3c4czhhB*L z$11(;oH3jKZhUXQ*Hb^J?%}=hYv~~}`wN^$;}i?)x^*AHZGa}B5m=G9DDa0_8%7V< zSBJg#^_{q(N6)`mRP?;I^19mw7E?@pc9+;Z; zo(%;R1IMVSsja0cXAx2_P9)XlK$w|9t;pr3BC`>Q2)vpJgwa43LZl8bo5?6;^nlX~ zU>cdG(|fr*x6ggmKBGq4;;H@&;BD7}$TmDQcKuR((DK&WboGAmsoHe_Fn14gNh={0xyop97YK`5SH~Wof91xXNS!yLSD-j<3G8>F z2d!G_Pp;(uYh(oIG;@Op+PgtR(nWG-k_?~=o+KA^YTH+GVz|;XO0)Xc^Jwl9E2+kS zYoZ*O#%#{%)qwMJt(uyf&w+-Z<-ZZ5W2I+%)Isq$Uk8d6P^d$>=smCD;C^}rg{|7K z{9PO+DCpfq52&mcaI?_%btT9RLG+|uIXN{2q{uL0&7R6XJP=r*tviH#T6e9L7Pb1^ zo(IG*C0zmI$JkDSZAUloz%fc91ETa_bT>piRF?X$^(pN8(!=n_1c$Hwxb+TRK%umh zmkN(Bj-QBHrzSV+nxMS>#7IrY2#zlQ#w&*C@-oWn|2(`+J;B?mFt8GHpowxors}gy zs1b$5Yzjz0*b8byq8z|8CaH&LO;^37dOI;WNs|Djo%vwy0?138NR-2&yJ-;l0Tn8A zdih4d{C4kei(m5xsnY^AgE!F9+&tfw+rzRp=iOQK2+*Xi+WiRjh&~yZRAe9+u8$0d zBF_6?yr^MxT;`Ixb-pa795?hAxc^F?o~I!Q4gtn-cm6(d!z~fKtH6H$QwbbG_k%0F z)uj<}_Dol2si{qge?6da>N=p2r#=^113ErXbnZ0r6F;>IOwA=|mR4E)c41{^){U2= zPD?edpM)UoA^$xt-?!%q@=9gY>TfBMMF{C<`dc#pnq%Cp{-F;7S#$(LO?Mp(gWyJ969MwyWh<%pR50p*Rs$A zAS59Cga^$L_({ea4<0OA=5^^B@p3p!jq786{hPw#C||@~mHT|@1VE~zJJ26kqq=hB zKG;9tH58_g`?9YSOImWfg8Cjf5+v2I+~z<_vqc-ojn1p~_V(szvvu%?FHUk3m!gl1 zauY$kaee$gO+J8RsWmIvA6FgEYo}MG^Fa%qqF4aWO z=5a-^8@RYSXWsZ@nJmL;Dv?V^3xpF|?g?N(wC_jFD^A zfs5bmqoKjN6RmtyBhHG;R>>w)>-z|rDrOII2TA1r% z6ulA`WmvGT67n!Y%;{*XWT|jqCvDSjHfnxesNU@n75!DNgeR2;h%~JWXC&j>tGHdm zDmSPFw@<&~Ltla`7CF^y?G`B6V9_Z5&khI=A=aermgM>O@;Z@)_Vn;DM-;kn$SSH% zqh3TUla|_OLx6~&R(R^el}&NtTav}NV%<&zVIao6_{E*YCkB$p7TgCA5^@Rg6Mb+vt5&SI7LGV*O>f;z?G>mZtIRMkyr0$fwI%SOp=mxeF|5hU4qwnuAy-Qu&s7Jy5< zL{xRtYGJCJ9$`l!};a*eh8PmTnJxt z&m$W85v(meh=Uhm6am*#)j{nsC1C4ul)*OQTa)B3ul0+nL$KHUSxS#FmhcIS^Dl{L zpl%{ztm{6<%a1NTeE3A60K z=cmDp*4iorZYyc1`#7lY1f)a&HaQhg$EY-i4b-l#-jZCB-;s@0MgMBudwLW$5g3Fz z5QAW@sSYPiW+byWXpwC!TfV%jZen;PgXjaH?f>9;6AwlSj!&ZvGb z=;PxfD<&vd(-+446_|PH%t$bw+GSXLwN0*y0ycTw_{~Y0)P-T%n7~41PGG>j-*&PBg%3Tzap4(PDE@0V|an%Thl;6X00okL1I#g6j^RFOn7}neQz* zXo}D#%;>@-mi+0B=ptEO;H>ty9XEguUvP5@Ds?g^j|F6WHjh8)2+bojHvyBTT296h z`p2z2fGPsA&~xpM$5{uTRapW1Uba2nc&0qnVEPr-B&t7ne<>)4MPLdD>LCS^qzBAx zDa9-*eXP5Q0fXOp=;LpK2?nf9@DiytC6t^wmN>0%an&FE&LwPR}9A^J{g z%VXY*M!wYbP(=$E@V~n&+7@gI!CjkUO*dBHbafAQ6j;@5PCHRCz$&*7ca3lE!8zdh zjf2Agf=Wx*p7i!OCcJH5Io<=O9ThY<{+Y_-EEi!j~_}V`Z)3&>E`KgF^TG0GhU0}Oz$|q0a$Y+TE z&?F#4YfC=z+@>DWTjO5mHFbF1tmqMyX!gnb{-|UoCnpaofR;Xn$5GUFNKWnE3*ZuR`Mr&w4?t!LFX&OBs~LfBg@mDw6GmtJ9vQi2T}!C2;p~#ao?!Jw@e$o7L!ORU@*9@QV*KJyY-- z89?%p|M%U)7Cc>sS#Y3r(n2N?<#<$Yb$INh?cH~L^c}cRc3&T}Ku3hiq6+MN41^RT z$>%ph?-jWp&1!~s!?$kt2F(c_SgY6p7wX5kNt+}r>lPE17>KbAtzbF*;OGt{Bx`2M zvoydkLonBx8T~61IfT?VK#xgDNd+I@AefOg6_On&A6y;=E8RYGI3X{uH{&;w4zS?5 zK$aq_cIxYy^R7ilLu7@&JhK->WiVZ8$QBb>Cx|kmtKpDdJ`M3yG8BQV=X+mJ32Jw( zcxr43`FcCS^vu_@)_n?L)Smi3F z@(r7I4fz@npJB|b>&PloG4?RIKQ{RSEVOjA&b8vPhLL&SnCeeE`?wr{u1xZXm;^-L z+I6mse9_Ef60GcNgk_)g#-7*u-23X}RX5;OfBp4WVggD%#H6!H9&>1F5}nnggtoRe z|EC9cik{(NG`z$e5{@OVvN@Hq=ZLE!pP7Z`cOH> zG4kv8Z)k?4=eGkwN=Z!I{-YDQmJb9Qsg|!?zw;|P8agd9A?McOzVZcT=|BDkmSfG6 zzB35=r@)&=a>^|A!SZp*L}xJ6Si<&jVLc}LkTtuGfeJIcgkV1oCc=C77Gal_U!4sP zA746Vh!-p{@yOgd4ACRq$k`BSqv~$GT{~XRA5&0tt0zDm1F0%G-)W1qbP1}5&aF#< z_V)sTm7G%DMvER1V*mKT+r zf8T}~4MX0xq(iKg5xrnRIYZt>DvCcM4!@-pSJTlkZum(Ca!~4G`p)ldsnd4sd4)C-2=D6BND7WY;Y=Uh z)Q(#~K~!`v(1fD^E$;e=N)a(!2q{GATaaCvuqfbD-p*V%clXOf-K^xh7_3yJvn&w{ z2XXB%BqOMoV-znJH%aTwNm`<(VS-8(hnMbln5#hv_{k2e!`dYIprYHk_Oo~UJW~c zP&R9(uSxUYC%|$Dc}VAQ4=a?ZdP{p{(d^(G|FJCHgw4+TEMvRB@Y5rjQHTUHXy%C ze9;1onR)Mfv(4PM9+H%&vb_Cdc+R_;8bQqj`FNob^tzD*)7c6L3fh6_g=UqYQ_Li4 z1C_Z4VC(eBB6&+J?8WKfGXmdM#aR;_(38hRRaEwd%nUXjPqp{kM&z}6nfSMFx58Yf zHQQfm`NQI{3W5hAAi;yOd7+{nD%a1=JG=rY>b;l6v+O^m3-pz9R3BtxsIyQqR zr(xdxm}5fDQ{02S^+=qcNq+`OJgS_vQm$~0WUq~mPAeH3*kr8qbrZ>(@?101ysg(2 znl^lKxQ~(e8h+DU1K=)X#20L$l$4a_!SRJFhoJT^KJ~fX+*(mkYT9r- zCdUMW6EQCiMevP*qK2C(g;QdG4etiwV;BK^JrVnfzYuce3Q;DZUJmZLM0S&Kb~nnz z-CYvBqh${Gkgmj>_|g)#-sreV0-)ApY+Sca5|mz|MqWe(4sg28|E@NEzNNsi&ts>4QMqoEW)x3jqGa(NHKQ-Dgk6a;_ zJ$`}vqXOL#5M7g2Ym}IdqFf8xSB%4-(OlG|Qz{l>EDZd_vL+_2LtJzG+qc0%FO;^< zCX9KL5Q#LO6U7ify4{C#){s3RyBCj`gn#X4?ZeVr#V1gIq%{V!FmAevsfU%<$06GQ zVj8W76RCAUB1iXxd!82+<8@K*3+nVCM}_-^l~vfMnlsKnrHOivoRO(`juy;1-s!%3 znhS#z?&f@E;TO+X%}>pMl%+L@1n=|M_!5e+^wt}sVMci+YW|AIoLe`z;RJxb6EUl% zZ3?lbs<|@0xoNla027LU!#B>;2)7(uNl(vun(8zYdY)jz2{|2huSEXM3PQKp7Ib2J zp$5v=^;!tqrJy7|GCYjchHTDZCKymP=lBHH7iMeJmfzcR){w2A4ag5h?_<1f`bkJ2 zZ^g*B6ey=PGMYSJP5M5U@T9(41c4eIv{z)3%?Era&;)ZmMCyx5Hob2{7Xq10R1GbL zUWX9~SjImoKG^bpGS_B-A$$bAtGLhJ!(rZ#37i;@#+J*C*ydjK_qDSc@ zXEj7s+-TEScu(oZ7xjdh%Acb+g^qwTZ$2(4)Vtn1 z0v`$*I_dj(WJD;5{YBTFKm38`YMaCwk*cI!tG0b>v2)=r&0#fXbCGMd;)NMBiXn+{ z{r8s58I7MYG~QSwtc}3AN$WELCp}t1q#$p1@7Xw52uXgl*UwlydtF_zs@iG&bzyg^ zQkMyoW`hf}#~O zqJEbGV&vOpoC;;?qS_Nxm>eu0SK4b%#moONCP-q(PT zeiRKA9_P0CyHaUllG6s~MeCGZCbkP!aw^~Y-rB}s9jhmlb-HpducoFZFlBats37;u zF2@Rocr#Xa)tkaoCj-NG366Yv41f*7vcUvL4}Jj@hkzCNGWSd^6U1*AUE(He8&qpY zOjA)Q^s9TrmiQL|mDD)oq-YTUe{(HKgKj7UXw{069{kAAy!Qh5GT{T;Jr*h%C2Gtp zbc0;`PTZ*=)Mtpr_CM)cgFktS8DxZQLwg&@6d||W4r1qknsh3t@xZO%q$2q;AqF`)|rm)>ZKgkTPND_H@A`RjDCSJm>TwiT`9 z9KNUzK_eaI;C2kVn5rn2L=r!>-<|_Qju_%W>vs=`fckXsiG_%okfNRJ2ojG1^LQQ> z45_yJD#!JSGAwdYu$GF|GQMyu+jAKRLn}NGzMO9R`_@_5&^g>ggeckJs#Pc=cVihB z5`fIQj4wSszfsPks?P<06U5$!JmmE0@6eO@T^o8U8=rtv?{Qszl> z&*ze|^@Yu`V{!0)0NQ&{>mvdiS*PI3lOT#z3{Z1o)5j5E(Yo+S!RJc5j}!U+jxHF1 z)~Oyy#Ra%w0Q~S(LWJ>6LkW&z#tZwgFwA@HtS6Lgk+m3mPg+#^uSo}q8s%9ZAq0%} zYNp)%h=Yt2AMimkZZ=!!s-5e*xv>}8BuJkuKzw{t<8wRh~2w=@~#41!tw$MCy~`3*p2F(uO%nDB0!BoWwRe#H!ywB3zRk z+3uR5y^a|cn{eKXis1YarQfeUa9BwCR3dKhSys88n@#b8-YAYYSr`j~tkIXzex&x7U3Q@NE%EY{g1$^tA_UE`)C#5k=gSrvg-Q##G zY!x!cj=R410CtFY2e9&12N#av+n1A7-Pg-#(O~qNI_(jWP=$iShqqk-ALACm$G8Z1 z6ih0ZC@0L#eD_7hw#FOeb#7`!w&>pyx7}+^#O)A$r?!_DsW*rQ8C0g z7w8}8YG8;7^9_8M5{5t*ECqR$SASXxTtR5Q$L+o|Yg>mvX2K^mm-@_OZUdi(^L4&627e+Mw@16f7ab$)p(5@pPs?1riuMy%1|aDYe0wPW(e z*Vh-P3bip7M?D1b0ba%vUmIhEQqsn$Wgrq@eq*dIMh^1*QfRkOUjoN~Xi*foOI=F- zMT9$0yb(2XyfabiMVkPO!hq*%7#JAVtkJ}M1WO)<*@!QSSWf%xG%_{=DCgjmLW~0R zEq#14G_oNO1T7#$q9=&?kAj--JePL5``(uyrjD^LSNIk@@E9cW=wJZmL|KP=7l8+d z4vstv=>;T_aS%8*Z1^5_x#`|+(eq|k<(`GC6X}FYdp)0D3aO=NiO>n5zrb@{v;YdF zHW!&LbpCV7G%%dy=~>*CUV+~EdvMP1uHSr$5nqvQInKM0vmDS;$F}IUjlR>j%Wy}0Z!(L33SWgLHpa_fhiQ~qu6M0 zzA*vcp9t@fw-y#$3~5l@fHbFe)tP&GQN*=hHhnJs%95l|BsEUDP`4UI2X{}%vGYQ z4LSuT9)EBG1E*k1(9a6S!(V-*u%Q_}9}Ke29>623J^DwbcYg}mmzP$Hk(w_geNr7l zM*6+I)MxJHi4!MaAANJfcpnN&umuWdY8e^Se(4HJC>p+h>)4KNM^?LI$Ne%5SnF&h z6+U+P1knWmH|PG5jOYL=if|qhAE6b`}eU(~Z z$-nf1(E|eht0@39cIW+tc0c;#d!dYg9lO;)VL5>^V?36CUeij{s5Ane*Wp>Pmd;}2oTB$(;sshNibF9a+{q8)pJ3p%sSz(x$shotM-FuR!HZesDkE1dfhdg##g9K z4jedu2~rNv2cWwmJ&8`iCsHW&(AFSy8f9g-pRx!TKwBX{9*csnH?ym?AA9(kNdhiyc9Fd5;2Wvlo zgDhrJT1E=DdMq*mgzC{-j-&@2pqJ$G$~^yhgKUHk4ov%@Ou5Ukg3_V+wYxhPB+CE} zL$K-KWTbZzgSth;)<=Yd3ZbH7Zy$7wLeW?rn}&bDj|bC+4KslED_*|*0J-q`6H6#k zg%EK=pqQ$?fI4>cl_~zr)C}D`aFgk!B@rc2khq&m;f=3HKL7G_l-L`7I0V4;XvOJ3 zw1H+^XJ;qIO-hQ3vG3<0+QQh|E&-ttlnsd0DA7hnm5DbcKfVVSd)ABpZ{fd99Zw%5 zKJGt1rjCoH+JAm^Ys23b_RlZ3Dg8Mq|NO@HwdS9b{m-xd@2wVY#sA$aavT2782&$u zp<_Ph)bgF=k1ot)4h=IaE&M$ci2hZ3rcloQE2K>+i}}xi6Xy97naQjE_a#fR&o1|x Td4Jc5{L?`Nb@?ngQ@{TQ|Dpii literal 0 HcmV?d00001 diff --git a/_freeze/11-foundations-randomization/figure-html/fig-sex-rand-dot-plot-1.png b/_freeze/11-foundations-randomization/figure-html/fig-sex-rand-dot-plot-1.png new file mode 100644 index 0000000000000000000000000000000000000000..71d3e1cf785a2ee910a1d8d33131976cb74d5d8a GIT binary patch literal 196468 zcmeFacT|&E*FGG}h>jEsB2q1=%!t$o2qCBlh*C#UP^uI`2}OEmMum|&!bmRyBPc2$ zD7|S=)Cd711`H628X!P`00Bbz?K>3bdH#BTYklwf*7`p4tY=hA?)%*5?6dcEUHdxm zwxPZ@&(A_XqfjUwol_@&L!o%LpimnNH?D=B^z)09!!H{ypV2;vT15VLuR1plezM8+ zl&L!kWu}Gve+~cN8plzn-6)-t$Itns4t2ixO=uJUu@>}3UftBh_lv=oU*Bt&JVBJU zyYq9>$K5z-+EAhYnB;>i7u;W2i!^w{^_E{AjX7c~zek}$$omC`jZcV3Xpey06M@)$xbxuDNDzb`6sDSkqK@OS&$p{M}E=>n@a|XtWavlf#kM8dU#+J)I`f#8H9*SUL|b#p&&S6nAYiVgWhP)@tgpenX`Sn)5eB1_GF%!) zpY*G?FhDM)9G#&ajJ^IcBY2_w;*%ytzPkNw!(QIr-ZH`CaH011wcBZn<6_@8)Q{cu zBUk)Lu>apJ7ag+EeIFH4Ta}|NYXXw|!YzxbjF>82yzG1XmzE*hDZ^ee;!XC&)`B@g z8+JR2G|UGDe_3C-v-=CLSHY#9Q3XBI!yVp?u0|TOm}i~qo|T_=7ZpGl2JZ9$Q#|ytg+g*{G0B%A&U?N*E7Gz zjUL&yQjAgmn-v_=x7AuQnS3^8^jdm)`fE4HqwP*5CQ?mDAwxo54VZC#YVzKG;oaKq zzo*#qUX^Os|LEN8dY!A%TQKzN^`ku)ln#+dtn3`o)*iM9As2Q!v)J>cVHYl3V9o@* z^hL$;VpUbGSZh-|l%ov{3}k|f%%sDt6R(ObWS1@qnVZR~aO0r@d^|gsTv=JU&s%V3 z#48t8B&w_ChDq@Ai!;hx-OoxW!}i5TufO!Go=Px6WGb$91|^r4&82m%l{y3HocHT$+PwOP$u} zU#q1qP9QAcSq-&X@o?SSs6L;$6;?oOLg|m>UMP2_0oY~vdxE~zS%!D(M4nsCX+coKYwRC@QgTrKfl@8NqT8mar@BJlox{4 zYl7xyCnhGcvzaq<_%J?NDp&Wm4k}e$T|L;p?BbL2k6LdsQ4^7UJ|LWYxjE@K-yj~G ziW3VtQ%D&`(04{hS67pLjp+Cje|A9&GL7BCwZGQd3Wl~Rto6AebtxoHIJ9SaQ*rzI zk)M>GFuV)&fJ-cXJ;B1nq0FLhbke<~>)y^!q`W}}$PQx74n@X|{!nH9FT}{jBJa{_ zJu^pCs9HgZ4c7_l%D;I&k6c|`l)1WJGVpgEqm%rP>{YI#Ds!+0KLYU*p_aX?cH#<{gQ* znNxT!6)bk4elc;xM%FJVD5&3jby84nn4r1o?R;81L*E(v|0-BZ5cgZh^%pJpsdsg! zGrMN-iFTaC+af2CmeYhRq){hTJNleJIc8|iqYge+P>M9-ZlU0unf6s%(22dI4V}+D7+@57ZSyT z=f>15?$!qA)Gpj^}@cm zysApXWnstSo%P)$Z(rZ?cBdeE3tBI5YHdeFL_|c6tRfkH8Ji&^5W(pd$4ay>V%MNT)U{V!WUj%Jfx&KWZeCvJjawPma>wKx$DoB7 z+FRS$oPliZm~@QqZ}DF{UADt*Oje|V5Vk{QXL<(mD#fuM8I;M{PQ1pnf4e+Gur&b3U^9;uxY<&c;PSup0hxFObQyv$P!o<^eDo)~;@GL0;S}#nyAV0rm zcJL8gqpz>85}A|H+*J`{BmzEup}->QN;50alI%%BD``b7OswRhItu0 z5)aNpCh%QRs(!A91XTW-i%)9i#tE5wK}*DL4LZIo+x*Fxn+qrvc#@ZwPapeMsr|n8 z5RsX=W|&=rqcqwpH0>9SF3xDQH;vaj5C`gA@2iO5MK+b;djy5DBF=g7F0J*Jj#sZ< zfiS85xH7-8rbg^qi-eASar@<`iH-K+ZQi_|1J}#Vqy#kfs3hq^Ykq_P4fg~Y%Pv7n zun>y;wbDl0T|}qTVPbgb`E*bYy(&eWa~vy7q`K5iCe(_gE=ecYnMSjQc%`c=DrToB zF6zz%g=2@{{KsjZ{~!l*s760BPwz^`1ng0FB)?!@;qW7Z97F4^8>GmN3T za8;9Qfi1!vQGyFA?v9fvC*k|O?M%Womig@2StuBj3%g=U_xoT3BcqePEi^>%?i4Lh&3S}m9cBL2Xb}md z)~Z@h?0(U2d*w}kV!m@J<;Ku@6l!&e>z}H=bbpWLyDkCGbWW7iT9MCJ1o`XO${k?$ zY*`gVcSmE04U@_y9wMXVSNc2~jIuS2L~IX2{#kvbXtZ8~zQ=oXL-7F1scNL`erNg) z6sqmu>X0P+_=$3YYHx0~)G+kmK|>6_FYw=T??h;RFvxiq8}G*hW!sTYiG;6S{O=;E zFwJ;7{N>8dXay`Q2S*X6BqG7r?Yg?~nHZl@E0Zt2SdT1o@)5ma8ZPpJ$i5b^^+XFH zOZ1)r%!TvHloE)@B!%CX{Ihrm0DNOM*eEaaU6NJYq%mmFV8xSHlu7Y0gh0OXGk&&r@mQc zQ)^F?kRRhKkc=MYX>6=V>Ugz-U1Ry=Jd_KiE5+@F$|@=V!0X0VD{>|SgZL@N$JEwt(17{Tn~O# z=P{?*VK0C1GIctK0Z(zlL@pE)u_;7asplRf53N?in@2LB#}tfxOhT)vs0hurytVz! z7>f2FdtskU3%c>@bD?W3$W9dbMELr_2e!cU$<>s!*B`2^368h1U-`;290k(1dLSl{ z>* zPsy+-0l=lTU_L=kRr&`&Rv%}3-IB_>SNTiV6yY+O+=)4 z#!4_}pcp~|;O63Fw7k4=43UYMe>HN*sg#mW|6C#}P|5ez7uZ@u8!+hLdAg+y2G%d& z=ea+Yi<+wp#(xUoca@A9;p@aADJG_X4!LwpcLp-w+w4BI%2U$c~rDi54FYm1k?TtY$2|!WBNX5tn)fVslI`XxyuC)@xuC)?6?bHYiD&$-UmuSNp3^uClaV36vPbLYi!2IiXTGIWSfbDOHY_~>Cj zkH%3Lx2y$BLq$GVvFVVT!I!OGyY((ab;ickOQ>D<@|ybAm?CW4Z|KX*)wnovDAJ%t z&V8bGah}oI+RCI62}M=I=8(n3SGTFF%qrj-OK-G?XWnv~ci>9AU7Tga@i>Wr3Q$MJ z(t9wo75PjIlzGQw{R45WS0`I9Sf-_?V0*46zqM|ctVTZymgToRO1+J7F z(6ZD?bDt#SZoII+&gfiRTuiN2`~A4Qpq!4e>CqbTUga*#T2kA`ko)X~XXj4sFuK6H zwWB`n+H;(+LUtguwn+wVN1>?Ju3rHu(vRcf;vlrbRCKfWJUM$>GF--TuTJbtfEYCo zM`<&GL~+m{y*?d|oYaYJTERnRx;ToMxOf=su*5!Hk_R>;ci;dc0+5ca{EX|9A}IrX zeZ?{ad9gNr{|wB#1H}t1G#M!F9})VjKOr)6Q32KqBNm2)M!v>8#ijNZ4)%b*#OfYc zbJuPLK)m4v<5thk{+O|`l;OiF=nO~@d|?0Q#rIQ6=3#A0p6!LZC4GOidr)2eA`c;H zfAq2uKjlnBv{rTv17gI%QpJqb`sf1WYJUWTE#9eHJ~mUQdDgfUy6YOEs)0F<7x`b6 zBvcL}pGAeBW;`iWkHSZMe@VSnf4ooMkim-OnenCJk+0IM|E zhJ#>jlly*|{h{(UR%o5rPM3W;v1R$l7>3fmk7QdzO+(_h5n2nEoUBmxqqPtOOHh^L@3qU=;mz|DY@pnY-A3 zjaVZ|E@zi&;K*-OmYi%J{=Xh*+&T;rg;#A<2~Oiq&cpwHUil27##T}ijxrMTYoIwf z^G{I&CT1ssH|B1QV{$VIrn)RF(H7vEm%-`-W!0_*1lcb@)hbsjVo()4Le-^Us)B{*|3#iD}2 zE|StP=huvUWKkOw_}@{#rnA~#i62(w#RPp4-uoo~QoNlBikUA^9fnh~y0TtvT z6`X&Bv(w+DOPf%+LM0Xh+o(e%K!A4?@ydF<`V$C%cNn=m>$Uqqj1sK*fc(~ zsmKYN5jK^DhsgPNYO(ID3G|1*@q-<%pP@%eO-p-@V}Cs}5oj52rwgL7N=oC2i?9S- zd}24Hb0Gr;%~XqULK4;e@^tJMs4q`T`#n^m;(9Cdf$0+!-ojBv@}oiofaUt zKQ*a;)?Z2u@}C@RjMigfTqq@u$@%o&KWAcocKfhJkVjqFNeZ@7E2D-j z&07PUu;$m*gp)vcevSN%IRp5dQM+hiYd1=rMg(ocEz+0U4BlhQ3#q z$DoQ>RC?h`Ga$oHZ~hSIvOGT_=Blcyu)3L={j%$Xu0v|P<(w^kBp^eI@Vd{9Qo`t} zzLsoH<9y6aWwqSx#Zj<;Nrx$=a6>&3!0RO4cSRscI3`>BOr%;PfrTMLJrdDboEoMS z7Z(HFk`{;%4S*EYU9j!@G{h6Wl5!0m<^60qg-B3|r^V&(>BQdLG)Ysry#fDlB9IEZ zgCj&GLzQ~qn2a=0;F55FrL*S>Y(#9t_q7>?VoD=sG{~gn{6dhg*SH~}^8tN0e6Jo! zif~yG7JM?0iqI?0a`*nT$K@i~(}I0rX$z=W&D zkNCqcoRhsqR70k4XC`^Dwi+F^DOMhryGEXm$O zk6M4V*P=pJ8*)S{M8fKX-2$BoP_l@9L)bHi)P3q=F*N23&3niE0|_0#`2pCNCt4RC z8I#bN*rP{h=2_I*FY`bL^uFi+!gTduvAz_z!<0apelGN(T+jmZ4=~Vs@(n2MInmJ2 zU~G)Dg<9Bs=KFl==H})?WNr2|jh8!mkzX@)U+piB$q*lZ?Gi0PWGXl&Q+y5CcsEwZ z`V#=rmKLK2l#(bMHUfdQ6caf;Qri`fRG{En1Ve5d7#L7I55fmF#Go7Uj}T*bOnUgsC&WR91mS^=Fp!@-me?V6d+c({EMTlhB^# zVPxQP$R6@&MKL-p@@NxI_`q2kXV2#s%}drK zLL3@@pKZfggtTWy`!-4uypD=1gr2R;k2u;QX!D;n^u)uwU%#CU`@O|{WRD&x(Lhvj zSLas{9YQh#sKRZ}C3NyFsw)`gb4M7|T1LePaRGuD7R-Evt6ScOHPY!S)pYsk8|E37 zxL(MUtI6L;^AdBNn+x4Im~GlFIVUVE%)f)L?$$FiX?n#%vHGO9Or0WBm?L`IYeDCQ zN*}|XIbG#5ws($nno_dod6I;V5r5^7tcp++q?I`tn>GV;@`Ze}_A$i}8Ccj#Zw7XZ zXJO>0wz7PBS8cF*z$+P}#f_GWi&_a|3rCu;)49_Vi%}oY^9_M}LxNMK2y=Fu3vGPU z*_Au3im?G=t<+~I;e?!wWcpo++qM2{6h}IYlPinw< zdM(f@7cP8Q)EXtqI~9)`<$pjaN-H|VjAIrj)K%+fql=(SAg_?k`==%&kyO8eg|S5RmMB@Ow3P187Y4T7CLR#kR8iUbmwG6j`CCCOghpd6YSK z=yV9fF1Go;iyLI`?6OJ54~$mwuggYK?0=v`ISIe~h0_7IF0Dm{oH?-ylX~AUF`u43 z?XS6>7ib@sX2Mr?x35w zC^BNk_Ywas_%2eeu>|K`8)bd^h}MOl;P2^TMV>2OfPX*T-&v9;?%0`1PHhu>LZ9tW z)I#o2sQ&#b18wRt$;=gZGv_}RYP87hP-@WC!Ph` zV2_?+cSKpAJTlVr?(U&VB!kL+=S-RZI0|Ja!QL8Tl?&s2C!Rj)2fpK74%e|dwK_jp zM==;~&2(BO#ewVzX~=$TLu0R-=J)`{TgV*-}5RjuOgrF zV$jZXDo|Yr;w@^A(Xb}W&cAqNGFs22vtq|!mgGyr=^BQ2vn}vQAUbMEx+k2E5Sb}T zF3$eQ2H*aDM(>;!}3GB;*eNGv=2%v=eo$y%$UH8sB6>FQg z%Un7^I8{&lKug1xL0kFT`2GU(N;q7p_#7d=rQcDS38egmd3L5g$wM(^zs|NADZ=&V z7hi1}558n<3~3E1OOUN~4`hOf=msJ5@2M<;))7*dK7zWaknL&Cr+Q<-*qjV*?IJ0g z!Do`;10F)aJjeT6vdaV@Tr6j5l$OE;Rp$i&w=y5;(nM)xV~9H=G)?389Q<4|e7#(k z1RovqnM;~!D#1O<%cHB*fc$|#*?uV7&>qU5<^Kb6^0l5)_~HxX6%xS!dXA$^HKr(W z5Y0>gASy`q29^1T2-mAEXuj!SkI8XNPTw5kWllywgdWMmTxl-5xeTqh$oP|hA&RR9 ziQpmn>&VAAaoAQ{f?IAo{@Nrbf`EN~O}PwW7%LiXIfvLWpe+RzvgeC2KO%T*Wd>4_ z7M>^ITWZGU$j}Q-)q)q}1T?o=9#vNM8SVbPD+^}-`IxE-T%b@KWPg9w$UK_`3taMS z<|e?f3}S&<`E?(kvKzxtKFv;*I(J@_5-`ZXnir6>)m3hQD205nK!Jw-gnEt6pHa|< zNj)y!QSHwHOhx$&0AutgPS}Q+(;3SMLZ3I(m$0i8#$$jd9ikI{P2*X_O( zL6u-c0^|jXN=3dZOFNKSilcaTmfx9hOh!iLQ)W>BlJEkoO=p=~-=`;+azp^~%^5o; zcU5}J=)`7cXZO4h>#3jN<8u&iLWIL=i&C8b@aH3rh(7$T+z@5~<@E)CDluK{8pUh+ zGUPmQ>{v1A1&+xy-&D`Gl3^HuWo^)W_X|K_Hx7?Le(rwx3jz6Z1v^s#O*yd`;Bw~V zKx)`u{o0g>*E_@Xv_Rw2JzyGdY&?nQQ}2NC1!Jq6hm=-FTLQNw`3yEd(J<4nvAePp zqxkdL;ybq8_k?AjyQb}`02Pi&GEj#YX2Z_sOnlv|>+tgM;E%E4C>>2^a7R;SMo`!& zkF{idA*~-K84wPvcjF&0_XU4hlHln=hJiLh1L5{QUVPO{S03LHRs8<1qxo|0ABqQE zA$!`HhPF9CYDpa|t5iLvrdnWNiHE%FG8ek4%o^XI3CY zV}@SrmyW+?r=gMI1H@e%*vkCk9C0!6C%CKS9!~nSih%a0f%-guLt`nf^5ThEHTJMJOLDLxx>JWk zg*A;}8@RsnpPc}WeHN+Mf`q(e0l8VBh17h%+H*6Yz)CvuB!(2zm1huZN zbI|vIw0jfi@)$43C6+-m`+2os*1KnzGz5W9j-u{L=qOvv-@h``^b4Zr))zWbO5_wE zks|9#1ckXSXlb*ictdbj2F2U$B4zoe1Gk8Zj8tcxw>}s60FKAU#KhDFY=U^)+zq@K z(#Fr=Cm1V?&l$M<^v`u7HTC7CS1F45U=IMk$9ZQrVd=WUB^RIQ>+7FTd++wmci~px zwI+yvC|rt)c-ukXwlx+7N=VtMQ$I)c9Q(b(I$A*|_SNOBG)1R+Na{%-VqF#|eZ4*d znm&&-Jlvex(yWB41utMgzkId%r4#|EvSPe&Q;rOwh+bhRE-H$%0l_#V_^+KZ7HB;M zp(qZvw*D=^VPnOMhM6o#rjWJFjg12yF#7u?#XiBCmxV9I0VorMuks&3oXQyhR*|hf z8yWiEfyx3z2J{YQqx2b)3&;g|c|ZfzKFJjwO=(o5T=H-L^l^L(eNyG*xs)8=vEEnl z9KI6A!EJ?dfz$@mFg?;uMaAqE2bDDEY)`$vb3k|A1o;PW9v$dK_ckz6^7=OB)ARCv zmVtaO*xwNg6+OJCqIPk?|1ki8WmQ%Y=0nN4+X{wN?EvK~-Nk=k%m*`My?wJDAi5C3 z!+bjECZQ@`vz&^FlTkC<@1+Rz>%X*Mr}vQHPJrdGY%5^gsfCV`Hav7?+iWM`29>6w zFsMh{_#8kx&}M68x7fKe)?GFX!A3iPHg>wY`1lgmk?G}H?karV}Lf4uN2}aqrFYi z`)*)Bq-5-)l&GnyQV@=Vn#y-f_Tdlb`#5YRIB$sI^D^JbcRLx`q{|Y2irkRJ_GCXW zbQDiz9Z#oOS6l{pRACSc-&;}U6w2(kF>!C;dM2UM8;<{F%fI2L)9dTy+?rJzBj>T+ z2XtcjQX*eRLEbRiHYUPvpk*3AtPBJPy(@|$Ns!-Q0y8YSr1vQ9`*sp5(PjU921b$4Wm9q>k)C;^a>wM zm_^rJ0n;a`7Q7B{p?=3!B%#-3UiY3Xua1DNQ?R=Lu zWPE2~$K;<8=_=t}*xB7vmzDiagaJBeQ(Y=y>mVf+Nqx#}bFo5OXq}Eg-l%89pZO=( zGmbi5<`64^mBSx)=<%UloD0SF%VY&G?)OW=IUBl z3{#GxEsa^&9n?p|$c8>w(Kb)>s(l?L0L)p*K6`{pVf|en){|h|V@E5}M4O>J_Iv~~ zh&-k1Ir!VDCAQj@h-l-4TIdl(S(%f~$vFRkeEMa7Xzy<;<%sBJ`d|wH?Oa6wdJXnl zPU_}FH}nZ!sD=}ryzwwS3z5s&(Knr1;d$s|+*=7f66j;B`4a!OiNM;6Pfn!SnZD2K zDtAAKILN!VRd_QjB%v4XF8GP=DcDq~=5|{`2Ri#cV?Zb)UR{2Kw8k>Ny@OGr+WrBV z_lvLCppQ%&T94bq8GrS8crkBZ7ThN10$ffy6Hp<{xM714_lmerudo2E9{LT~SKdIR z4nNrl9s2`I@e~KFQOyY=d&pX$O1|T9kyJ{~CXgBB^8KLVx(Xw+?-O##yvqfkeRE_mCzv}$FtHsyu+U=q$5Sa)yvKEKj z8*=86WVo__ret_xcgO49f95#G6YL(4&`|h$eyPC_K^d=Ze-7`fJ-)P$ssM;1oir#K z^dc}A+L1jiYfe&GP|iaOg))l zXId4hOPT;_9|V2^crQ_PKW)|5fo?&Xe&6mt!O~#RJFjL=hBm<~rA>}4J{zi*gz|(c zb(or8mUiKJu=RkZ9IB#60w_=*fyeb;eLgGvw8b^;sMA>}-8P5@-4G+*&;?~46^U>} zsE=$PNsdG+@iCAJK78+oLR&JO#LNHkO5E&FT%6H zKk4Q)cQi>iH1HV6&!FK!9|Lm_+K@Gi6B8b7X+T(e{1GQ0(6CF>2zH?U&ESZ}b(&s% zucKNVCgx_Cu6-s5QM5CCJ*ChS?}iq#GmVGkwv(GbDipv`0 z{Krux)dOS@=gtaG2;H;*DcD@g%#Gp+qk`|P`|=hDrP{2`F>4aq*!b3^w>1on;N+N+ zr?-p0^{LsV)4;BY4L{t>A88Bm6J8Wu`){S%hYqq}xC#;c$SD%durDh;Ytw#cG(HR8!CS>zv zAo657G(n|=Yp}WzLEqLK)&uL&%iAuw8L+LU4|#C&j z6m1?y7%)(*DulJddHm5H_+~?3a>!%z;cOJG`@F!NL1pv5DO9^R3LptJ<=R_hP+2Qp#A5v!jh4FNiV2TF~@;W@->gcn(5d2io-`0J32n@cEJ%cCujZWQxGGn=EnJI$- z{PIO;RuoBrF?8KxIUfx7saf@tSDu}A}wjz?xRt~!v7 zd~M_yAusO}eNvVWMgSP)ZND~16k-%;0!;Tow;D%*ve4uW?Uh>aSobx=^nHX#S=M$# zaK1C+Ux84G4Y~(jicIJ0DM*i4s;S8C^lzkKoq7$Tm|!SE3-3q$S2(A>juGOyVd zhydSl35++HHP87VS`Ru)L)^0o5=a*gE^>m>GX2f1s2;L)Omwv3#2yGdnf*(v-vt%N z$(-cb2_@a;XXqjaU>9Fz-sH5JWb=Y18t&S@kAw*GczzL@+pyWq1R(&xON66DFDR?s z@cW8OkQi%g(5$AM@$yYW^h;jbSzxT3{+{0*a*wi2|^x@PE^G{@hNownt+>A{5&{ z8p3ATCFIlw5*!e{$-*%j$gu8Tl_2e8KRJ%z?B6<=mv@<-3~_VtjSKh=#?n%9 zZj&===cg{2AC?S%^O>cbtOqvI zpATz-Kj^{@ye>@b7GkwIwB`2n_Kj(;T#BX+*gyZ-aDo~igPd=6lBT2tN~#>b4^+%x84(}I(F}Xo2zx9m^%5u_PM5(((SKc~ z11d}1eJ}=|Cwo4y@rU?iVyG_$<>Eh=;5tG%>}IKLS}2FeCYn{e?~9xs;rqkFvo^l{ z2pt|qYT15>yfgbtm`=$DuxEFMy>hvfPJ;ybaqOm#pP!I7Eb6kcsc;umaHAVzDzX+^ zM(PURI&{>vwt1GAra82HYAkxXE1i6Wh2m|6D--gS@Vfp^v2-$ry8v;8}VT`sgR8u={*Y9o6& zz1M{$+{sq!)PAjbq!30Uo!fKPeaz&UjGXKs@;3jaj))WTHh+eNg8W@j2+IBrz5TvA zqa~DY@)n1ptn$mAIXJ*#JMnabA|9DG)K1E%+0>ELmOskk3a$Vcc5Po~MY5m_ZB1zy zI+T4h^`y8`9Bsxz5wb_2KYn|27!TH4DxIe})%9-xtGT znfXBQr}l?!7o6Jf{Pw?zZlvSLSFF6WN@RXT4A2zmyFI%O^RtuJj#-BpaY5Lx?2>g@ zl`&Tt)*W$CZ)NTn&SmBPp1CX1tflo~9c+%}RzxH)Gtf!s6kDLlR76A;}2kx{YCqx44F|3bx3mh2yT8KN3h}-AP4H+T!PujhM*~8oVNM!MODLz;&^XZ8s$Iuez!u>sTZ{lOO|{$>hAAqOK-zreU=bJm zgvcm;*#;9w@2&YR&bYa{Zc#`c!(MOD;8P#6P!Nj&?8xzw6?&V-i;9Vbf`jZ)-si7k zy=x9b=gfHGzj}mDx>Yj~tUI3OjK^;sNa&}Q`rMI-^+o9s+&;iK^z7~vEr|EEt8oy- zser2;b;v=P%Sxd7qp(YDMyL0qSa~mD@VRoGVFilse84-oJNmjwe4NHrkF2yl@SKyyu{G?(B~9{~fX;)+Uv zXfL}t(ow$swG323z#S2g{?IhVB|fZ%5e#BBD!B>3f-XBo>JEs47`^Al(>uBd)w_Ns z3G8q{{t`WvtJYV$^@UDl!L99}@TaMIpHLHvDV9R~890iw&8r#)cw?}si{O2-sXPk{ zy`mt2E@<)Qc8;Uaz7&x4OlTW!eL5m{7_{fU4?r6m?a2_3(+%ZreOkIW@Wv?rWnFIO zyicJ5It7j`f<{ralW?(^r3Awx9MkYLOfQ{=f8Sq7dY^!FYeE5d*+aw$?=I1UL$-q=wkg0R=6(^b*)A0p1ddA`6zw zAZQ3}SP(fwS{yv+pPoS1B@BAM01vq8FBl&IOmiX7ryeH3t@)%8Kgh;`sYs_~*{)N# z!!a4_Hz5f&8{GqNr~qNsnrJ4vpSPb;@ilh#l&PJ^3z$+b--Su?vg>0X+ zqiOo$K)ia8E{UvAlo-aR*%M5V46R^H;Dva*NdM3{UzH!8!G)|3XGJUAy(kq@1!csu4y6}k_m~AIc}NhZ@lUJa=pP)1 z$*eho+|1>v$sDllprt+^+)nx45k2_2gVD&TmJA-;NrdzNgIK6KS%D5RpbG#|=jG+~ znze>VB_7}a>7h3sD)VIM+5y{#c1gWkSho83y=--@4;k!-)44{J5)N~Lh*l4nZWi=| zPuBiQC<2`cq(kU}Li(~47klwC^3P0Y)IL2j0Q(LiKsKeZq#8Q#-7ZTyxz`ss*8n6( zj|6?x6K63jDTMtA^AqADq-{n z%>PdCHNja%i<*G)8Br)4W`-c6f!Z)nMY?yoBs3_okqhoY80;j-t^_7#&I-N@0}h?Q zNnfm!9)R2co+b8Oa%k$wCdAxm46mLOZptxOe%d$T^vXhRWnTIU{;v-@pN`6 z3@t<*o&#a7fafiNh9fO?5ZdZzT(wja_NsXwqa%%ONE%`>U`(5Chc1qE!kOaTFqMbC zYy&ocYRiH{bWxg|Jl1nS{%27QCWcrvls)fMk$-JrizO7Id^+s+&ws;rXD=`o7Z^xS zHW4|LYxRI$0VYegX=O`g6Q0_GsZA&FE$%VQS4xf)MUm#0o1`%UZRkc16&{1JR?qpq z7={IK*@UsDmtf+3FAHH>Kr*!jet{)fT=8@Iagt0h^5UMjVqtB!&m5 zQNX-ZLJ%^TSfQ;Z&4M#oplRZQ4!~p-ELrDDpcq4=_h=Uu2otQ|zRW$pB4Xp$UK+Ub zRMJ4NsaMS6I8BSB@Nk(~=nIcjIJ+aZ*Y3U3h)`783fh~%;v#9}G-oDz^{ zDBf}A0dCb6@RYZ*!NLm6`%L6tQ218Rr$yOLu=Vx)jhE1Y=Y^eA>~&<(C{_Y&v!LsG zKgj#F>o|xrVDX$YEe7Ev(_}9o`GRKq4Y`%G4~kX(9c}Sk`bun^vwd zX{Akj63IpZ7_s28)8=IGjm(cDv_@tbNSm0(b2_``Ij&&+;GjmsGrpfbgqv(BL@~4OcCH}av622fd=X8Bq-&ttS1l? zO(DS9mFwxiZjHkC6NzoygLiv0jvpzmyKykihamli-K>MWMI0~5qZpPhm-`Bn|{y5|)^ym&SCLpU1^=J)`FJ{Epur_JCj0wO*p@iV(wc1dmq|O>+$xaS9+7_ zp!K7U9a?%8REQs>-_gV;!h#$PP|=t{-gW4M`YjmO28XKoIh0VsaC(5Q}v+f zNbrq#iQA#tkhM|h7|!rfs0R&ryoPCfyq&S}{jZwB4q7fB2GCET2>D=~$DyT&Lf!N9 zO^?yqw=2b9;)pMgkp5x9Z!X(>AAs(Ha@fkjUnrCzU$LK_v2nazd&#h`MI5=iA|FRV zuBmwk2qy}ac7I;{eW5*G$>H1KJxajJP<8SvrnkY&TbRk+g+2IF^h2~efFgSc$VWoF z9DR+7#o=@!kLBw*p3fdCt*ArD&qG(-xJMr3ovsuqF|M|^|E)R_t(Q^@+z1ABr|aHb zyI*dEvRgJYH|VJtC6Xa7QTMDlr~&4V=h?+bJ5#@(+X5zq;4EuHQaLx%3e*P_s=^8@ zdzIqFOvqGnh;**A0z+ zLt;_Fzzk9M4zJ!zOfAw$N%pFn7~}}ly}0*^n^j~Z0u>!=Hm~Q*!?8;%D=EaUxo2IY zLy4!L;|AkNj69KfUK$xVD)~y+n&&|=isFK;Y;EKRJWC1$3U&3Kb_mnD@mpi5nG@X> zSpU+S8@+G32rkX?xRnf2XyL8h>>BQi>XB$#YeWkHsShDLL17W4OMGrm@ekX*~n6FE5Jz^~b8$(f>Or{H574ilN*A|eOP zGc7{t700)r19l;oT)(n>F?a9o*yZqBvDBHv2T4H3(Xx58JJ+sV)3ZRP1NF?=)6;kZ z*qlskJ+QKQJ2^q)yD}qcpU7mpZslltg}n1L=C@oX#^AH)=aMHn=aJ9$|7lT>OB{dR z`cszV&kr5JW@9jcY%{`&9r!^Qd@GbWDCUlj2dquw9g~~P>a1j&k=8s4*~2L_rGUavpCTjpxCduDi6 zv+Y&EP`_R9bq^8goV^}zSWD%@8@^U~!>merJwX~cw;`S8c$*Xz6}2G;nUK*VD-(hX zpi)17j&<9zKDy5YYxxU{r%a(PqPySNx2mq`M3OJLs6GFHOQ z^qq3}-d)^b8nZ3P+z&5_Nhs9dv*O}?yPy-&D5QAN+E{nf|tnOfSzr)F+`+B=yK!S|M!EH@%(iio-qWDn~BZ-F`dE;o7w`ua9qmdG3=U zfMi;2&<^LzlXPu|l=Tb9aV!?b<;s=Z*SC@P&xx!oZxD1{K6o{k3}QDTDGsN_8k8lcvADuWlti%)2U|)ZZ7NzzTucgNUg`&YZ!Dt;~;9{kwPXdU`S= z_cuSR9)O+_0-7ccUWTu(sCRSH(pMu2b8q;3Y7C5^^Fg)I2FQm|GB+7)RW; z{_)4#%KsAHt4%GDB1q_PVCVR|_np+KsVPw52d61e-dqAtgsd8%+C-(RB^uSoxVmVWZ zaWUeDzST(ZA{z(-pnM|;8xNHyd2pHv(V)G}l{T&=GAHg-72J6MCa!V%OV+$(_=LBT zq9QCpb(sM&sBZ0*EVcPrbv1~_Gc)CLlI@1YB@a?hUyT2{(1=O=I~6|8e0~b1d(tl% z{T$~X92{(8W7C63z$jFD?h7l#hD9QsE#J%xgm1}Ej(%S9;F(9^Ld|h^5$%ZBLCY=n z`X7s=bnaax`xA;3m6RYN1Qs}nb8h2u99ccJsP=1Ru)xtt@CqMd1Sj^D4Q z#&@ga-TQ&v;{Lku&$lSwZM#By;2aLWW>mm#WC%X_q4*wvUqRQeLu=J zqbC&2D4aTLY&^SDq+u*jom+#*UR=z1T3%jWTB>w*3P~!cQ4kY=`~;g@T3VW!^&i^C z0$5*DeM4uY=?hr6{nHOBIV1}Vv)DlNzpV>GJ`&HhoYtGyH@HE2u(+t`dQcE-vLdOt z@vILwYUJO~_3HYzWJw-~yUo8#lzYQc*y;rfA|LnpR#I9ThVKD;0)xSLUiDz=-r{SX z~wrIM$DQ26r6;CT7Lwh(d#! z`zuTGOZ?!#R$@VC+Au<7Dwm8_D#)CM*p!qJ;$4{tu zi5%Schh+Fa-#~c-zdro4MBow1r%TW7L#|s#Ff?xc`t|GNWYLC}=rG^(1~-xQzteoj-*t9&f=^aOWst=_9DsB?P(J5Bpw*5Zz1?SG zc}MtJmgGPCt2_Q|JgEIONYA%ZaspLVq#?TRq|q1O^eV&^4DrDN zmp~3y02u~GoyB57Z_`ive7v1V!-qtRw>-%U*9zPan)$3aA@)8X@&=pXpWK3j z7kltw&?opQfK$KKZ*V3H=;)p=4u-GcJF*&V^deNE6$H6o$_DsdJoonD7l0jE{~!kH z?ZXdzV518~E$7wI6B0Vt0|KO2faLWKY)3vvVzB(HyWs23PK*6C#Db6|9Qv?%FVTIb zB_I;1FUM99;H=&Ophnww5qvYfj&kE&l|_P{aLsSm`GVfKHf?XTOW zwT6Fy;dT>WOzdyjp$@OC)>SWecW^aC9*n#F>F({U{+;ws@0o$> zfK_&CZf$rP*{57nUH!zH1I&E9dX*REW{M-@BwF+*Y8dc^V;R@YOUZPdwXH)(;EPvY zz0$09M;3H?)5_@60G!=`_8x15rHp7(3iqa~ka zv);uf1)}@#X6ms;t{z0lmjBc-h{xZsKvGf2x0MP#32-3dlY@oA#ihZ#OeK+T4arC@OIkPHXV(BNTm1mW#T( zGc74!^5^OehmjT+3MC4$g4NFb-RSU4J2zm5H7BY!aGv2<#0q2bbC5o3u)mS?!d^Lg zpZUPyKFreBMugmN-COm(x8&8jFOBNnRUp>CcBrBkP*_LvWiMZ_KNITWRxNydlRM1q|EH^ z_0-XM|2{u|98O-I^D*xGx~}`W*A@z5%+6HuTh~s=2@$qO|C=aJ@YiQ@EBfVbWoimI z>deg0zZ`0aN{`mH7oN!Sxh6#G6Ec0DxQdX!ai;zvfBmIFG3EVn?!<6$|5zUyc~$Fp z(D+c-p5^=apX9i&W5*@>V9(%jZl;WBHr%nP zIv+?5W_Bh%nbI8-th38xIf7tW+3p%k#>JScBGw$P`hGf%G3Lqg-pm*7v{q>8xK621 zVUqeAT4JfJWmp+hR9MwY#C$BiiPb+<;gjYg1_4P|ti^uv*U=r>O^zq}n+|@aBJSmX zkN`pcb}Nd|nNk_=Rm;1isL5hfky>kR$`MboI^vw!ek%aW>zEyzyraz)<@z?USAP*D zj$XTlEF}vkiBE^WiI!4S8OED$SUf^`Zczt1o?aQ6u3ceq~ly z|0zbv5Tt+1XsBWDYe?okK#1m3{;vl4Hm7aWti&QBs!*#2O zfX!^fH5=mBq<`+`}qOiUyG_<9j$kc zsOGm`m-FSopS1tKL5vK}T)-^+%%z)I%$kMLo7i2uN2ljj66%lkT{C-PFp}*>%Wblg z28M<%JzUOKOa6|Q(%cauD-Z4W_Z1fB_PSWqwfoK=AV7B1vnmy8GaZ(eShofkPer)=4nnJnVBJqVmv7z%U$q?H3NnwnGxE{>Myv`mwQOg&;!tRkbJOn`2O?qgDh50J?5=p zU-soXGwE4abH1C3MqqLw>7RmNUn|2K?@bN(nL4|=Gy=alh0n{QYRZO{FTX0`k-*~@ z;JiXueWUL#9bBy&E2Ox6n4glg<4|z|*4E78Hv&kYEcMhRl1(ap-sOE4rpH4p;S-{tqN{coJY$;P*LQD+}G zJrc`Y$h`G2ns~M(5&(_+6H5Rh6}E-hvC9*OWbYOI3`uY6v@5fUDvT^|vT5;D)+fs* zKiqidRDCpY-25v0uE|Mz=4;^zXIf+fs#Hu;yn`8Xe71w3QBzlEJj9LW_vvDEoc=UXNnQ#WVNgjx?fg*P8+nmbLL z>A!8dZ*CDNfDeoZhkZgmf7II_Hc*}Yj7>Tc*@T5X>4(@fs4 z7fQ+d2nHmCLD-t=TA^-ncbd)e=Opi}Ow{hOGHE&~fhi*EV}4=`zLb14plZBR!F#qS zZC#yPadB?$)G)|*#CIDuOZi{bzs!1O*yqD3SM!j?S-LA}3Fb<+fxD=Ye@*`R*zXlU zt>onQ@81U~qVRs1bGU~Y?{ff1gkPJ0>$|F0X{EOY9K=zBnwy*1ELR(7Km>+RDdE}) zJagmVnT;kp&bQdZ_l5P&d2@VD|3JF%pVza&pkwOeM?bbxxWXBw%1oGzDeN;3xwIxE z0TnQc4I+M%c@`ZTZSSKmWEn`bMsck-QAx)>FVgDEF`)2 zfBEr)w^CpsgV-|`7}EM*z8{~57GH=3WxaG#A@O69hQ`0!N872Kp4DIhf&@Hs4+US1 z!$DhGs$1Y@S|@=q(@FjMR>?U2xVl<#@zDBWzrcTY(cKGfOOi`7H7JTkkld!Hy5v7x z$1Z#HmXIEV>NU3A(}+Hype!x+r}(`aKVuEFVXawG(g@sYa753JwLJNfg+{ZTDC*h@ zUc6|<4Ys$3%$z4Vf(#}c6>V+D%|5=s5Wlh&W|J0fsJlSrVcgvK7^471x|moE3QW2| z%sK*=2s=AzKhBWMT^ZaRuy)48`HalmT{JERAjj6f9O5zmJG5&bpwsc$v-Ls%JFrYs z4n(B#gAZClue8e?>w4~?zk|4V*nuAPz__=ydwFID_~c%4m)oFl!0)+JxSp==r_N3Y zpz2pqmz=xX`x{Sl9~bOh!utb?X4`+rFzjuy7q4lkaz<@$e?R6j0F}n+RX^!84OFbs z>V+O(-Q1nR4{JIF4<#qON6_hM$S!koa!d#@F_!U_Oey5DtE;P%Q{sLAWy2thzuF>mtH zz8#704MaWAZd%y(3dwjlrO6_|lLW}g9p$x)+Q@zu0t!blH<*eud3w)tl5}s1)ey!;Y-|(s zwqzkgH>D7b0wX24fYW)>fyQAG5t3qJkhe=mWKfVGpMZTfZhnG3Yw1?<(RMqxMW>+P zmgNjjHsE*BPS2=UIDP*wM+H8p;Yj-He)0WTjrDK9n*|zq;9ol-dFplCHvkrHbgq8b zX>kV!Q`CsYq${xK@cu&GbAB9g;tRlPtZ!~1DHv-kj$U61RoFKcW5i;ow6(pt&A#i* z^VQnz+7 zZM<{qb;)-D$x^UW<8Sy`X{bs+*V2f?nwahWn|Ah+wOYG6?|E-p_wD)vZjb~jZ}Tc;yra#a9H zV38yf4gM-GPdbwmXy@n419L^Za!%pr_HA=5<*saHp$IZKeEq=>S`*F2P8QdZ6CfC4 zKc6b@*3-~fck}p$-8HYk{$Q*_PvF0kc!4GNSK@evlV{gXre6l7Zj)>oc5BxK4UM`z z7tVbZIZG#ng}-QYnEPSH>0S*R)`+K1gQ{aF?Aitg6A!z>e@-CStlYF_oa6E2DdT%P z%GZ_F(xk~()C0#XUxrysz1FO9pL9@_q&>S=_9Cxb(P&z7vYBzw{wu5rEyGw$(=3T5 zDH0NH*=^$P8;MGig@r;NQ?`Cvo$39#(gec7ajx0QuXcqRQM6-89ppTQiFo1yB{Wr0yt@zl^>!*RCA|EmBqG%;bqB z`i`>3K8}e7zDG8$Aqee;I?R7Uo5f4y`L<^0_5q#3(obf zweM`6x)tw~s!KcfIUn0!%gypWDsI`WY(vZI{$Fx3i$hi@L3roA-%)H6-TTf2%zA=+ z>o~5bqf@t)WdJ3N011t`{izQ`?lrH|OAHsrXwR}Ghs3kgZCVlS;WmsOQy zE=Zk=5g#a4l=GFy7tSv#ir*_#s{z&J@1G|C2@W;O)JID;-dgN1qOY%dHZ#xzh@`KN zNEx&5uEfG^z@u1?2O1}uD;@PocIA~N%koDjaf#1ySB`!85*vNP!u`0aCKMD6yq+XntqIIzIDM#IG{*QDPelMVP&dU%>he+GW`HJ{fL=l>tNYVh;t6QOncWiJM%W>{X^A}Gha-Dx~2DciFeRv|(U zDI$;63kiF(%5%J#HBHXCD%j*_{}b!tnriBvmndh#b|cW7;y?3NeuQK7;bLLD*zLa3 z-a%VR1OOL%vnH4)oy$F~l>H*bpINF&^?fJYX#O|B4^2v{I$W##xh6B2pN5g{-ew|n zT&*zEj;qKV4yzYeR?7PtgN?N%$I>q{gft-g zw%5^tpL&Cb3?J2T2eEwNF;~6q<$O2W^xkMMq^723_i*CO?rMJ#GbcyKT0xlKGl25Pi*FPzEm@A#}Eczap;KfeJV$o{Uqh@sdsr6=Asd(S;<9n%DnoOnJ6M8O`}Ju)B^%K6aXn4$wnH@ zF^}(SJaRw#vbeY<*5sfTySb2(>f?_exrj-az2Xn}?2M|aW|rJ|h>87kDG=ydXNT9I zL+la3WA4V0dQQI5NBtU(@0CPKpjKbM0hvs;?ix|Do034@L2r{l0b}xNyN7Py?6+Lj z$-D7k_)FdLt)>2vJ^U%#2hV9J#3DNgA4JFzGD>Bl*3pRHN1+H@vYlv2?E(ES-MXt= zogcPDHqgTyJI*IDc8wjj>*kziDN?cy7o91jlpuWDmqu}1t7^1>ca^Vkvj?v;F>CIA zC9s>?Ju52;n@NM};5Aqd8-A1Wh~HCH%caB<$zJ6)(LVd~vqfO9NWF7YbokC%Cldq7 zE*4?drYo#xSk7e$uM(A+s|!7Nyi|*QJn)~LLx%K3R`DNE8#6g1EckH97{bjyKFZ_c z6P2lY*9D8(n5qrTxUhA}Yf~Oiz&Hx{ZDMHA5w7fJ!pq0iM;T*cdx^vsWaT?C-2H(zTu)qv<>&O})ST2bBljmiAua{|8Xi4#zdYG#a{DN7^n z1n>Qlu@ZtVsdWRp#>quug9`sYu#{3VE5J8?TZoZbTHUxz&3H)hR+8cs9rc!-JF+v^ zYus--x{sd1u6iuC)hUo_fV*&A{ivIk7W+kFG5DV+s?YX2XM0n<%57#H6!Y1=b`dXD zdr-Yff5CRN&Ps(Wkzky`Nzui>^v_N_Q+)k>6;R2royraMdOz;cCvbC@8E|SLYYFH^Y|EW}gRv&xCch1yqt&X^W-Xb(aeKiDhpBeAWh6K6&t1!u|5`YqocFW^gNLhq;)`ZlU431Gpo}Va4 zdwxQRj`qp)!AfP*#vLqL?2+ttkni^w1w+dRtTL+u+>pd zyD=^k$&ToTZcOOdi6gJpoB#7E*D{5R7*P)q&8&&~{EPudtejma+V`%5%icob)U%ez zKcb@Q|L%YFjl<%Nw<-V$9u&|7J6%NX#u*$K`qNADaQLtC-n^IbtfYW@(lb$+< zA7S0Ny#PbIbo|w8{auE(p#ulCiUbiZ0{?VHI>&TP!!bA2;;daAyyU@{_K z>0wVP+(*5t!l*S@k!#h!qtBN)*JJ~_D*Z=SsC2!zp=XIpcgs{mKL4tLNT7`=&k_s{ zxV|-xGGW;3Ynp*Y)tH}Y;7iQNF6>D0@1IFz_d10KieSsY$^P4b6gRI1@+E+yR?Z3k zQ)(g_rlyJt{$7!gtsS2}#qSiaJ&fo?9%2+xc zy^G9DQ15$b=6D$VGe$;6-YKrvKWb@VG2txEOcsTSgoq#Gk;IoD%=cC0juaLa;`coo zt!-^i*<-&>=E1@auu(5RP22~_(hCX-Ad4!wqN$|?a2OE}_T~*;EWyv8S|J$5LPgyD zUnb&VzZ1NM1)zi{w*s{0=^cI?pIDUD?*s+}UD?$)?W3^sGTEZt(xmAOd#Pu!&_l7j z&XH~O|t)`$BdrARKt(cIJa2P{`G-&e~|EgJ5WN&~Uypscm!`BATJF4JEdRm}mfg8nH_G zmt_H}6&C~sVI<(6(JO*)94i@n^2^9u1AxG7imY&R$?uJB^d24gQ50j+6jwi*GzhpH}A zmA(hkp=m<#Q(;F zJ~nFNOCn~(kaVR_`Y}Qu!)ZwB$}T8)E>(N2FkEBg!gyHm*<9%{D?B$_Yl5+glv)`Y z3rHyI>im7G^O0fVlq|k(hf?<1le0OWFyBk(9)@5_^9$YaBTnJd$iIVsar;{L5vlF< zj2;_R)d2S+>{~?NL3A-RG?eDLio_=e*si;%socD(%8amJd%@|Y=X4zp?*6ql*Fic! zdQr4OwKf0(pn9q+H^0<|4BXtx*Cf8Rt1E7aNK4W=RzgCL3pzSY0uj(7Qc;TY!C6v_ zZAn`^C6jx(8AF}6MNB z3t`MKL{^@Y^FuE!+M6ZQ3kgD2aEwtrpTfoUhM%VNpX-P|p}TlKXA9{QQb^nfAiR{~ zTU*RS_Q~!spCp_eY;}&%oa&w~-fqC>b<*wKd}z_=8KqcyKMY;S(io<0ki@M2>d^GM zS)9TdVXt8Advh0{1;#jJmq7Z~xX_Vml+#)WKZakw@ZOYnc8!a#^4ht%xec=-co8HwfV{+aQu=Ys^+01;6A)cQ7a{N73pI3mw=cuzfFD^E z;0_rGvkzm9k47(9%l#c1)NysshSutrVPK$&8@dT2T3`@ryLlq_x<0k+xXN0NG}m7E z3zkgWSs?p39Q+7`xjjnCvCZAo;@UM#*NE_NIh%iK z#*LKV&tjtF{H6K54Qm_A;6cm<_(zMd9-a&)iR~xEjqs_dsE}nXMJ}CP5UI z^=1s`8!$;LP0UUXL;b5JvBkX~P{zW-!sEw}@9&g^UxkojoM&M2$-s=&)x>`pfZ7Mf zabHxHB|~ZlAzQq+ILYNnzY}f)7NSM3UJ2z%vn)I+X>Q1qKCv0eH%4?$PSfuMil6hX zxrKRordGbO-+ws(P5B|SsL5I`8?gGsX3x)1eqy43CA4%T?%gX(`O$zIj@c=QNDIT4xHc`Wa(Kp72eI z9)Dgt-~9gKZXzfNU$=71b>Ni%lFX*cX~4EAZtsG_T!U>5%3pu)1X zv8*e%=`5}W2+lULT`MM<6aNnC3l`kBB8XU|WO_x0w80Jxij7T_q};UWIG>Ddf116b zy^eaNv228z;1~)EV>s8}#1;s)$>q2HGNpJ@Vx4=xxe!a()2C*UyNO;>mzqBW*h{Mg zI0+J~pGIKCeQb~UduUF{Dj^iRKnNL2j^HPk`QJ*{UF^tot8Z{*v$?LlcU#leTUjFz z7Hc%6{4_i;wHcb9@5~)ZNlEc=*-EMbCW1n?#i?da>YHi8kB(S(VjXNynUi_n46!b! zm(iNJ`59YPRnUFjv;4R*k{j#FV#o>c|G$#QTter1org=b#=h&d{y%gc6BdsdQM~mp z4FO(6yF~|d;9LyJG4P9s+tOm;VHND!A<3CVj29yM^R3ca&_O{qfV=XmWt@i{WAn zD0*H(DiOl)SZ&PN5E~{WoLmb9tmXHjIcZMWVjc!t_!@anf>5j(C&bx zdwKc6UA~8$_Smt98INAoXQKpd!A;UDI-x)N(QrPpL@G+(^UJ(L4(CS@k46HC%R$jH zwjRh^v#hJ6RRPRJFrJI&l27JZR&p6J%%J8x|1B02x0$iH_)Qc&-vD7^atZ{d_{U4_ zC}*aj3K^T+{A9%db(+_bs=SGgIU$6aYhU~onPb=l8|fEkul;^I6>Mr0w@jgtNMTcP*SH^`+Al}AuR8` zurq`dQ9C+)J=(MTRZU} zPtd~PBZy|N0Nt7uEr9N5+kSBDc)|kEg2--V4z2izw9d3FOX&8m!G`@iC<$7DkC)fz zsd2D$D?~VVbcc+s@*z=W#=mlouC;3b3qXUAXE@)xgC+QW!+;N_-mLrbW650^N%r~q z`2p`uR8^gYUffM`i+3v?bqe>fujj4=>(6-Pfcv)z%%_yE2~oG-N$t7KTqD<@lAnem zrUQpaVfL=BJpPKdWFx9-#@$|ffD=5v4~}5R#Lu7bC@@NX{(uOVqW>x04F{q9~r&x_oqqDP`8~j!c+&$yXddJ|!3z^$z zKSK~xqkudo491dn|AhAw0aJ!_yhVrZKbA`8>7+7$AQw`T0DENTYa&z~P^v^%QDkg` zXCP4uhhibZx$}S0dP^&7>$uyGnH8yT>en4bg$Z)!F*i+F5S<7TA(+*7Lgu4*GU)Mq zcKxR>LF>}FE3-$(L18ce%a5~na7fsDr}_h$9P>I~Dz{-vadAPUI*>@geZRse+WQt`r@}vHj@lALvIQPg30e{KX!D0U`l*we8d(tx~K1@_qHNU99w+`^Bx+i(RZ$_A@UDv(S`IcN)4r=29E=)EXaD;aw~u6>MeIJ!~c zo4s%`Clus`Ou$;1nI5CEfR^s4S|3-e&aQ!Fk?ns()19j#C@2*SDH=WEM5|dMUBmu7 z$=T7-47I1(Fxm<|q{u9UG}uQKMcRc_Lo*azv0J8$TUqF(cH2MU;o3#JJZZn)Dr?^hkKFxg`3jhs34()pi>li0|LR}8?_pst_GujlQid9i+!1x09>Erv+6Lgv*gk!$xO3LYOUy;`TC>F4R6;o6TCAGd?%|BDqJNI_Up;JKYuO&6x&W`uA2gyz-$SQg08^$yC0tW5B_bzCO1B-RY}U1{$Y^*mW{p+pu-c= zzIOkc)3f`3YH|O&2cWyJU33aP zgGbaR_3Ou9p}zLG;RM-AI#W~ot_iO+qb#AeFizfel4*E_j zi>5F?Wz0D3+RzEJVkzRSTnKP>Gtmxj6|L1cv3cM{SG$|ZS?~2RAbMv1(L1RArkT(R zTwwcethC+;Kf@qZH~(0y{YR~Z5^YahNLqiMSR1$Umg6nZ*prop4_qzea7B54?V9|B z+O+EgH!^7We;~mdmL1N0{r{?sp@M3QpJWlsf>O2A{ zzvB>Ukk>@X_R+E|$9n&b4{^ZJG}$Jqm8hAU(xoHsQlCU!J51v1nCDV~>4DC!K6SvKLb8M$`oD5*aRM0ZaSA^j zQ}x?K&@1}EVfdU4JH_fUL9I%Z?E3X)tJc(184Pg6GExzUefJl{sI~+ZfCTw{m(zZ1AQaz~@jYY2yd|PKFDS zJCWa~rpjHRJI)xSv&#tSnqkFcCU?I&1b(Ib7JWqON~&7n2ri*ayJ(cW5QP4+Ro_Li zW!v4P%CGn?mv*SSOf3pg$)qh*(9tFrDC`~tU$k~0$I9=)UT_|Jfz?^N@=PIgwf5XH;o2Fh#oqPU!{FIu4}~4JgM4~(N3sf?hn270 zrH)(#6`;0>b6Wo;kqkSg;3sMP9Vq?`+=ZfiQBqpVqG_@w4O!zdWIo6xbYAu#?35JI zP>{7;;PAnjksm*X!Yg$5tS72pS!!e zdj-V)Q0;%m`Z43`O(8jDim|1_R>KqQsz>LHelRzmUoQF~xobGXuxR6CBlESbaUl&a z?^t#W@kNLXr+1Im^m>u3;1J0s>Bc?GPqTNofsbs1%AJwwrwf%MvTpa;#6ueBDLUzI zz3!>6K=$b9mQv>^7A`^M%+JKHOLyVqiOt&WgfZq!j`S2?%gl!pn=LFXss_Dq{iM`o z&v^V0bSNzLTYjqR?2wp1jADZs#~UWpHhp);(9NUJZxeHyzfd-K6iM{G9W^24GLpx( zZjsvZaGs=4dr3b}y1ulEUGP#%zKEZF=B|`2>Djp0WLxnZVSzHZ65ns;R6M^!4^>QE zEauwqj3kvr*FGYWC6YTcu*v=9t4~DQrX(eWj0DDV@O-Zm&S!p^k?~sNPD%Zk*tt#d z(_(z!SL99XJWI2U-el~!SL>ArsVavg3CZh@QO4Cb7DTEoZheOjs5EB8=st02?*t^yaL786ME06T(DOVa+?5-jD%TC zw|w5~zexH%hmhEaj)>5dg5;Tm*)dUa+-6-Z7WnMhBfbR_)^en8L!ra@xZ3*qwWJUB zK*e>c@14z-7T7uApv8XAtDSvepJog{4FJx2>6DvsJZRoBH6a}c@C`TNwC<)p{@Ju*HIWetXGVs4n}+}wZ<$Op(QC5T zp?l{j7ASW6Y|WThTK6cKU!M02$13-bpsU~KuwCV?)vgfYPUNxIS-Lc4qtgOSw7z(a z?ZTlJdq~g9idoCsy1H`u?J3+XFIIgzO*ZoJZ#ENSgXgr=6&1}GxU!ahrcd!7ox8f9 zic}T^^K{*`{loX74SWt%Dob9~@n=nej}(`sZ?^8s)Q;gvA+{kAKXGlsqoTyJWLfBl zpIG17%)@~kydUI^Za;Q05Goa`gMr2eww>z8g*msMFD#OCN9-On+IR8O2*(=x03E>N zI=zRa@KbCQiyI&rz-MJlmB~+G=h3SM3(pUtc`3rIn3hg#)g?+NNPG!%@S2hz?)7pruD zJ^8@IW9ZZGgsTMa724uT`62<8`*FftUT>HhgnX;?mb#)jmTGNSgR|IHzn+@9THGB$ ze2Nco4@@!_7mJ>*In>3nV0tv5HUE&bM5HVk4h860%O>H{TH#HM{GS~wi;5o&)vcxJ zrNwS2710Fe8;!H!hyaVBosX}gXLD=!6ZY@7b~!?!3=^s#Ey^As{ZM!p69&vE{LN5` zGXAQrYIadhPp5^LIWLQf7UA>DPt)((Px=w3n>G#EF92Qwel*hZI?vBwo4}ER4&t@+tukI)yOe~RCEgT7YM{we^JsC+J^Ow?|3gO%$e{Da z+#I}EZQ$Mb^o+He=Wbr#)6~JXG20*hfzv-jHtZb@5`1^cnjX=lB=CbTUc8_#t+m%V zdjFGl%=)%FsVs(w@5f`{3I-yExo>Sx%~z+Q;$nEV2XGLz_Pno?pL+*%F`5(F{BxtbxT?geno1s6@Tiul+_?SduQgD)itRzI1-$Q9zo^ZcF~k+0W?( z)d|s#?%-ke>Ka=48QFWMSD)A=84*877)QFfed;<$arp@Col=5J`ts#u5&AxlsaBs` z((s7geAI6nQOvgWF=yo%KE8l8-g?JwS`z#QLCWf&^uc)ZY8zIV$F)q_YqIlbrw+>r zKU@M&Kxm`E2=nSvx))dou@D?CD9f=p=;F1zN8OIwvhMdYw1gDH84w)29nLIQf|gic zd_%|#5fmU$!|R^tE#I_oRwGbUSH%Q6;TT!&IhRvy_p*zzSYnaf9dlwclVM1FTX%Qy zix-ZI^GC}YC|@*!ABEK34L%YdYcub=1umJZZ%sMb*Uz6qG@Pp**OuNRah}C4V zZ<#%Z5+q{1J(|$ObiO5LJ{)T32rx3H8dF0}2gB0WV2zG9M}39}K+Z3btE})n;+NZ)>vf2- zLZss#$lc=Te$*`E6)^u0{_{A|>?B!}owN<%==buOc&H-1vQLEk?iaYOA{jGyWIwTK z#0kp<7=2vU@|Rfm)cnza>FW;V6HxdM2{obs%u~Ym(232r4IC%GA3R#DyU&E!%RD@} z;7~Fw3d0jxjX>A=-@m}DS23@Ngmt7454zjI3nopVtW|Kv?H$%iE(4}!d!AdQZ!k6# zXYu_a64(u23H0xPcSh+`CDM}s>VkNwz2D69qzM$=(f;juZ)G|u!Z9K-MG1WMqpwH4 zIxWJI8Ya1drgZM$s#>xK(uh4fP2|3=+ygoWbKeh{k0K(>e24N0<5R@%F`Oa8L^~f$ zqm@niWzgNz%MiKn*3Wa$-`6Jh3p<6wOdi_kT~b8&B~z+}kk{IJ)T>L8B>(N_&z~6K znY@)(5V~<7Ji%TKy!T+|pp!0ZIidvTq9mHL&6?oJa69|@I4Rv*J34@(W2#yMU{&cMvbo1N%176^Bv638l zVMCgJ3kCp4pAlS9@h;r%MnCHwUHbK2JkikkN7kWu&h^zkAF>Uv8SNr58A3-xAhDK= zzSyl&ho_vy3pl?yrKUhv0W+T$ZH1ICHX(*2_;sFbemTPHOMg004(ASv!iT~{+B@12 zqeZ-&kiwR%TFKk89Ijlscy6*m=Jsk9yZI``+Xk(p)Aoon1;pvem5s#p zMQ-xF)9>4Do}$m&LtCX=yVB1mTorH=V|%E*Rv(g~hD5h*DN5LvWI-UEK&~2XlqZcC zWBCZMjDdV5*_bXP7E}dTP+;;;mkxDLk7VuokeQvZ<2v>m&td{JE>T#)KLpk2-c?lG zOEyl5Nd86|kYpP?qUaVC#@zH$7}XI^uTgWS#G4DHwF&udti8fo{_#-f)7w2c$!+Wl z=+_v(_8jGfE2^q(Tc+-xRFwx{?nbXL-|z4Kj0a$Z=jY}gtszS7Q2uHpStD#gKP_S~jv zfF|F{1D%&tdy`0k*qB7WqK=@N6ZM0oZPB^+m~V(4gL5Y&KGnz~e{3$G!&dB*k=2*A zSE+HZd0>9tMTmv?l~q=L>ZB4(ZI7Ax?vq$B2Z}s{;n-&*g?lHptO%y70{navhc(Yh z`1U%UHCOsfgkhLDC(rbuXG-;GG|4IfWoltx6AmTv)0jGT4hfapVD-q+S+Gmq5xq^!m9#n;W!&d-I}7bdG)vzDogxxx>yFQiPK)7TbW2E7Gn6;)yNPL~FCc=Wz zo_dni{uI(x+xiolc3)1~>kKy?kSkGs`QpWcSd)(2b`}qVRz-5Gcu-f6k_U0FzX_E| zA2xr6kVorp>Zk5cZU6qu4S3QwBhxG+)PtC|aktpp2LuMbt}}~0LaE=Tz__8=Qr`!FcCv-C|PB^x)!2$6=1CEFqmww{*{1M<#KdjawUd zTBl{!t>sGWx{p@1%S=Na?Z133|Mn>wo_nTXE!!M1KEm0YpAD*d`mB#7WVYtJ=)&zWxVeSBc#XgN+YoZrr3ekJS=hPi8H035b+_O)6) zTg3OP`lELK&I%?TeOZN?+RWb2uwV(2W`Fpq3tY3G^1PMHQ~Y-*HFZQ{V7;{?H!f^* z?aMsB3pa6=Xue0PJ@og800%v+7VTXIl7Py8WNiG(={~3Uyf(Vbd;Q#isz$b@{B8_R zJ0(pSvXIWBi84~BbzbcHww<*`UlOA>6XBlsU+}>FtoI=`{YHDnpHJ2nKC_Y@I+{-U zafH@*NXu=vs!aJ>^fh*X_t^zxW37oc8r-p*=61TrvU4pbKan~OXPHL=U5*PbO$%yH zI}jUS$={XFpg-G=F}?Sc`hMO^cTV5CL@}+~k({yLZ-FILoW-#zp8Wtt>mtwY0_WHcknaA@-Y#Je}kI&7i!QG2Bbv zhrxZ&)SMxxAtb!`EO~Y3wW$u53|qfyxY9L~Q>0FH9R9P1 znRD}%&8s)O+(z;i=wivSEO-!YXHGt?wCacWoMkF)#Tza5Bm&z>zx*!%UP3eA86jSI zzG0nC<`MR``>O-tuc&!lMv8Pn#I>b^w&J8F`&@Kv>y2-pMLxz=OnP+EWZ2^XJyU;| zfSxIu^tx)9WBDI$E9olEWLK(RpgxA)0Y-!W!<-L6x^BFG8L;Xlb^44?P95CQY|kG1bieUwperF*)cHi|E(H_8u`&l%Q>F2F z)be^z@C_EF?Ont!wFi^o3TJlwG4_> z5|W8=u_rlJccalhRKuo-Mh>?J|AE~zRc-!iq5! zjr=tBo0P5Bl?Z?f31Dtn_>MjjEib}IFAkeoj!k0t*U-7fSQ3ic8!k2>Wy9jWy&MT zLok2pucMTQ`VWQ4A4I8FEnIHIUYDUl6pb2uJcMgVzp(Naxy4;)Ro-mg*1OQ>%#SA4 z&dpI&s;=GWc~>#dyT0eDrk-BQKR0=Y^3kr|jghBvtX>wyCtBkLobJaAY;A3w$80nL zZ7m7pv>BQlb6@S2I3l8GZ`Taq$ZY0PA@bAkZYktv3NSC7rKtfD(&w-|KwDOvnW|7G zF8ZnF6ALQ8&c3ET<_qmWxc%?172B#UC@!$U@Kd2-Tr4aODZ^7w^CtV0Vkd0*`_w47 zc?yI>m_`$VKelC7hUriV=dagq!-rGXU5&TRMKrM19?&DCL@mQah=s4z`#OJQ?)-*; z?dvVy0|8B}7OO$U_DIfm%d@D@yNWiA5C~@#GPoDKk)W3FGo+QNHf+zR;%%~xxK_wU zK?=V!W!x=;9CK=hvh$uhN8#i_dm@xti$YArIZHlPH3P%J1X7C zUq$@7Sn$m45NzUdey;ty!UJ9gl$FWHdF^%pGvvN#M0#0XpvG2Qrp~^LL)K1k48P9G zU+-QpfFDA(<@AEIMz*`#GZfue#Mq7~8v59-+{)RlqnX zJm0l__c8ygt>iCHpb*r)A5E2B1%M8{>qpGXLo{n&^hfN?HcE#9;aHqe@x+s~v@{sd zeEdRBdZCULSYPriWM9H5sx3Kh#g}^Sg%Hc!&W(49FA-99e1P9uoz!FH-HTF;Y4wyk zGjx&szUd-50?Yj@dn|Sq{;_$kFovB0`RY@1_6kzD|)KpbXm6;MrLS%*38b0~oMv8*6M|J@%$icoq&h}A*S+`V-Os9U`GP(FIG zUhE58JiPF+uW#S^1(E_@8u(U1(!&?SIp!*u;4g%Rtr?r-5E)_8wvlKM3?=IqFY5}m-#zldPlh9H?!mdpVhGghdrSi>#UZ$hvP zR2zTOrjpxeu7RPqla*Db&A;5_dozk=lagYE>$!{=;rLjCZ82uNzPGvh_s`T5;65Z-ki9Qq)}4)BdpQwW zSq@o(+VqK_5lc-<;#^NFDl>4x^Zwb;XD9u7-)k#}g~J9HGXsrP`j#${I-Sry07fFH zTTxXFj!5zMQCjLH@F}bqFfg&Vw_haQ6;$aA<-b0C3b&I0A=Hw5vLVI)kO`UWy{??N z-oG$-RTs#u01jY+u+8u5zaYUZENXM}bDUj-^4MnCfYxLFc$cvBfAKN+9w|^QfaChY zWDB;8k2N*bH5YCvOlEDz(P6biZa|Z2S#vDuF3sLJ&{i z=zaGnw40lZ6%rTKk6vkK6JAf+27M^XCjdeMf~v0Bct#=;(z;S?6Qv+q(AvRa3D-+n zWYRi7d?!V2FkmV|A`SC_i3t_Is3(b-?>$BSPI1^?XVV>2c9in_5T!(@ z$0Mbd+IIopeyx8Q_7D9ptBxL)eEtCAjYWKG`{ErxDK`r-wri;GfWjNAz4O@Ddtn#X zx)1+!T>|)qR}ATJxRq~Jj<>Q-3xF&F90R!x0qU!}jH`S6Y?hZ~JS9Lx^(+?}&kfJy-{BiAMWp;P^!vfh^d)ur^_lHCD8`_8Bb)E=XAJ`>jON4)*yy*pDjcl>&RY{!rZ z`mq=-V9+-h3{7xr`f7J`+%xbR%Z_FLBBFZ`e6z$qwVEvLFSp^iPmjh0BKA520QBX{ z7wj@qvdN^M5h3w20K9=DAKC{wx7UYE2n&*u$P9bUeZ^`Xa=LWnLWhrjy{@hcm?0oz z78?Lupq8OM_wgn(dmU4aeLHJYyIExE1Dc^PZ(3N;ZNSWEo|9jj}!z!I;IQs zjH8c?4;=Fsb?fu8xGi25Pb`Lev-U1c!X8J26%sx{)3y;QCss# ztZTr|hUi%6UDNcy-cL;(zST-GFQ=-CrD^t8?;SUoBf&^lIP-pNarXL(nxF^|vuI(K zjd#EVOoN$$?_Rzm5mu4hR$Pwx^`JHv7ZYprl@8W2jBw<<=9@Y^TO{e~f~J?-`iUww z)yMr#FqExHFrS5sG`e1hIsVlDk+!x(2f{@>2gKxjq4EBM8e?(czrW|F_B$ail{tA` zcfCJxLFf)CcE9(+RsbUlXi|(f49lGFKRhU2gaUHA>gf2aP_Y5=$tC}~ibw+{6q(xm zuqD_;8J&9TOJuro7#5TTaaR(EyeY^om*43z>T7y_K*@}^)2RE*vIF>;yrDQ3`_9_$ z%`yyIFSkUrG|R-NZ#PUzA}mMXnbq8^=D@cslmEAWI*DWp_2?7ys94A(%AQ6zU`}Pg zG+T6i@^zwRhnnhMLF=!_>~+wf;^;yx__XRzpFZJc;nn1#yWag6#PaA`q+1E9LnBa8 zW%tpjMa*c0Pnow8(BqNjRM=-CNQyTPmv9x0c(STTLPSzh67K1I*TH(aEqHa?Vq$tm z5lg_!&B02fTp>lkL1{KMNw7M~YKTDF>b2PilO8-B*%jjtgA40R^Wt86%%20RZO?T@ z$0t_3W$3BJaM_~M5(c1F7vJVqDY z&F%%3&?acwfo4(bpOuo;Vm}}^<{BLNl;d6(iw&0$Nr~w8{E-PPF!ZTeqVE%*>3Nd5@V3ALd5?Epr z0@3;i<`^{tQluB9%d}UaS~vp51gW?HZAl(%$k1+WOYxu5$3g{ut>D)Pv91QuuAoL( zAoAEz@OSAE7xk)RW|O8a-FbO}!}-mG7zCbGwMVr`f#-Evt{zA)|BWI{Qzz=s)!pAZ zO$iF9_t%9DT`0aZ6Uwg`U3**InLbBRB{$xDA6r7j_`FFPsibRP zM1at4u7$Dr?O=_=rs(}IU#73Or7<8b0oi(7)!*-f^@c(Z19A&Z`!WqlyYI0) z-Q*+-C;m7+=WC<7*NJ<~_J?G91RStycI4>?GF8y(eZSJ4BQT`Zn|VnOHpJ69v4-$cCgpM{}*izK{HIBav`@LsCg zmFsXp>Iw%bA7ID-4w<5lX+Z;lF!pI`R|dRfJY9-Lrw?}&nvWx$$cX@}i^)()2R@8S z$hT3{F^IWeM8<{mmXq|qpKOGgM6Q9jGp}2cw=Q3D{@tVYGKdw*h{@!C(3K$^%WXvo zw{&=uR1pLm4Ywa>$g46|en&%IwY_AdM~n?K7aAT8UsJFUg4vW9XBk^yF=~K3>noAd zVt=&ujYIv8=er{L$9*i?Wvp-3R0B$AFmK%T!lV015&5h@x!_9etl!hwsy{%z7I>tl z*VJQEO9wau#em#VvpDu>H7|(?m9NpIjvQxyBg(ubSrAKQ_Lib-+viw!;nf@QpnDH- zK3LgTh>0o5v5_BZ&u}&^yCU!O3(KNaeE!?+W$T%B$jrzEC9g5zdvc|lvvcha;vqQt zr&GWd$FeyQ%B>ActFoaRGTeN`%HE?io1o06?$f>JLC6z!@+Q2Wt3Ax*>EDH2MO(IW zPwcYOPQ;B*G`3)YXH+=yj0SuhNX4r0X)?A)H+C10U#_f|KAfv>Gy)fRLpeuw4Im`fVqncOc#R^Arc1A_JJ?&`uC+SzUJLt121}TwR+8 zfbJ#+u4+k}rux9F+9@Ayj|Wqga*CGw&~RbDH!q`I&FZ*^*B!9&2Ca zg54|-5`4g^MVq_j9``QYy-Va9M$SA;I;NL?_7U$2;Z3D0)pymp-U-V$2L2(ZnYAvx znZC}!`(e^Zi5YStVEBileL9j3iUT`{CD$?>}sNMFel=I{KXS16#~q4ETmq#%Yi;%7YVf+nkSI^D8^NH?%7zht_h3`BE{S|yBP!n zenV^HeZ>330A*Lvd-ZQj0ol3Bar`$=`#%u*`6}HhJ{NV%0tZfsluC(4w-A^{w?ct-8mxZCoIRn%2T zQ|2v_CVp(P18>WB;UEs3`?6o8z5Sx0rne+UwX0})i~XZV9&W~G0O8>a3jZ0<>0{UY zuqxv9e{)P`z;lbyD?F?*?Gs)Twyr9HoxYXKdAxCb#+<}O3HmRA>lR)2FVmm4sZUNS zHYY;sZXVAg>Ue7Z9!*rP-jJnxC^(%{u^ItLmN(m%Kb{&b{&ix2tLrx&`1}tZ2-UQ( zB-5ixk;to)mDSX8}(a!~HP9kHr2yr6|W-rPo!nf9U2qeiUrN$(R`O1mRLSbPFIRQ{<@ z%B1y`n{&;Cj%Um=e5Jpf-?Gul!4umZ%)GztoQbF`8vr&x{@`n&v!>9J$}bL~qctNT z^2=gs?*nx2*GUWazf03>2QOC4y!J2qSp0VG)lj`!hsT$1ctkW-HJ#WV@^0fc!0pIw zE@119OinF6zI~MLy;VzgQ}So7k@$VIUF=^9!pd6_sfAx%4v3<g%yKWSt z$yMMj^Lr*99?4b?Fl2am^OUJmYVm%RB{5fg*O;7SZT5ZbVYWKtI|uPL|NTyTyvuNr zd79>Yt-Ff6^;RDM?iA)iU#X151Y>(vXi#RneB*-}g>Le%a0|P*EtUKFVfxiK&%Jcz zDig$$cXEP0-t20L=)sn3JrD%I{Kkjk?9G4K+({V zD`+r*Y4Xc=9+GfSd8b)N8;f#vjYsKMhf_v%e3;8rYEFg9?9zaO@l?;LP(h8#$j89= zf6|+D75$!3v;SOD#MA~|*@97X?p0XB_s0TA3N%7d>VYn?LWLGjF50setL$!ZoLAH*j}$s*jc0n*-TD}L;s&W!do8_(#F*3{(Q9r4QfKezcVe#y)yiTU(*du< zM%O#4;XL&-w0NbQKhsCZNC|MAXpeOa-lK2;x+NU9N`E#wg32lyUBBI@uQVr%BNN#R zm2I=B4nnIMsFJ)zPo8A5uBc>22pJKgnh-kW)OC2^)^vI9)j_Bm@2IX7-bDL{A{vPU z(~r9efuF@WE2{%L3F7d7sB;Gz`duRf#!6Bf<=_MENL;S&dz9#r@#`V70r0cWjHNQ0 zwfd1xPP6M_LcpE!%Z7}N@WhS2&C9{DSbBI&Lf8JT?Dd^)PL3>IK$dqHRtv+|fJ_Z* zZj}hE1#U@d4|G6*<5*0NJPJ`3r~#cL#Grawdy#4gkw5=Kiw&DtGT_a9HstMF*O$=O zdg@s^3?0)&;QY!$=i6yRa^z_nFpW9n#TACd@997MfL=R>3=n42P6I@k#@)M*AQy)DzR27V-^7@ z?|vV7lg{KUzw%x_oWJ|^js7-P4Y}Wadc*AM&%Vjvnm)#I^#VE^KN~P!euglP2fG+P z=mcXOJ+pNGU6INt9tp_QX(|aGz9|F zqM|)jG+pA)-HVrD6dAiid#r(}*&;gGA?%|7VD2^7uzx7ifTn7-9vVBKo#)he=ypd! zOEcZP`^p_bXVt9*UzhHGSXSmk)g(RMn<(ei46~{8fb;;kdI>3Y=9j@sG`~W#37jjk zu)9FbDRu6(w$`kWY~1jS!f%L5^Uu<0fY!7Yuw}F}iTM#~nFT5o8{Ezx%}iKEgR_r> z88bY5jjm_J{8&3PruUzm22kKhN$Qg(;`aCwPRp$i^qd@y=9yhdddc45fv^IH;+-3^ zo3w-UyNZBH>ajpc=8-XNi9eIRt~u3Q5^8%%g% zBcAj&;SEYgxGbcBc^_ro6^R4^!+IWe7D^Am_{`&=C|0L0@kibiH0N%~&74DgyYz3) zKR{;?`7D8la3AmO?%wu%jS@PpmD9Pe9k(wgOWc>P%j=cDXI^^*J6l4cRPBmrs4u#g zh;wBN{_-E0Bns%#dlI$xb9smvim`5yWZqPthXCoFdjxK$K~SEY3>ru$b-)X};N^{4 zlk{Ty)3}{3v`o!`fHG2UPD*KlINieRDlju4$@QtoOzarx(M zbC!kN@4Z0R^R0z`mS3^bj*)Hs!;7ZvOggD12uiTe)<)zKQ(m!rq ze*GZnr>-j(1n6g7Ttu}YCns$9kfAr>y+uUCr-AK3k-t>T;&*Ada=}S1_Km%gf#&C* z!$=1O*d{Bk>R;LIuh^+s(xrx5d=wgKL0r)MFo%ukpPoF;2 zQAltlB{{i0muFd5=&K1`A~0?T&_%syJ%c9t6wv3QoROV67v@=iT|>K=&~uOO?Cfk% z4V}H>{xi5oXjE_rwGQdkHUWYZX^fpMKu-`FFV8W3=rOji7@PD4T5*Q$3c$61`C>;@ zkpm~xPPy2GPA>ISYWon(wt?L|oVnouq$+1`50riyu9DR903W*g%?pjpYlGMDl9y z!dHmw0wLZ{6r*Vy%$3XUoR}sA6ByFo_4MdOTK|8Q=z1(T zEg*woRt;3(Y7QycpPKy!kA{dR4lG3;_%oz)&(AA7TTbd|m8}2GZKMbyMOiRNF-zHd z!ZAJ#U?=!~1yzcAG2B(Ak8x>S<_6pKHFsVu4wh8&Faj(Q-#lG?O2=LO!}l_US*04G*Hit_27B*n9?ASy)?*ape zQZzyvc=O8Pt|H(@a00vt-pC}k>|0W*Ju1gkDo|ILIDkoccS`+xlO6ELUsBCN(=$hjSBpJngikm zHE(cNUIB_Y<61sMq-Ei$VAGy;%T(5=*ugtteKb!T5HMjv0RIJ^_198j6#BV(Hjefk zNv|~lp#uFc$T-L$*=ZRvj-;{VEH|b+^&L?TwLmcR1D0@FS!-o-IlF{#(3k>Lg(R@A zTW%Rgr0|&(IK(4!8UGTn5v7sUqsqff{U%w@x}jI%rJ)f*az4!-w$ehKB7i9B=hfrF zq*!!!Lj)7gmOTP^v{cY6T`Dr!IwUX|^lY+VffSgUoDqKYR4I)Xm>|N5FDkXvQVkjnaP>y5BFD#c+z!{C+m;#EM5R*k1aEpT?SKAXRM-G8Y)4VJ10`aIdXg^h zBX8}T5dlcP17GeK723`>cioQe)@e{h^x;TX-Iwz6mSE7Sx15tuvr9!@zW1pPuL9V* z--pAzI=$cF-*4B%n6NJ94Ocq{>q?(RA=x;l={J%0hx{Va#AMoXg*Cf{-OY-zAo>}n z*k0t!q5?fxG5?o*7FeAoZ>f;#9HhB0SJs&5B*)%@I)8(4gCZNztJ2ZxpvNN9+)yq9 ztvxtlN66xdtems$Q~@ydtq>HvUoCX`rLRvPr~2kuumcc1et*Y4baYsJ=Xa-c z(-esA3m|#AF!Mt@Ww>wrEn*>W8E@3TTF{plHS&Ma_+~IXRf9nNRXbkGrEjwi31#5J zc9-uS#~7pV_VbYlb&c1%-skx_V)^m(@^?jTwO}I4{T39$cP@E+05PC_A7G=n(=Nx8 zx*l5{TR?TI8@mF1do_?5KMCFWSWMm?*CUh4xY`eqQ zJC!0BSx6R#>^PF`;T7133YOa|!7K>h+Bv)qn7?p;yuVUmQwXRc38!nCLN4?9W(#xT zfOauCU>rMsq9OH7s``{SN+oS~m-Pbxed1vy`MJ<&!V+;sL_VF>8t)c zb|F0FC)d8k9&&A367Ttr76pe0>fMX?zt7E_+aaypGDyUu_1k~;YB@@gSG_^#2}46V zJe-Tk-N(#Ct@qlpY_rU?cWN!l-m@LEl-Ic1{r^AZI;2M!ykD6V(|?ILPi14cXdXPL zX1ULSl|s?jjvCr5FGL(O3OTW2yUBT+@!?76WMp<~oZW;nzN0$C$O5y?n-e4ObfJEm zfH#$vN~FY$gdu2i8O3QyNF6$NhIU-N*RlNJd$u z89Z-V*s=h-_| z`hbLM(bS+GsisH;Jp)r;r@ZB(oO!n#@wB>y{Od2URsHtuPt?2)9!3M|y*z=eN80=SgBak0>rz{j$_Q?sktx zpYFOkyfbTG_WGZDCC(03(tSD8IaVmZA4C$7A^(fJh()RG6vKawtIQ6f8u9*g*vB^hOP z2Tb{7YukOC_=B+l&ZqlUsr+sGQgNQ}LaFA3krsrLd*tRg4c#QCtVcfg)Y`(0B$>)2 z7O@Q>SP2q8`S+r%M(baN@!m%)9{oD+O%CyAz1EW0Y)V#g>=bT`8xq2$&*Pq8s62M~ zCYywp=Jv+H%n3lmk&Syx58u1WB_U>Z^*1=ObkRL-dthq8o$`;ej$8*++kUr9t{^`11{b@UIJ3IsbFn%(_2wWz4OfE-A3Ije2At7v8C7QL0kn)adKBCx^q zwz_fT#FmRqLvv~~gs8qH^ZM8AzqF6F?mF1ryTX5IiR6y*w{{LUeWa!Q&ujG#1t*xnu`J!+IG*r+kC72fSr!Nr8kuDCRIHR6 zEHxkYADdY71o0ormpR{e#Y2}eMrAg8<(kKV*OYnspI8TIMc-5A=~ zRJJ&kN}aHyn^KRlIZF~}IuP&Ys%gU4;jvAKLO95AkrQ@5I=AQIyH%v!9fXzd$2lks zl@r5Wx;&X%kTof(%n<+lW={U=u#bBK_3QhcOZ>ZBVQ8~^?c9;(pN2UaCG8;R4+rrYC z)rYS7%ceVbWzoYr`mKDKe2n7w0e2OfZtxGrb zh3;|gD0OhMtRkc0-iSx0a%FS#xw3Y;^UJ+sM~B9|cOUsDp6>lx!X}W^^wXc<6W%Yz z;J^jI_Q6@&O{%6C1d^i#ouD^PyM(3 z8A6rTG2}HSDDI z6Q!us=tR;zjs@O+Zd&9*Ou+x;iO#Y)KGMq`x)XC;ks0m-bhSkWSwdn>4es<^B`*KA z;Sg9BvAILN$tHwD2w&;cV#ST+ve8c85=0Wt$TkH>wk(OMpP*}86`0*+bY0v8z6QG) z2g3LQ`m!fd7#`WG6w=o$!s`Jqn{P;iJ&slRe0(DfMj(l8LYmccs+_UC(mfa!v>guW zwaz({1{2FW3s+(@H)mNfg!nLpi+YwTFo)V0pCw-C9ZXd;-vV%SRQ%t!Fx>`9A7#iVZ89`-dmDs?XPNu~8{fQerMo3Vsl=b;XCJQ|~5bA6DlHb4Wmo8a1_f{n9~}RlzWYkJ5dVFZ*rDigi!$Yjn$j{r|KoO)pInh zvHep&y+>)mU%)^mFq`;=t$V3Am0!rul8gc$?W07hj*9R$EEGyn?SYP ztJc|DX~;S;kqzUM!kWZAE_Js^9g+j%)9MSzky>r0e8>z+2W{q4`OrkNg_9#-OLoNk zIDQo$`TxrBXAWI?>2A%qFSBMFJqKn?uovz@HpWoPJAUy>yi+dZb@f-omg)euSJ;NF zTD6LxU5^I!ZC* znWHDBlE2kF9zcx_AHSYC?t6yqquih$_Uf#Lh0f=32EH4Yev`@0&DC@~MmeO%;TFO@>S;9owa|Osj+=T~gITA)98mD_>+h659fYS6AsFIO_qN20`skUS!WzzmZ zMiB9h|Mny&AlP8sce>q@MFlmMeL==C@~~C(?DwY_l+HtuWo znIAib<}~W#t;AOzSVZd_i^|J${#~Bt5O6$WSr}&knmD*Lj>gJ0Ox}sH&cD!0q^D1r zka||ihXEZs)@MwsoDV#B<+xzfEW7ARC1X?5sHcWdgqfzi<4tc$UuF`6yd0C#98E;5 z9Y!&liHZKm=H*<~dLv%g&YEDWy1GhC+aM@$UX7-l`y0QRFYM&vqT7x=--~nv3uy^R zr4>fMAH#b`_MBi8wH! zNgzHA$u}2j#X@SV^{q^HY8%Ku&#|yazDGMr2C`&TnGI!DXaIzg&(?e}u-zW54*|D{ zC*OYk0-*=O&v5a>hnoj@bZp4TOy9fSFSIsMKs~wqPS8OvF0Ru|w1j@8Svxvy=d%`X04o$ua(Z2$42U5u&Pb$SkN z0--^~b`qjMPa^Z0snc7Trr3O;W!AC!l9Df?l8GO}ThNtXP=M(0^JmZ6vIh`7udorQ z??(J~8VWHI2jmA*KNI52+qL>yOaBG30CgT0q@YulR#phu2j0UO0GEJ}hS1;+0t_x6 zQ%slA*KO+e%4t}7$1(Kqkt3hzct}T&9+k$=zJ225MCV3^+a^PG^_Et`OTe!=&CvEc z93ZnDo_!$NA$@IiV%UQBVDutQmF7NZ1I_j zUy0E1@1HEiexhVFaRYTpqcI>!Ou6shv-e*6mYK|-9U-JaVarUGG%^ZGKD4FD&p8yj z;#w(7#AcPDO!l7adhRGO0ouB54{sr{6n_IUOXyCZ|piB5iN_JED zn}9@ulE&&9J@hq)ZF$I4C4Ud3m#T!NY9o+cy;X){o88J>89$MCescF_|Jb z=j3EP>jIUk3xx=2`0zm~$&ZO-fYmzzxcdNIesk#%A;pB#OUEcFnTTR)eQ5owBCHP? zM?Yrf;D^AO`&%p)+Dks0nj=Ekf#YKI29>YfCbtRKdHuB$!yC0jkF(?Tt+v8JQk%iH zpaoZFAH%m?5L{4HBhU%Lz57IBl7Z1H$$B7&QGtf{a0ScC_8NjQI~ z6E+q>k*O9c4?P-uJTQQ?FRw(OsAj@aS6|@+*s)_1KHz^n#0ussSe#ytx?VFfLfaY(&=O3>2&$5^K!nGnH)Z7z z-E}{a{mg-f6m#c+*8v_(RiT^ByLxqL8>eFF$94FW7V%JNX$^4zL%Be@UAGEa>K@$mJz?( znx#?{DFd{hS~QbP`SdpA39Cn1*oU_6ZwBh`I@_SQ0DBO;2n`FYBu^?Tr9m9($J}=W z$ALaxJ0j1wbwIX7GMFf(Mb#goO7fjcGdqZ@_hI`Y&g2%GHiViG7M1VZQWw*NH4E#0 zru3~@U3DnM$vQxrU?5Fnwr#qBHURJ}@Nju_lg(HA7lVd^z7(Y{%CqkmhoF3(WJ zd+R1~DQiQcE$Y{My1P+y4+vI_X_Kc2spq1kHiCBqq5?0dnxqVD+y**!ZC0jlGpCt_ zML0PHvik-qC-IBPdBPPJew{&HvETMO38SkMx^}vLWP>j^97Fs2-l8njF%-h@4Wh*U ztg>OzWc^w5b9;s;+Gvy2-k7ybaelga;FnpUZl>zrpQau(pk}Upbbkg9e z1_9&{PZ7nPak!Sc5>2CW9(=uM0S`*%SHHCR&_I)&@k?VG>O1mB!%vhPpnLT~9FZ+G zeUr1RNWQ^9^|j*oxz>pXlG-*_XbKqjQ-<51x{C5Q4uJ&-ElNcd3o}OyNCxrE(r&o2FBYLuxc-G_^&f6l^9z_zv zvNpy#0vj5r_)@)3o<2pF57rq9qC|v3W$vFlW+TZ-3{u&41MQDB0 zdWhF2ivqt+19kIq!;F6i2Z?Uq4~F(6X!HpToarFsxmtBUd5*^R86;sxhgRhbE$9BVxe`bkEGfv~W^#F?o3T@@StUx*e}7`w(*9;nC6F{+W6S zUx_p;ne}B8@gF487*g(Vn;knIQYeUD{{;#Ncs$pqSp%A_01L{q;`zd8Kt6MixILwb zXlH4l;y-Izv+(=Rgj*ypZyubQY0wHDZoSuljpU2Xtyl5Z{G$)z;ab&kZixF!li&Cs zE>tcgd+X_cso&j_T!I-Fo~3`KbH+SKo>_)Y{JgcTTfRGHFUwiG?6M!Xi(FlibK7Bc zr_^OUnojPhIKld}<#(Q&{^E9VZX(lHhgR*`DbO5H%Yz zHBT=mwCPO34hY-4_dzD5y_r8B^Bus2 zOBRQyNfePspN!!lGBT6=Cz;{MG>!C1)RaRq9tNSOv&^KPoUE*!nJcE%Cxi^PZFp$@ zT(X`}d>C2`$2CzXVd3H1FneHzoi)04fY$Ap}4)zI8wLl>C>D4$ocQW8qQ!< z*})8OBD)ZQ%5^#^Et4fVKYzCgQri)j)9Mc65x;7VNs4z%a?t!;OFfqF5#JDdqfbvv zAO(vFAsH~v+<4k@t6l7$ybpPgb!CI9*>GHC&gp8m4M;5gJEh=5id4iE>pg3l3PJx|5g3%{u{n@_rELvYL)>JFS;*Ie;1bJQF z=TdEqu_ae}IJC$XWH+b-0bx`%bT&a%&-H74~dMwSH^)s`KA4_uNWCXLD(9S%aLC{}+ z+XUsYzYDK+?CuwDd@iXScav`~$`Yibc?Q?0tEf4?cfGSr;MaNP|)B zp36O)HGGlL0`_n?o70IbbYHaDcC1uUgeHK8>YSy(9+3OpnzSC)khwPmd4(%bVpqq%-uu<+m zTi0D4SFWt9JnYW%du*rpKD{J8bvg6BRN+9@qm-lOpm|4c&WvHaN2JKr+j=yQ^%iMzRqu zq-{V+V%hq;Nc`QRpu1IR58tG)a;ct(kN@iYIsbED%~u?Fb-p6n@XGknGYP0Ukearv zz`@KTVD`|7n+s__e9|nZE}xKT{ZEnYYn|LC#u`cW@Dn$JNF{wu`>J!dv+hUM|K~|L z%@hmR4hGlAM|65SNzMqbrbPqUuUZ_1>Gx5~CWoYqjOxFt*0SyJpK?6=bTI2VyU1Oq zi4`f1P5*j*hM_WWC4ct#H|p;oDc^7%5rng6y|4ox-Ht?Jsf$3IPA6zxE|N?G%%l;RyYWTK*Z3 zFP4Ao_?kHpo~W98O_lEH5&i4$>TSgb*!_>QL!Y$NelKNmFkh0m{gy>i|Ni!ZoFpg< zyeOQv()OL7a7-Mi?+rY5^A7G{e&+SFu(8TX38EFEtSA|wK<=RfUXJ75l;4$f|C7u= zJy&k>>a#_RO?_{`sH%p4VaJHnf6px{G<_43ZYpFdA7_UcU+J70)ntOPIF6|}zZd)vzm91_9??HFe z`{Cwh{irF@hv*wq<$cmZ+o4aYQc-_?+?xn@l2LXEwf^?Y$v*Tquk*JQr26^uODhiy z;sLl8GTh?STK~34o}DTFDI>`lsS(&RoN{V?bWCS$Hhe)P4r1&XGT%5&__~Vj>zW=t ziZdb=z)07*C1v%Id&z>W8+^R&qu&y+-QRv&9&bs5a7U@LgU9t)@~gQqwVq*?Y~-Gn zQ!Eq=N`9nH2&q^jC1|M(_3ugkM_x$Qcm5i|E5FCDOt`Kyx#00*LD#dSu|!C57$(+g zQ{ljl$vF_gHzirc1)X)5{ z^r_Fo@NG9WaFwjAY!vbzDPe9o`GBCBm(8f_op>tPxMMnVLZ2~`U+=~79sud>uc%Km zO^J0+h4y?u^=Yov`Jaoq9=83Q|Jmr~Y+}bu9l}H_ZtrJ&`*m5y`H}lMaZ-wM>Mv)>+IBX6(@CX zahXL$@{_M1hYHm3sU(v{%(K9R>R4PIkq7Fw|qwW2v{w zXfxE&{Nm3UvT>;lx+hJ;QhUGfEN z7a5QK$$(mG<2`6?8gA2MQ4!|}$7X}M0?Cf&&(C~{C4D=KR#D+yyC{VtCDR2~W$sT8 zqIr2-TAg|FzH=9I;AyUb4<9}dzjz8tGc{sgVUi-(0J+UUISa%@KraW?)@|{)Gb``j zCQ#aY3S|nQi8_mX;Gz!i6Cf_itnlI+;alVkS?K=f>#(}ty>4|Cl(-UcuN3~xMS-#$ zPn|HAPaVYaQ1$_<_Xi>ZOL_Y=!wIQ7(qVnEv#!zOkv~gmwPPM6q>8n^Ic?^(h44ghK)S6hPM7r~A%Qq`W_lPe7~}V}pENy8 zAZOY%-8zGoFtZNC&`8+oUhTkcnP9OLxx=x(TG|ff))0mk%BxtG639&Bx|fm+uqPV0 zdp#kP+1|}3hb#-W@ecbD)&GPNPHqH5-UfZRag?29}l=eiw#PZi3nuQ&`|}2glp@J zj57JJysI#D>MBAuR7_0FXSY65PdJkKeJjvtm@Ht+(Hk5%TiH^mR{N$^6aq0|w2vN% zCzUSyreGXX2(Eyg3G!|urwIernp;D`{hE^iK~XY0L+ZH<{2LBMyZ!9FJHs8~7f?Yt z=QVc?0X+EexhI2LlX@P?HK1t|S+PVL=g7y&Bq5C$8=9ZNQw{;hCH`3mC1rZS5-V|mgA*W9z zr&v_LOUo3Kw=-rVC9&ib;_azumP^tSz{7z7BQTckLp>_I5w(0(R=Z_FuE7;!ZCgf@ z-Qg`&Vl*T!GUIykV8z1R7#`l*S`GT#C6%S(s8-d{F+{;-4EDVE3zo{ApZD)gKjLAxWXSc zE`k(P5K_M>gHN(Zsdo@sv0`%f_ukB2qpll~>qLkYaYA9ASWC7x{y`x81j%$tCn0n> zsTPkeN)lP(AQ|AVA!3Zu*P2N&RY_{Eu+8K}2svV6k6oR1qVY(l0r1UplH@*u%Rx6` zIf5%#w^fM=*EKh!#G0$6Cov{~`y2q&N=$rk6BU$~1F_LYldc|65okl1b+c9_xwM{?b|*2hr>CbjmZ(He zX56gR;?AWSy}9~VlAnZ>wt>+-fQmv0jp1Zq$G9guH8lm49iY6B5FII8sP6mVAX1%c z&b7)Z&e;L;uej|T+8WV_@$dzCvV9QH6`+3T@EJPkwD!r$mOgnBA?nx4sV)*fedWH! zjoBkUZbeck1pJAb3g3mfa~ul9;^%|ZAHZ5gWh=i3#&H%E=xx>>je#(CgY0$3EdB4M zj-#QoS0%NBlW%MoR!wPw$Liz9EeP>}l3lAgnP_NEwf(sRH5WM}GxOoTX7!Ewing<3 z{??NSf>?7&DLPY98+T!Xh(o%sL#KpBR8152A}RfrVD9Q)db?8u7NFJ%(vPvBaO*Fe zqe$Tj18bGjp;tQR>bk|DsgqbL_f8p^OsM+p_qlE`0);iOY#b7k%I}orT*ijz-@~QX zJ^-p}2V-ntDOj?)$Qh#(dcO^*wzNz?fX+I5P+ug+V`rRJ4zyodRyJ!498(tn(rwK5 zYOgYI3fHZyIxWU77r~bBNm>Uju$Xhn1;TYT)&O6ovBXG8Nl|TZS?Z6G;p6Fyc8Ccm zPvsPQ@v_qRI7LSyl4WSfAzO4w<)*W+-1_)r6Tb!44#c{j#CQdvL@YeR=X42cQDIo}^=b#4sei}i|AG}Vdh6>$wI<=6 z3EEn?M?1e`WUf`Nf_KFwh_N~&TXo&bP-pr;$o~{>ri7s`_w<7kD>2azkIyz4D<<3W zXjbk-{q?&?)<$$d)VsP&ffDy;7&@h+XAHx0lKU}O%(iy8nE=S`;;d)e=5^=u z?Cdd!S}--8@`*;0q%&oSm z2e&$M4DD5MRv(Vj^LQfHkeib;j1<%2f8pI=Zoi`u+|K@5ztvp{m*ZI2?z?n?9UUD) z+Bs7~6z|p^PU9GCB$@-U*l3^vI>#;nvst_MO*y6mE6%msP#zCuuRlP>3dg_0fAQvk zk--@mz@Rg6=kS-?5kbyfSigH1$DH~45f{~F^|fZaB4U|DhQ}#RNhml2v$6oI*MAl(%s|=68wyqbKxpM%odF zFD(Bg(I)Poc>m8MfXe}C5Bv9^>tru5aVS1m02bW3z~tTuJYHsFIYp@E)SFT%K&r$D z|H*PXICvHIfyC8c9IRVy<#@uYtqNo6)#~y-mvCfyCZ^lI9bEtD+BHT22f74(mKS({ zO*AjOm(&gvejPqi5*ZRJbTe%T`wk)pzYWxg!0PSlTd~i)yo-tzUv28}`bXGZRO{0Z zUdj`;dG+X@YVDSjAL!%zr1P_3FGQ+7&fuNO;{E^p^{b9Z+8ddZADX>?C@Wrx&tPlZ zfyyT#l#53z)aY^}8(;q`I6ZX}eRk9d8j{L{QMsk17pZis=N4cz9ga2E&dgp)-7_HH ze^l*Bi>fe{jsQOGH!dQCxAAQXZ>U{SIAYs#ti$L48GCNSEAN^8cimX749LGG_acW0 zBz-v}wW~9T63OMV{yAP~k5LwPneMkD=#W%+VvZG(>+dYwl_SdVtbSj}_{F@W)&sr2 zqExIRmaF_wuu(({JjZ?d4?gIG5A%%?YJKaer$Xk|6b2LiWG4yO{v)l{sN~kSmnDPT zPn@BLC{9SeaXmI58@48eqv|J5Dsrv8ie83s`m!1ie3iRKi`a*}b(ii5{WOO?Tr}ZK)I2y;`dY6zD!_5`Aq}Iagi=MH48f|yF5#$S9(7Iq^=CMR z{im`gQVYjkTPoC9pA7yLGcVN|TqHWQ3bcmkA z#ELyYE7-yJVbZ-&spy$4=}X`TT10GPhpX&2G|PnWb*qnin{s{J-GifUp1?NQYwW@5MN9e)nmy~ume zseBOVGuf|0Q;8Ct%)ha1t$&&zotfB-u(qkuby~TAr~Kmbp7ZtRf{-7{CTF(eAl>7G zclr)fZj2w53kJi}LHu2jDc|K}26uJinC~$zQ-KO|CA6fYzqsjY+i=;FPP_HPPn^b+ z!0ml7i2l*5U!lgErIKRhFzM=W|T%P?$HM!Z;KRj`HZ+kr|m2FpT z_E<3(-+9g_I9o3`mQYBLNV$vAK!@l%Jld4kh7>X1fd3LVg+8oL(r-H{p5Mi-MbcC^ z2gJgTNRo_l&t!g!{HC-9GuRbN4vfj$>RxeqdlJFsxzV!3E^$$P)~a-Zahk5t`HQNM zw|z(k+qbX#!uVW%bwmZ-kiEB(&TRLLFikXs5Ai+}jZ1LNA%40~(y{6A88Z`!Ox*I~ zGuw$%{BtP>-6-$6!*ABB$tOJngulwxV0|_N84X*NKYP#llpY}4@r^FKsCRdhE$^^X z)=KdU#Om{ZZUyp7yKdwGwEQI-mtfvklEcHZ^qYA-52;(j(okTz1X^bERPAO8C5{`4 zYB(M@j-ma1S)`rAL@@pm2eap1*h-udRF_B?GI=$A2`2!?zGU?ianjiBu^GpvQ>>A} z!&YUt#8$fBVA+;Q!Y|kbN4{tGpK>l*X=B_zd!wmS$U0sisR>8<`@l^CFF3R+jx7os zs+kCY)+`53S-HACsyUB-aj$$$u6x3DpJ4;eTuxcnsGWOHiom=X+=;EomK3lPNyn11 zl`lW@=iB^$4hvZ;7_BauX!Bj^z4T~1=0iiSci+hN{dtFU< ztpD+WyL`fR@d*Ryp5vF^v{^-$>;=*Fxutgvh@GHP_9XT0?Wc@og7rPD{^wlI&U;s- zH;?c({`T(toqIz=f+8{w>#>B^KU9yrG9;x`Ee}UKN@wL7wy|z8B7~d*tCkFMB1rP5 z27Zn8zHl9e1_Xs9Y)uN7XcttEw9PS(xo;?!sf^`na~5&x@zoWE#MDaie}^4+)>Y@O zJU&R)=wow;Zb86|a=~aQ-VymmQoCi!XA;8pZ4y#Pm@68cHlx#7!XXss=xh5({`!!q zsO0{V94<|fVurh``VGBXByCDgLp%Q3B3Abj2nAN+WByKJ0$5I(1E~_Qd&{q$d{%z) z=G)rZl?bv=IAPrW@@0U@Nay%6$_*aPXeBax0GbtcQGNW7%+s!|qY&2TStMm*V)Cz? z_g#bkgyHhCJk{e*MYD@xT))t}U5wa<{1v6QeEphZqNUv&Ii5tlk(S9I${%{%xE(+) z5qj@|(EHf+he7dCFXY5EB@6N-^cVjJif=&nx9xUbxDIOxs7SrxcA7e<5oFA3H#kvL z5(nJsLv#wsXO_*qc@sAMkQhDwM;H#%4h~%yG8Ihda=ea-*GY7aBAr8@0*pFOe8pW^ zT)u-h`=kl_Ag)ENB3Tf!6&Xu!$4E%c2*cj$;wbRt`Ha`g=>(g|b@@z@ihitv`f z^=HeZn%%NUC1hR4W&0bIoD5^`PwNNq9H0@$M;4798F9{C)6WnXMX_RR>p3238VNKu z#cAU7a8D199rqHmqSDfxLsv5Uy}7DA+OE;SWQy|3g#ZHt>G1O|yW5AG+tp>@L=yxN zDKl--AF;#Up#e3^N5f2lT>?Vyv4bMjoX%a>IW8JI@XKDZxg}X*#0Td~4kezs|J8&S z6!51^p6qJhodUU|-o*2Y+`M!EtAZjj>`dmKD@ZOT>lgs|ILaGsZI#g zwYo77O?$}HB*HZB@8V~E z1nw(^fllc`c6QCZZx9lzJ7w0~h1}dkPrqVULbOJW<`syw6PC-8s>FZ*K6`f21hRIl zo_apVnqsA%sw)IhH#vLlGI|=3^kMS!yK)+r0q`F|KcBsP{rp_m1Nx+C>TcEvcxbtq zzRZ9_Y}m(Fh|X;7eBqXBy;>@ISd4R+(JMh#2F;MG>+uU~$#~s${C3spXCvQ9ZY<6S z#21o>g(Rb=0aQwKvXIiC&m8dbJ%8Tmf(sJbBijYTtac#SUJir3a2*1?A(Vz3>oXOa zWO=}P*tuZq6+rZrD%^$Sn~>BayA#LGj=-~r*c|0@tFE)_7?|NR_*UHOdtOJICPrZT zZ%tqmi8MfHmYuNsLWrk$kiR0_KT$o#5nKoTZ<<%z+=<cun%A%i*ox}53c&g4`RzP61hH!-@IW&#=SHrxUOP(`(QhT$#j z0qcp(Zao%tc|BB?VLNZ|u}OJ%7w4~XQKOwqRbV9KcAqES`nw#9s5IAadIFNsx|r0l znVb=d@jd3ZSe#!~wQEq4tZ1p&Ew#Q;vL13_=0$W|MXBpz;TBC2+_H__7}bX4j>@VRSpad4I%M_fcJpvu*S=r z@QpFQYACdm>45xNz~Xq)k^j~^NAGEe3pzbFUsI#bRZZ?DP)GokNN6S0;vN9pfg;Mm zp6?jix?*yAJvATms8pI^xkJ|v9OL=(=d)jFeR-mb6My`=fRBVw8+i->Q=)BlSQS74 z9&J0kv3|jb)@v+o0tGil{ny!a-*S(2Ao{cqqF6Yd5(kW9GFPNDWGchMBV!eBYaF8w z4jLW<41FyJm`UHbu*Gg4L>+c4A*07bfpGxwMR+b25Eu$t3nBWG-@oSxu8b2y!cCvF zt|1Uxyp!A13dvD5|9F^5{o{in1FC0_?w1xcl-TZL((klrr2~f7;ldw z_g?!sM@4;P;1a$A--?R7JZ1hRl~fTCk=4uSjSlc+D;r$3AHMyaDs*PJGlIf8u zUP=Kbk7hP$7|`kR&T~ zjD{^D5<s z=n0OsG@$Y-YEN6A3fS%3aVPRDwx~l>*UbDYy5?rb%h3ITJ6lt{h;$l#Q}5ssNApBo zGpbZbJcW(6SD&Z7KyRJsA+f3)ct$b0F)Bmq;8%w-hbj(Jri6}SKYD0In4|>_eF5Ji znm_=S`qzSf|9*X)9qD@*GDe`wk!#UBO4gE#ldb1qH$2BXpE!*hBk_yUw>L+HW(2r}|7-z`VW9Hxp-9}0yCR}gtSRQYZ7s>>=xw+7+ zCeRWr$bwd3O9R^<2iG6=U)}{O(99d6!9;fcyoeH&Gi(*$bw_TPpPqoJ8^1^u^y5_ztq4v zMEse0&$z-ZKQtb7-i-AAA1TO#LFjBWJ*o#zWSHfEx}K8mkNXbi2jY6M&u2pc8yV>Z zn-*Q1d@dC@hmd1P|3DMIFxlX<$Ck_m9`oE?3DMH+`&K@^=WsqvLT9zGM4WM{!1jGh z_r-ag6X*EXDUJu<*;|(MK9W}zZ`mbv6z_P87k%4l_gyKb~Kwaf-E3+_=@%_?#fi?j#{~*DEE{;7Y-{ z7IW$}8w#cjD(E zCrjs|<&&-j6=fMgsOBBsqi4svFbIz+XNB3Ky~Nn`Adg)TBt9Fde3xI>FSx922X3jI zRpWhmiFfudy7-6FwL%0->XJ2)&fm{o#beBF>2P*ujk|+rxLxTx@2`@L#-2}a$Rp2@53x--X0Mz+HRN-&ku9H1`KG? z16qlqeb?o~liLQzVCRjg&ep!KEr0}NHK%tX{wO}6sC22FsB<3vqjq@_aGI1!RVB1J z!GfW={lcBpos~Fo(r)oqV!K%z^v zohVEy7Q@ig`Dc` zVTMtcMd(&D0%@x`2`Tiiw}k@V>}$@Zlu4pSxukv|dN9OA6>`Zs1@}ekQnO3xD-{ws1Fw0@78mO8X zY(7~C2Y}w5Irb`!_Bfp{R~YH^c?6v5w;3H*^Gjl0YK%ehxxBpoAUO5mKvU!^ZwcMZ zXt4zhOQ-U|wzf91@X`-sj~+fe+%}pcG^TQp?b=wf;=0d?UAr8T&uZa;VR| zJRJWVWb5qpf5p(4vyelP=!c2MLASYK`vl-n)CB0B0z1=wA=@*9SGD_uM?}x!xLkt% zR&#^ah+VjI5x9=~R#g|EwNeD8_{}rs!7c)VJKvrmPI_b`x(Rvb{Kt0ijel5Fq+{n9 zulLnTL2LJ+Ba}C+iacF27Oyt@e7m`Mzc#CAJz$9*K}IorSF?oFZ&VGkdyqEarM#H( z@{~r--&DdM$*+n0Z6DVSv)n<%M>H^FJy-Q5@P6=nTv8n=3b zX70;N7+m&Yo6ee=Pk88x-A$3PU5MV7fe-pmMc7=S@x!St<6St>g1$86-+US;ZvwV}Mgw&tz^1^}yIeoGDv?ntu(6z1o@W_Tr3G-o2ecRn!+0*y z9Ggji#z2q(D*oM_ik9XlK>a#K7NUc*fkTxYSp?T;^b;`GpLauDaXlXRRd?>!yiBcH zr+CLH9@~%r2DeTev!X$2n(k1>I)Kxp5HKRp$49QHZEL`&;suPMjE_$pnY z)j4|DB|eFSl^bvZ_d2+y?ch9*HMfz%4z|bM?%8jUpR!dgsC4TK1m@XeDLO)_|}D2|4VEKo4EMVU=P;IGb*UWJ#c^I95^ijIQ5^V;4Z6)PBHJWw7gp(V!_w_rKawwHGFTXPM z{iEN^QA2qS*!iQBvKpgZzwg0^v3a9_Eg_BcHOd;b1vObUzpTMI@V#v6{uk!v*EULS zG-^G~qOjrRBNMIr4@9-I;qbk?UU8Y*_^6gb14sTeW9gf`DBtiJ z8-uXtH?AveP~ovX_k`a$kb#ZpPk--wSMgD8Ltn0@fSSSvOq7|($>F8NCMe?mX|@lRS1OL-yqD+09Jy1iAxT`-mn!#0ivjp|96$MTaT=0o3?}C8x^U^&2)cFT3ny2?-1h9>~5)vTTt)a{j9hx$vpulFR#GTaVkR%?kEr zYoS0 zT2d}l#j%&ANT}+07c<|B<#8)4s9_r8Fm%CZt_F|Em|+^6%G#_Fz}_GA?UKUZ#G_}^ zym#M@BvA6~1k_Lx`1FNDlf6MvTPG?nE}?*&76y9OlKCFu{+{?v*daDnVrhK6`?jk# zR5$aj0eJ`6weNUS8G)8s-E6Ur%5J!CRo`hmu)qU@8S)aelC=G zPQGO#w=xNgRe{?!dav$pjVBAgrp?1>@t=5=+n3HBR~-X3QH;#YsfgP(=(CHcri82RMD zO)L{5-0!QF+V3Jb72{M7Han=qiGB-?8T6bty*ALl|9)|!zEy5S^$PLr6ROv^6s#ap zb?luurqh$(XjA{Z1;X8uDTYk|g%^Wk+mz~<)MO!QU_ucm5Zo3ysa;ZZ0K;GNtxQBn z9!M|-qA)rorhDwV&3l8>om(-ux`rxnnN&o9&s_7$o-PA*wJenXdy6JZYkB2K&WYO{ zIj!0~1r_|^l^la7jc?QORel=Ql03++N#V|QmGevaO=()akhn&-5-9M#iNH0cl z4xDVnFFPbxLJQT{MopgFY0cv^1Dm zyovvs1yjEJ-P&Mh2rX0NL+49qCQ*%n zy?7(B4P;jW5rV*`f*H8=Zrmewm48eY_gMF>`Z6@M7fB6abSHZO@6IZWYR*fH71%|TnWMxOb z(y*fcx=A-&w>2$&7vmE{1wqDd1gSHsrpItAdsl@n9xN9-ULL2JI=?)~F8#H~bKAar z6trkRtEVSpZu|Q9Z5Gc44%9LT5pYC;SQmatRJYSV3`t#_jR`J5q`$@OSv__y0%xR- zX7o%#PN17I`NVi!3|)R~pDI1gyn^Wx;Y44LP~>dynL)r&Cgb#ClGPfUIJ<6JLOGk% za^(?SyGD)Zh7(&$>s8d|)vI!Shx6x}8>H{|aFRzb8AuMsXSu9VO?Beztta$oLLS=UM3MJR0Br#=CdQYtpoDjyb!K?6Q_uN(mE%Ik-%clYI$S(0F%-S zg(W2pUc|+f56tgiIdbyzlNt?ScURO_A@5hJ7kbTZ+~L{On@2I|nVJO}97z)F{YyV= zhm`D%F9U2GNI{|>f9a>+9GhW0UppeXXHRFz`PRX)$P4Q*9Rfg)v?2&IC@UyGP*M}{ zyizhWh3v!cV`4Nmke&1~&mC)f0 z!oHSlBWc~x85kZO1{{YV{*Kk1oJcUW4H(rzq+oY9Z&l8`ZT-a+ZTh9wU8%Hi0;Ad- zD%%yazNuLkndXr^F1clfvrUfCn;9|bl~iMs)9+FQt7?TK;X-f3O!@KSM;Dp=(hX}n z$3tMD9_4oK)%l0B0!Z^f^N3=g$md34=ZepdW5eOlwu_2!cm&*)E9hj0_Tq4J2$Xk+7e6*#m;Ye{mFIIW`3R7c`ty-6;SfK`pU#2 zG|0d~m5-3Ca$e<34}Y%0^M%2Ga`8eRMN|O5kESlq1fS~23~KYaqc-YGXqiCy>-*2p&Fsn=%m^ z7{xWINyNuJ%J8qQaPOd=9-0s=(YSREMuxo!hfk{lKvk60CFML7oV3qr9enfdTtqJO zkI)^Rs_)^0gr%;+7LqZ{1TwlE`(Ys45aThv+;#KBm(1`(g z5{*-vZjpS>3nYQtBgzrby_d)ux1HT2d%t$(n`0*2(fuwmU;-~h&xADI3H6oX&rdUh zO{*?D?^uAcp}n*O$i_&_8fKb-+Ep$PYR4MmLI+?+jS z{~Z6TxP@zFJd;8J`6lxKtBMShE0ZYGR5)TTd(ff3_=7584$r%*BdEGY_WiM3hrL9y zI~SvF|J^GlgMz%S7)AIakv?8kh_TbqqOaL7{0hdbuj(iKuk0O?34argXhb0%l6iWa zwYZFw6mssLt}$itNg<5F4e>$N0WM*>=i~|;1_ehGS`eFoaM&HhvmWO<{psJ&P=&RH zcTI5b1hzSu2U}gwmmtm5O)AB*A?o(ikAPySvVlL{?_!83*_=MW69M#Bk(ro z&!;15A)L^J=xX=e1$2ZQUA5@)<2byZc4WFMcx$i@r;jO;+@4@&L1A|kEpNHU-xSbe zxqeNws0i?71}|zG3%d2VQkDAKv-jt)cFY$-G8i%?uSYIOMpa5;#eiSiF-3Am61jFG z(-NngJDPT?lu@ize zszt8Gia}kXT?V2JLr54{V#m<;FfFaR<)wyS3(yXmy@Xetb#Wnj+#^^o;!hNVnGVf) z5;YasR@brH6gw9*2?VYF?Zuf_B6D%yW$V>WD@6t~w(ZUE>yi=;Ro^Z$DpTt$J+@Av z^|-02R?3kQNvki<9jE)&#(E#zut!WxaG5_^!aTAUf4Bjq{r1byh(_NoH}=f>;}qR< zCl$5Nh{)Cvgc20ovTKOsc@FNx`q8E0U?PbXnt(5ZAMzhrHwA9C)QIGMovo`8-i)@( z?5dpV9F1%=V|6nfB)!wtyA|yo*;{xe5BWfj{;@W~G``DRjNIiV%zLzKJvAmr-_rRa- zX#e$xT1l(EG2Vt1a zfhenwsXT6%m&o`CqI5UTC+5Su>nyPa(Ya9FqGEX4Qp9MhSQ4TRc-Jk%NB@tEu7QU* zWqVXGdXpqll8|&3bVaga3VcEl)fIiAIYL95oQj)NuHa>>wZl{mZ6a}`6hhS9QP}x$ zgFSZE=83m(yxTkBCKXDTp=-*1k;~MH7zP>hiSdP&&ZGFb==~pl&f{2T}85*KAbdF0}E6*|sR?tX8=Ft{qXtZxrk-+JBaW z1VLy^f%xCAr9?SPW?XQ?NfS> zRST-=!Y)OLR@cw|HmUo&euO9JUwloC=dIWsb@gOh^$#zdP;|CM7RvbO0oXDc&%fLz zfP-yUS_I3O>N*@qb=DB)1o5ExZiotd$q-|OwgvVdp6NAy@c~gY&qPCYV6#4j69M_E!LGM3f(gRo!K+GFuqbO!zG&IV<|IVyuLOeXe$RS;Fu?<6 zTt$NCF9rl`huz zV4@lEo~ozc|8l`Uvk_0lrdLcm#iW{<+6(yDcpmT|A=X`t#khGz?ly7C4_yE%>JIrS z+9=`}^@8bxyAe64^j3>X7XR}z;vA~}1jqR=9>wG3opjN%w22y(k$9(#oT~WjVU`{| zr{}H(d9|!hhYNvvlT^2<;bQp3`kvDVbiP2{Xch8OuyZT!>rkvYtFq+_UXR2v&r)ns zxYmLKLE}jd?Dj&|vV4}TKELq0zv{5U`&pe;k-SM-0({S}>n^I3=vn<;XStz(nrLH_ zeRKHNrKrP*w`cC}N!c$T_j|}0%?~+_@TlM%?zZoD(j)CJMe=Av+cw@@d3jwWCF0zE zh=v@w{;n8;Oonl3=ym-HVi8wvd za%8ors^4xy1*?e6df!D#nPs)6rwN{nszCl0=fKP<>hDAjg};}g@HJE&GvF z`88m_bI%P$cNOTYzVt?>&H#zh2IDoR+tU`4&-b(+U#>lPQTw;P<~lF3#~3mlAoYnl z7w^W!9bM{40FLg-{Q0OTZ*K5|4ILhcBpyNbGbO;A^Tg?fI@FSTj^!71I(Vg9oO7XlW6y!gBjB% zl)9hdLnDAW>0<4tcc-AIZZIUALA?CJU9DYj9Rh^5(bGY8_;k{>3X+e<6|=h=)}XPy zc%uC#+BRN77k__gbDiJWbb<*@fY1p!p2~bs(5LD8HuMj~gJjN90pd9_%GggiWbJQ}dw0J=1tu?v3tV|RYLmMOfjEvXrspp2 z=Slclprpfe{V5M>351|m=SRpwxI6?`3|{SZ&zWoe?k0cZV7OH#BrgKl^fm`N-_upF z{@*&jr}2aniw+k9P~qcHM+*`s;uFE`d->14f4%8tKd|ss$mLI9pQ_U7NW9>^8VcMXTbo!x$ zA?Ft;1e_Iz-Y@hicvG;mUPEAkrGaD{xK5%8BlN-f7Z;Tud{K|u3hUT?o&INrQcVFK+Z?sn1lhcY#%Yv=LpoW6~)U;B0-9UgUzSQbX~8n2u`T zo3^(47?81hy1SC(G>@=e1-YFDhVY~~>D~SOe7?1T8|?y!7Q2@tWa-N$YFmhb_owFN zic&UE+SxTfyc+vmR3qx4ujMjZ?iodTSk98VO@Uo1TabIcj6cz)DA7DFJuOl*#V=$U zXU=O+KZ<5Cept5blEOCb>t?{BVQIYoY)sVIkfP=aRBh#;!cytL+((bnTLCgrPJ99E zLa`hhlT;9~q*%wa{#=)`NpU_hhW@fm6fB9_dDM;>ew-@h2bVi<% zTB=8E&Ji`79&G|#G>uKaA-isRZn4{oyCtN-pgG+nTfa(=L`ENf3`~EfUV=$* za+zLZYl%~o}e|`7B2U(Iw2DSq#=ECYOd`OC*gtfIh6g+f+SizcRsFj zGb4vJp~pdVvMVIi!h5gK>~NIaS`|D>Tns7B>+<6hXmrS~$vwQY3RUUak@+=-*}{)l_5P*+f1LnTP! z@@g5&e7D5cT7pEA{YbT`*qZwQ6dCA|j9UiBpxE7MB_tz$mhr(KUW(e}Z`+BE8&z8G z@IquBbRAFN2ZMdG}_cgY)-l zc|jbnWKwDMe2;=~Y^E$<;A3fkZwLEakId_9qim2WMEAdMKfq*Z(Bm$rUr}A{v1$=& zTmUdnzXan0y4T?IcyJX6&-SbZy8y(H<+=P22ue(XqSuoe;f}$<&}2svDlY2jgDlpr z`JjP8-c+LRtIBg9Oe#05Wh2x95=lKV6sd?Pn3Mu}`>Btk;>4_|q5!ZkdU|T9&+i-c zba42oEb`%olLrC0!=F!%cH{_csx{0&yC;-C^_x1j-yWnA2EAS0vG_%AydF+q6*d{% zaQEGY?EY@kJEKtOMEt%`k^n_G5jY`*XO^z#kDqh-;b?sBzC>E7(X@}`Z36(Ku_i5D z&1Nk9@7~5bTxS5g@17o|QjBJ8)}GmTUas}tNA7q(K%?%2`g+;bhkLL+1QWVab(G{~ zAsPVyrP@_(wf_4ThBqWGnz2~t#EHQtMuKmg&~HDLF)z8d1!aK6z3*FIPC9B+i+DSa z+XrC5kh;ND9;A`dSXHGSai-Xxz{F?IYD(ii9e&h&`tmaR&Vl5!jaL;7?q=I~Mwg9w z$hBzAu9EFW0mVOnpA$Cx1FrN|++@)1<_0hy3iQ0HDEdoFTBewbWKwr(Z_dpuAu z7REeS@u3h1_vz^i!n9k-{SZpSEGIySFEt27!E|gukL{Z4dto1|6oM17Vnm41bN@`o z>XA8>T1m--c+C6`4iI%^P80l0w=InRS)Bitd-Kra1sX)Zi!Jj#_Y*Dwm9v`O{e;$5 z;2_q(QeJyR4JSI{(6qIOPjIsQruptY4O-VG(E5TE?6u+I?~EQ#Pl`rV*ZiECh|eRU z083D169e~EK0dUF;Bl1X3+vAVAYDc=_ z|3u+!6%fCztQ#anE|Xvdo3I1Y*Mh zb?;tG&6weCjITt7ObrF6W=n&CU4HS{Af~06X6~mCcIg}7!#o)zahVZu&BlP6UiX)a zC!Rt~Oiw?aq5riCm8g-}2P7_^vEXT_)Hc4#o2hAsU5k&f`IEj^^<_J3ri8uFVG(md z*9dYzS?B3tFH+nJ=wQ{I|6r@rIc`+UO>*->qIG~0%ks${y|#67aV7T&tYU# zz+?F%WINZu-LOJ#_jBj0h$08`fmtrJnLy^-HKv=perTyRl`cC^PQG>IG?sN~t1mkn zwKsg$WYV+}$Di2*j1z+v1ik+1X2cFL1U6~;NraKMwzNbRb7v&y2*I_DyG<8+GlmpZ zv%Q~5R_EjPsXS1+khuR`-&&?_SWUsi`{8voR%Za9qk#e2`$*)o%Hn)im9bx@@Kgbo z76_2n%-&R2G1QTgny|-N=#8useqWA9+@!t*o?KTaVsKMmhaU6XL0g|M!^V~`G#K%f ztKW1IrC4;>=461sIh1vZR)ni}AT{w*}S+ zN|c2VMYhr*W$nbdS=5iIyr>&lng3#NF4O4NU)~oeR0V50s)@RH#1D;-TiF?NmrDmG z9AKf4PddIv{)jv6JZ*zwu$NU0C0BlKdIV{#s4fJQN@mc!JJ!YhJSh{y#mU+2K6}P4 z@yK!KUb$TbczR(nq2CpVorN2g&orbV7fzMZn#UDhDh=&ZD+ff7TubMBomK(#rVKTN#uP0JC5CVWGLF>BTMiu4 z(}T+XjU2m~ar8{-QmEE?Zl;iNA+CKoIzHtvdDt+g~^TmXs3|x zw*t)%s7C&oyAlnkhMUCN!LHqKS#g9shw|ZrvNDLIVbhT$GM_t*h+tTwV`?8Tx_Sgb z9d#&l@8qsayoBzh2#qI*)>fG7M)f2|2$lijZ}2m{V7}?ffRam~GPXr;t2@1|J-D2nbhPepQEhL(QUwIQx7nYxI~H-w5yR- zbH5TeD*y>$T(D_lv-}YOiKrTM@uqsAaF;a*9$OMoi8}V1gbo@5ss_U;MX!IA&ILK! zj(wMJb;Vv%QT2KWHq)9Z@Zc;oyQPD=E4==nE*v8n{*DpNvnI+ED%uUT!zlL#>8S`v z=!2MxF?qdpj73^TW|$nbnvgWg2TrK%Bt9+am@gfUo)HqGmRf0XG8vHPZ{t()5$o5< zypv#Ks_r-ti5ssA;Zgjl8L0@{UC`*&KdVxo`6Hx9ij(=N$aHf^F&HzLnoYE3Vf28u z>6Ihbm7lzU;ll)~Xc#69m72sh7!?SIc5T*`OD@M&+CpAAi4AYyb& z<;L44<(jpWg%Pzr{Mk=hVin2digEHJpXwF|co2fzd?~=IQEtAoCjzIZC&YppNm68T zw8l1%nB>$pBBoaC+$>{JXk`l7v!UcvfQ$aNeR{-A{&Q{{82{S7r_HCSS7I=KXo?c~ z@m%#{tuaSmj~IeI^<&5sr9xLnM=+~K5k8!%BGcCo{+j6%g3+@5G3q)sZY>`_ek6V` z_Xl1oS39`7?|9wFx$2~R45uB*Hfm70J5YcA`Zd#}*Iihvps#_awtSkIQ1-)eH^0ge zPuT<*H7;t$pDtLKI7%NqY8-^xyyhcuj4l&wsBr7Y6w{UTs-7r~x@7|F7 zgUM)J81ooAdPjuGQaDb!;k0BFI`>-Lct~2UE;1#kOWMIy)9YS_{}f16JjAO+E3aUc ze`&FgWPF76If4%|l8haVAN*vo-nS||Lfg4x3P9L^4aC0syVSqCErpm+9nmLg@L~(N z(Kb~45Y2i6*Tyl#ggLRvhUEFY1{kM4NkKs3_Il$NpHXwI#@MG)<)x(ss+`#M7k$s; zM0Ev4lm6%yQDG}NO%xfR4Xq>@I|DhUei8q{pg&(jineyqMQj5TyFudr+(&58f2ExP z(AF$z57QuD2nnPlMeK!73p{_qnpDxjEAP1~jaH;TMB0gX018>%G>_jGb#Ol8)#XRf z%CvRiPu`s%yy^Jqa8|%CK;=atU%hCH&n?T+alqqQn%@+>8ydg;mZLHc5$51(v41Dt z{V#bKxg8^H))ChEi42A?PD_v9Lj#?WGrAPVw=uX}m+n5c&G4$(Lw^RtZPNNERTX~2 zCNG1*1+u12=rH;AdOqLyr1gBch^*Gx#vMzey%IW0+Qg%WJfPGihp-F^+^90e4)y;S z*x$b&;Js2P&^J}e$zDdraoA11?Q-?V1#u3#kgiPSC1!*gRWCC(;i(2_JN@YdQOD2S z3z9e-@hZB$)V4gKpk8;st{HgmA3ZYqnZ%G0D1HbqPLu7b@#<(1)!_~U+{~t&p3Q>K z{pUn=c;k)D;d?KMez0xp-rw^j8Yd1)7W0X9FU>|R4I)FPBiSW6uib$M{W0vGKEien z&}NQM!q9`@mmEo49^tA$@fHTt!6Q)Me*{Ahw8%EvS%`@;UZO~D%`6KV57~(A4Bf{b zQPbc@0rfm0(egEGcb{Hd6uuGFUY*cOn~(hjCLK=0Kaljwf7Dl_mE=ASh7LDgR;`4) zf8@jeDDT)x1yTf)s>`hr?w9&cJpX7-`0k^mS|beLPr15xwl&6wX(I^--%WNz;$oMO zgJLx;cQc9HB^|Ys86?^Rz!7pIOn^M^cB1fEG!cU8-@Xzqzsobo0J6Up)>D)fy|l)Q z7b$#KA)HLOuL-lg1|F(^+;Z?C6jjqM8f=L~5T2s;f}#p?kO|G)<{>t#)pvDyeg{DQ z-7_@-$GA(~pP zS)GEiP~Zkv;|CwNPi9OR!sTVL5|0@o1gYHVh^ZOP*v|pWZ`qOEWdsQ9r@gk5~TNMsiV_C;1)Y zC5^SA?IKzy7Jc{M`JyE%_Kw6k?ZUM$tQm}tgeA54_9;G6to%|3u=a)w6+4T-^S22G z3|{B&L#D9p8Gn++hI{XHueg)M7ux$+)kZsaoLZOjO+D+#RiCWF2NI%3j?{<^U4cdZ zq6V8oiG<;_ztaD_%84I!dhG>9s)__@XPemB6YJxTo}xI?xB>34t1iELAve>?M&&*# zZe9ySxs&V`(~a%NHvPFb>z7XDOC7M=od$@K+s{`yO)JErnq>;v3uQ^0?(1aMpVak> zUqqSm1{c1$2yL-zvV14dM zR=y8yVx2wk#y=NqdiBf_cY(BizSy}!RZ&QD+&eS8PgMePr5Bc7%$=|}#7PHeSv ziBe{mua2IcpZ3mN$^y4AKqEA)vNTVG{x723{#QgQqu8T1wl;t9>n$KUO~;U|sW{81 zsxQ|DV@G!pDObX_gn#GzWoSCN)XeT${OkXM&ZWs(XBluSg=oq{Qq0@A77*2tvlZ46 z8~C8gw+vMOH1fY^#L5@9aXt6I4nng3K*yb*NV;c0e76X-`yloDQ|c(Z;@;bxw4Dr5 z(^;Zql)8V-bCHAr)-7?Dj~4Jp)J~AxUZ4iFLu)jGyY9ER`3Jx=0CB}cW%-?VtBMG6@zZE<3{L5T!a>YrQ& zilq9kYNR`8!ZLgxe68a96N3~xUd2>w^E}o;@NruXXmbExt3$gc^kV6iBDULT>%>2y$*HsV3hc2!9i-6*YzE_ht>{jp zw($H!0k|geJ{#-n9ng2*GmMdg(4cbU6HYb9vMsYxq|HyeV?Fp0k3<;zuHT|~`71*s zqsC>KJw{t|M^){*i@qUqDQDNp6Rwc>y2weWm$oT5m81!}yNEC@aHn3UBc}eiYY%U% z9eH2up3vHpj7^QYZ20?V^MRr)jqJAf?@v+AGW#^&FDc2~K#{n)`+U{btFJ*q-&F*K z{3G%wyQKmNu6|TV(Cv2|m1it-+2DLKgu`EkIO8jV&xs}QhKniXq?fbv5!zScw$?58 z+J%4cGhmUNP|Yq`wRer7@)nD-Bb4PY9IHn;;w}TV@%C+`N!4MTGH{|D{$!v^h0pjL zB9-{~m&D~lv*M|_AwA*dPK+Dur>}*p$*)(eho|(mi#BOTdh1}NwOPMTs1DS5cf#`L zcOVehmr+5y>wi@I9EbDB$jpZ3$u6m=EhNCUJF2ESI;{E|`s1;gBW09=9#F{_{v(5L z@m5I4Py6tzs$Qqx7YF+;imOT_Fy^14;9|cp>JdR8&uP8=64E>4a^Z^{bwTsXM(Y6V zf3^Z?Rtr=tJgev^X3gW5fUaV%Ga)0 zbWx)oJfGjTbfK!m9OMV4WGHEmetPc5v1`$Xeh#K3IE8y`x^~ARB}XWIkC<)ySt{=u zvvE&Tsu@}o;A47W$KbXf0a`PY`6f}f_B~J7R7=km5DZnt*Lb$TLL*B#B{9B6_CGdl~lY_~Jg_ zDc#H%R?i`jgf6v~myVo7uc6o6YzfVYklf>pM?VwS2(7&oQ0bv6gK9X{(TaiyPxF1; z+iRVjO&d9lyWDB+Hl%m(LBOZZD`cs;msX`Kt7#C1v!Li;U>7QS!T$ha^Z64!}q* z$i&P-a9F)Ncaotmqp()Zku$3HL88s%LjrYV{Mh1H4&9++m~d|BJ^ZsWCd5PM^C!rt zs$ponv&=gi2J{L?p{H3HLw9zR?3f6$+6)x9Wt+7)YGlK=UEgf+-Qt|aonS}$r_iRt zj4iVAby}K>J&fJnWESl4Hyw*z@km+Qg1HXy1_q|4rccxvzH>fvoQ8eBq`+aXZ~XHX z=y8??KZ6ugk-Yc~FDrUX_kmFZTw`M&pI%3wNwogL5B(7vr8xS78+2mZ-3VzZaI04@=fAjk@htym~s4dVGiu$Oz4#q!?Z-59Ea z`CZ=Up;KL z62m#fhx)_(KT(L8f!ll95p>)L4Z`Z4(mL3GjPZt`aG5o_s~wwlq{zk^&lD4+=#aZ+=Se^4rKum zw(0-)+zCj1k_{e(nZ6T!g)J%@_{0*SyI@2Duhs!#4qR@=dVN&k96yv4mEqzvL zH(gEbSg(CVJBLjG@wKdbw(ECyQF+5e=^Q%#f$3;$JTkLM_5~I-*#|?)dxIlqSFE`q zqU=ELWO~}cL1J;{?8Srwnhd;j-1pN`IG``HJ}=3g)S#?$A|MfBxuu{{z`D0*!738h z2fDW%J@xRm&juQVdZkJj3aR0EmTgjE_-zI0`!l>Wn7V9C@Yg4Ehu3r0an*D5ds`p9 zgB24~`v}2DfGgzRU1!}*nB52SS|ELM8JoX5N1Ev<6J=4z0~sBj*;R|6UxQU+Nm%BA z5vv~>4+;!~>l+;h3Yh4?)fP&rWLN40)5}ZbS=s21wN*=_^@Z^ zNO7UaAx;;YS;2{fmr8tUDWexsD@V03boqPE61c;+u}uItpGb`wf6 zy$VO!n!TjFQH&!1iMxC=aiI-_u3@ZNO={^VyLCW+%sV};p^JpST3P_QMyshe>S4C$ z&p)c%u=qnifDkfra$zU>j@w}`C0%~{R8MS{;pEVp0^_jH$L&DFCHf!GYk)fJQIkzR z&3m|lF#TAn6+t(;^SogL%rgc`mr;-cU}IvW7r*xPtHT5*y&FVv9uY;9G|A**fMbUG z+`W1_>mM`Lj$rySZtXY%A(el565?K*L`v+z218QNtet6@7np9~ZXGHSC275YR~*jD z3uw-z^7<)P4=(dA+7hwvXT#<>K|+K^N5s>^bDyC(Ra)efm1QTaA)VQk)P&jwdWJsl zg(*ZjVVi)OUuN*Pz*jjJ;v{s`HbE1csPGH=MCyBpzXNY&A_vmLBT}%WL3$g z$@6xJJE*g>C+%F^-KAqR(N1Rhiyz;ZkDkKi-{Af*7;6cN%? zLd^aVs^Z;v$J-E;n%K^cj)z%jKX^2%k6SKcO-)s6QqdbR> zV~1#m4ot#~*(Jrre0|@lX^R}S6!oQ-FFxCxF|@s@iWy>RlC<(F7^XTpRCxEt-o|gY z7bNgw2WZANYw^!M;8OKu96BJWJ!QC(*x6-YRf2?{* zxSwSYAJz@V^Ft=8?p|>zt`qgzxqrCR&+*~vqwVjWli?EsxWvQNb*%jX%ZJL10ZP<& z(K}eNS)7`Q)v~PlK?dU;Y zdc%9wP}^KxyWj+B|ISBd5+x#cYzs;-$^hSRFZ|n1PUyAp>g~n+4kNp2taB`FwCh5d z!PQV5Gd66E-8r_at^v#(-U+k@o%50-#`B*jQi&Z^4gLqiZP0`}{;=O*99EnHUe}*b zs{Nh5@zh!36E`k46W+<8sEsms^HNz`-Ak)+`q}1+2|`t6fkK5ql10(`Rb?OpD zXCF%`wd85h!>k<}qh+GgS`EUCj~{P3zmuf(9FPStEigSULg8y}i;QK^I@+rioGzl$0xx_QO%`koPw+?v&uT z0VG5NsEOu9|@yL?NB)G08GARJ;6*6E%$QXjKe;9=IQO&2#a zJ`p+oV%?^S8}TYila-?xNI|L0T+k;ZmKtFhA>DjhH8YsYE29-C5AC9d4^P1LeW(GG zrGV>+RN?_ZNv^u%e~yL3jNI=*eaCbu?q{l3GRQRInvu!=;|q(bqr1_pY~n`K?{ZA{ zBiDw!yvokFS4PJ0y&?m78M*+;= zOjq+%pi>=<`gwVYyQ#c|B_+m$rj4}b)2B{Z?99|&NOYEAbN2J+(dEcdKCJd`Z}&r3 z8*vZqc=cXp_!4jWm(s2zIai&_yzz}cVaWOVT-7kla&_|pna^0;-m7}SwsADJ1<{`q*CRNxp+{=faLe+pr5RfN?F z78+KLM#Dsf4Tx>G5LI1FtA$^c#)=B3c)Jzao2}> zot6epl1bIZ&heSwVWO%+XwdrM*70T~>DVTl$X63X4H3Uev;7W;C9VzGC^EFXJl9H2 zJz>Mj2THJFHp5B1k`6)ZnSVsaZuUz61tTTPUeL-^812r&>A~po4E@I=eKooVL&m}9 z=$h`_W&D|ofa!#EBeRWKkoXabI#4~L4M7mnh~M7hg$2=H1{7?3kUtG#hl8F!MlZI6 zbjb_C7Q>rnNn84kkmssCG3~_vPN-wMVO8mHh9nO6IYG9;WfnN7YsUko{lY$=o9r?1 zu!+s)MYUj4cLrTs-8Qc>abY38>VMzHt@!S?t0cWA?(OM*a=PjZ+hb8c>eB;=7QG=trk839oIB+7`_)* zMj5}K1=mG%S6V0nv7m9`Xo*yshQGawDbx>4kMW2v+Yt%~B9cz_pF0euO4Lsk=`CtuO{x`zt zY5!RhAC5G?W0DX#vf2Xzj&xVZ_1t4ubA;^v=XGwzl(je;wsf*2EcNNxxn5ylO`U|_(Byifg!Q|K+ljCK zFF_rU&yzp$9$$-?V7j40o=zS7lUpTTVKaWD262 z32&XjJU_~oq&t6t)yU)Vopi|E$y-1~s`NjI=v5hFdSN}kL(#_ZUTl|C)}SQl@EqH| zDnEMKIuzp!@ETs{Z(T*1?V1PA>MP{hsIrwePO7MFWxPaJw-c9FwwLkyqEMq2%X*-~ zQALroiTCt{)FnG~LJ8Rav0%v3lht=+=ry;x_4C)o1pwMELw{R=q;9leI1z&z>2@22 ze`cqpO}KmMT;*Mc77rBe76#iMW>tJT(u&5MQlZXe+w}U5zpu z{e-K<1jGf2&BN@QvLyMblCTvmAE)p4bT$28Ty;p?MomRsJ-*(oSF(hhP8}}=MII+&U+q7KTBG(Tt5P>&TPCm(#FO{^$BeLgC~%RJ{tZjwLuU__2eyg_bY_h*ja=j zEXhjjeQmURMnFU-JXuY{Mh_VZI>Xiz7A46Bc!*~5VK0egD$i!%-Y;DzM zt-LC&Pw~K=)zd<(6w@Tg!k+A;NDvTV!g=MoY7zCO$imN!@QiB?Hwv;YVrUbJt2E3E zqb=QZ?W53k?x@V*f&=ePJ$QFYYpR7rW3F&S&E>NU(*Xy(dBo4m(+)^fHbSf9&rIT} z?YQ`Fmz0|ZBn&4r&0tmP!3`@?9+ThcZ9RzyJ?wafl1a4WnwmoqyX{}VxEX6pPKTzJ zY_BDLW*v==@+HJsQ&`9fb zpIlJz;6eTt;_bs%$T;C2?7hPA83M-}*|CH^cO)k{v%n+H{`?p`6?UW=#P5OQcYLaJ z*GFx;$jULIV>xWCe#N$l61N{GInJT*dByBuLBY1xqD*95)LV-uRa@)n8HRFJ)L(c5 z^leD%#U+r;aC$OQk4!%DR`W>f7{o^M+?{u)#M}vVUHIPl?;<#&YlgU?rD^Hcg6;}c z0kkchdG^uH2P5Ru053QWE&fm_azOj**>-;`Sr1BH)*yIB&oi5CcUQ8Mhhxa8T1S-l zTGVh8G{jqN95&l2*ZLX6Yhb~9^e$}hXu3r6S8;O!o#3&T-Z%6?V7~8*3x{05hn>C_ zol0+}4yL6+iQ6iyx?a&tb4<+KEZUV(yaQbYpP%@HKL=tftvASZ!!iniuOzJJJGMrF%!q%jf~C7f;~n9OY10Sc3A1U=ZulkgUHppc>LTWV+14MinQjP<|6C% z?%fMH$O#;CW>|rC96BOqIra#SOy=t{jLMX5Yu-YR|Huvp@U~1&GghnU9b4WAQTQa?YlbBHV#>fCMdV)@m6}HfAr`}8-{yA zcJA(N(P!;xwTD@spAdnOtCj=qJ<9`uUfUTL9D1Rw{d)}}Z+c&BO22ueW5;mXU-J!H z+Hp_fKphrs4Z^BKwa>g4Kv5e9o6A<;#A=hXaB|HN5(`N-=ed`ZltgeH{vTEE9go%D z_>W&AA#Eu#Dw0ImnJGmmNg{;E9;wX8Dn$v2va*TnO=OiK*<_Q-?n=r?2;b+S_x<_( z{NsMyd2`NnUgtHQvt$>ku@TuIstj<&2OB#@b&T146$@4fzI&8V-(f3x%WEgorP5yu&T<#t)x(B&$NPpt+k&d0w5Wl@1_wZ&z*LP>hEK=f2GS>NKXP=1DI;z zH=NEL_L7mvymX4XB$JqhC{Oj#sB~1^X$99@+YA%zHh<6EH)nrDIw%o$HT>TmCzP@J z24LCWv$M!UoH6uO4o{SzI4zGl+^(;#snBhZAZ~C)eJ39ez1OfNRJT?={&6q* zte>e_kUlR#{5|`l54om?6hD-NVb1SuE6%`Oxrh3Spi}#|a^ut+eqjy<2%hl;W5Ahj zGtT1<3+QMJL~*VHY!^CZY90A!#)1xC?P06cSJsHFIpBd(WsGI|rZv}(Aflk$9o3zC zw=E?A^^j3ky9zB-N{Z6MKt+k?mo9M}u%3q)cLw7WQ$`RNKJD~&EC@#X>(YsUHwmYY zR(@_8_qZ-0ivBsU+m<-oQ-#`zN5nxz_@Y)YWYZWJih-lugRGq5$PnlqcQE}qN#doi zzJXtd7ZwQO^KQfnJ7Emjkm3eU&WyM_NR_53&6mkAg3)t#bPQ>s`n(Z)4y;xE6Z;jf zEQ;}p(A?ov6wX?zy}b7|O&E_wB74Gz^o)$N6El>W{CE^tiokk<7q))Yx1?n$EWaF7 zfT0~`ZchZSu>tFqOv}h9=s{L4dv*3qJap^lsvdsI1#5tGv@_d92$?G|E{LBK=NXA7 z^_OX7rara}sj;|nCnu+9tGi0*V+;f|!|j9R4zKP`usch*DP(3uLnyhE-Y5aeICXV# zf3;oKi-iT~C_tB2t0h>zUtixr-%jMToM(`8hlCXp#CPxR)zyC>1eyKmNbY%e<2#YO z<3Et6jnMraUSE9sAq&dr8DD~k7ur>PvJxYI8nrq2lvWk}(x{jP*a`zsL}cV*nn;dY zPGn=6tiA3tV%{&+JM0q|R=$V0o7p!Ugs(703vj%&bZJ>x)L#|!gBfe7KP}q%nTQ|A zAcuD~aVp~Rpz9X6J#J7ug{?x`DQXreK~R5!nGo+kH+tJEsO$cvN0MnN=-18Rg~5n0 zcp&^=8jda;)H`N~>Nn?Lmu1J)fP_z}DcZWaIPoLZ{d1$4 zKr*Zs;i%%h1*Y2876vv%J9rn$8*62xrNJeKf5L_TeDdofaUW(r#TgI};;XvsK;v|6 zPRXrq1d;g<;B=e%XayRd0Re!JI9_Vf%SUiSATS41R65cpV3ZGNmNYT*OV?6Tkga+s z;g8b9DbRF83=kIhf@^Cla)p6$Z`=q%TQJZ#Z1CuW);)rnI^Dhg;{r=pwDwgpJFxD#X zXZMqzN35{XzRyufEvH`~FS*0sc+c^&=)^Jnhp+PU<<73DU`6gQ7_#ExmWlTt;v)3_ z)Vf=5%zA9Ocvh7mTE-n#3nInn8R82Q5n+#85AUDri;JBxwaRM8n8Xe&v%@fj-QyNg zron~5`BpBZq3PDeF}CT^c0?Q^R9l}P*1|8mG$cn9TS|(HGf5g%rSY|^G{lEYkT+Rc zU0BBU;qnSl+iH4>xR0ofQToIJi(}#ZJn&lH({tzjZ4UWdncT12!7ABRG=IDt**Gl7 zA-hY!^Tt~Cx`=(>MD2-L#%3#tYpj=fE++%3*_qQqANZXgddC2l8DE7*@bz9;u; z0G1-)kvy~WCcXaosF6iCcQKZ4jtRaBR|PyZf(*{}6jVF!VQR`yS4asyGXwo}pS7br zfrB6)zPw)rPAIfd&Q6+d40hq@!GOXwH{4mdZRTJbY(PEMI%57njM3#`rzp;v zPTDKSH{Xmp!nj=ohAW19XLdfF_-N0UtfouYa4fBzuz4uK1J!N$HnfV5I7OZ{ zwV0r-5Q1w4bh$8JI3%x$+E1){Hdg+0#A2v4c^V$&jot_eb;73B(>qsM?hkaP$ues$4`m9b27DjFVx3{x6&AnPhFF*pC$!P1-BKaOf!n5sFY&G74ZvX- z32gY*dxtaTUwzePVJ{K6kU+$NoK*cd?jYiec4KrFy`wHl7Jtof%y7u541a39w@G>y zp*O&)yPL+1=>flDKwQswc#${uLt??$+)XEvm@_iSunUl58_yriJ575hrgiM3>hvXb zziKFJ3;R`ZMKV!Bn!Jpvp zs(jaW5yh5T9eRb<3#~8k(2=XQ>DC-_QNz9^J$)@T)N~`_Y|=KW*C*Z#8SE_RxtcC3 zC~_{NRam4te2p18>19|p4oN7hMGEmqnlA0;u?V!f8?j)eg@{9D-xn$0;BXn%bR@ym zp?x2_F1E>qeN>qOhr^h;JDj4P87fl<6XJd3pX=1#H7trcZaFP5HZFNLHme#9HqCA)>Q z%t&SSS(B4eysv|mWHPf(0_lq>7C-aT1 z?Njp@w(7$zG5#5}l}%D_=e|IcT-d|>7nYNtWB~JZSrp8cVk{OGE`nQsafjLOQCARR z94^K3Bes>>3W$ZKBm2?^80`2ruHEF5bKEguCebR`+(K4H!v;oq8&>A|=F6lr? zH68cSBEN22xSJVuz&4!1O`0&oc@<~3k7gH49hhnka?0dX1nAH9OP;vKB}iHEO}{y` zmV^hOw#asbk7saD@PT`cu$uS{6!u_`Ej>R@l3FhTt3hqH!rK%6vCB+C=8qGT+2k8J z`C_t(D%kjTk=JNjDrz3uf^(y75oqckRkdOY5XEwG@5;!u0 z?X{o1vop`F2i4jfu2EAjL5z+I4|^UMZz8U$Zp(jHMN3<6K3CRnU6^Ed%Jz9~3Xg3` zv>v6IKTMytKE66)VD_7Z89CC~PqACr=w3qw82osNH%^gM!oe=9ce+R!Adu8v*Zd;6#n z2^lWf&iUlEW#}Sxb|6UKmbVs;nc54f>>m5yM+_$2x`?V4i|uG*F|~udB`6Qin>dEI z*{7#J?ut8ejl(bC^=;?Nwvz%#I}o1tzD6kGM)g7tG|QTPnnjYB+Dh=s@Tx^6>zrLw zaM%Up|D`;9ENi=S*r*jjTe4e^#Uq4?tmQo%U>JEwNP1Xz8bt~MMhs?8I2F;Bs8@@W zg5q3b=ek#;oarekp(E>ryYTi^CFF5K@99Z2J=8$GaPHFtcoI%$2QZ+b2A zj)iWWH~PW$Q81Kfm&tV^;3*Q@UlWE_Oj#24BX zWVU{DV@uhL-_L()1%vfii{l6+(0n_DqIMZ9P9$f}3j%ZUy-e*<)FkuUX~XZ_r6b<4 zhfh?0BWYS`-^-&F2s$q$#IzIY%$zGEX5$~8i*Joozfv+cZN`P!_hHBcB^^sJ|DZ+W z@>GM$h2&=>a6hXG_^Kk9iVcexTdZ zq@a>c)WRyqFZj$fx>t?JzzjOZ$V|6|xbVaOF5G}xeh7{*CKOrOX|BcR5FhG3Ha{ZM z&yz6IBo)D2vF2HwN&R!Wup`e|*D$AY(_y@s=5>_^)@(9kd^Yc45^CjVBBS?lzQ1L4 znf!+UR@}L{mzI`X@Pe_HbZnd1_X;Tor!w+m6P`P=RJ+uA z&cX)qs9TaSV=!CVoQf8isCXgg!)g`?=BQfGMqsx6{)$w)Zj~0%KQ8t7v39$P$%25y z8qJ&9_lA#-bk3tFdCFOUWMY`JBRsz50#)heCgDQ2W6v($4v!#+5?-mPMwcIbTUPt7 z?EXEEw}VgaC*`u~*I&E8)+4N0W~wH?f+_dvEx|mc?Q0l68Eto_n|_ClaR0?M`c+8F zewcLb36~?m^sHAw3M$pnc;&LKQ$s5d?!G93#3!wnRig>AoiVYROc3fRpjE_sHS1c$ zzk>t$p4QTT)GxDn$Qdt%HI}lrEFd|(szv3P?KQu;1rTb({Lz(lr6S?I&8JozCBv)H z?^(OK;PU-4p2N%IjEW7L2cI0!RuQr*KjimPREHE9Z9 zl~k?!J{}3VC~HN4x;Ou2F0H>JnDS1LDCvlWTO8>q-M* zW#V`IH=4gJlpVd=@vtlNl!p5ABW?O8Q`^FS)spyk5R8CEY*E@N3k|)?)R;GE77dT2 zHhmwNGaqXW+2VzGqTAFhaS74B!#VMf+G)(v09Ef8HjGPZ!qKN%j~RbOUvG8terO2h z;?Q*V!uNP>=Tn$(JnA3rIBfD)kW}{$#dJEMaXhc4*J$(U}KP$Een!H+p!fxa&oVl6NMwF3Rz&_vh}LR1v^@K2vLwx)c|2r2O9; zh9bzpH}<;XgQ+PgOx~QB(vWBLc>36h(HwAb5~r_KCDWwKYSXe-?@3uJeDYOa`|djh zdxg%*jeb55ft5zC9)(ahyx18uP(Wx3JyqYkf_ACa^V{+`$VOL_Ixt&E~e%G5HC$gtD2kR7bI7C3M0wl&LY#6kJbL)ITb$lPS z)x9VqO5AR!bo*(1^LPj5wjrxIHp*D5!6XZr;gE{wk2pyjx#L;oAurIuVJx1NK@Qv3 z5ybg;J+kZljM+%(efJBvTd`5Gj%qgX<)ISp!WO}Sw>5FW0c%(q2xBvb#UMxBiW>Bv#i|BmBoQAZldGrFG2DTgS{MV%5z=7fd1Vzy`!>0KIs(kMOQp|CpHWTcy$AM+2`)`c!cpQSFbvoK!y8&~ZXC?{XJsKvE z`kEdICl{>>`~lnXoT?c3cR ziCTJkKkOuI`YiH=6Z!qjtA|IK`)BRvrjXFlXFa>ZjL}qHM;1{A6sMsml#*av%np5g zxWoQZdhn+ZMK{vP!k)I8YE=ehdr9R$&TdRmN$IMEJ+1&@2R^N@ur(;yS2kg3DeULD z8`)FRPOHrb(mzUZg`~d}E68ufniWZU&Ci`k8a1t!X>ay6*4ju-3B&avaS*9UBRN&H z-ow-arNg#y=^C{W4u3TbtyT~NoP_;OB2NIwsdqoxG7(dgEb_XyHIUeb0asJ~v9&r| z9-+E8zjb?<3sIATjS1Rpee)A-4)MRoTjNab_DxB_WcvmAG{Uc#ykgHv0xg5d{_JP( z7i0-SUS^T6-Mtaw`fqL~#AVx_yiB0*youI@AchWh7&eaP^6uK`y-9~Y;BuV7dfOBP zlR@sfX>N$bcx;vO0RL%Tjc}wAguPiWZGCW3A$CfNFvhS@ZV-+b5QFf(mH)2z_)Fee z91+7(WYpB#;O6NXKR=q+hw%T_Gt?l!h8C7k%OJA9+q!T@yG47G)Oy+ZgMAJAAsyuQ zYdb-zH|qKQ=~L9)sJz;D8_`9|b!@eVo0lxU3+ZQe4E!Zzyq_Pea+ADisC|UEx5z=a zuyt%SFkz50kaNzn0{%JF^RcKgd&T-^FkM;)Y$9EQ43t;GDzkMg^mHJySA?0()4nWy zAkt=rV_RT$S6c*uWCyN>3-<)vIegpI!X9lFqc!c(`+z(nDi$AS15@J^UK{zn2(q5} zZcaLvliMIgBYTNMeEpj25S7fd1a5q}IQFGuML!m#PziQNcH7`|-A#m*+R3XFVs|D>te%r1JyBZpUnC*|Pd zNlE+L23GKlfkeO=@oEpo5eou{-(j~d?p~foMNH}Kb-w(Wd+ zQU+o;z_CMnX6$uqN#)t0W1SPgj)5XXzPUt^MFXxMLRoT6yFy&_*3M!TRTyi~wu@zD z!YGBE)Y^HdAE=vAlDy1BD>KM|ks=Mg#bZZ)OCo&y`KCl-Oi8VcXduoByf5)kI_%5c z7I`kqs}j46d9+fs?;yxDm~3=)@_>ASNdAx$QD;*lFg;&su(Ql*%Bxv~RE1fuv%vM{ zO>X1rRid)}mk^QC62|%9Y7fk0AL0UdIIG-pSx#iiz~ZtBJ`3RS;&ctXI`~P_8A_Z3 zrql(mqV|9Y%EEm59k6_$o>>mkTUs$q*ckNuMkOvL*2JY?l9VZ?WsG#dFaAVbbZt%q z`wwj1(uimpNdAGvG6MRY+9KBsR1k*+{I~XlrjN&bwBSlB4;|CE161NUXEgTB+$c|DJd?8=GO>U`xSkpu z1VC~_fy1QDxGYtMnFUv68O$F9BO6qFVfklnZfyNlBzs-hv%y?TX4qcf%g%~)5O1iQ zb+xmzb9KGCC`PM2%vgIY4Kz{I$XwaAc0}KU*4pMz(OZqZ)j#@)*)NS9@*0*P^l>%0 ziQaL|0m;`-Z;s_zFVi#%hEJpsBQY6}2f6zCSAP2CmvHwTp;-g%v1@q;8CYaj39-E) z%~o3+!nY0sT0J)7jL8Q1OTByOD-mT= zEA_C+UblaiwR$d{2SEV@RU2mB46nxQM1K(D+Up3a#ft*U=<08NL6zwxbpK(x7af=Agd({V5 zOWDhp=mGRU&njtbKk3qz?V#YF6~Y4?*U`a2>=#o7JKAbNX@PZ|n;Zg2h&tEp`xfm) zyI8~I6t%%PdhXWL)5G8X;qWTg^&lxK71JLC15g%#&yZ>yVhGRPbh-Vl;a>8oJ%Qi| zA`{Jtcq2y%P~4ID*|4$|eOXeZ^H4P3!tON&`eM68|mZT}&nS&yi1A+Bxb9y6b&l2F=P~hZL?6UPfqy; zP!=0EB;uJ@lYVFf4}JOa1%@YMEdpLg(pDg+gbLZTj)&7bqd=QaxfFpMNCVQ#tj;qe zmG2|!tz}lgh`!3EgwQ$Dg@rsjG)4Zr%R$sT|W5OkAB$ zXrztL9Ok@$Hus5z$w*8Xr~@9Z-?brdO+_f?3~abZiw%iT$04T-_4o6t_tPG1+fIuf=-Ms4=fPqRQgJa9c`jb<=pspVLJZu_Vdu@(J>ORH8HHyI4 zOI+q`G$!aPrp|TDfL*Ce-=Y-^FQ3z$*olS0sJq+(_p^C8pY!_c?VlZz1jm9^7smi0 zr%R-$AQnoFn^azWvcoI3P6txT{)rV{vM;P;KdG?>;f#<-fQsgYsl^hqHUnY&Th=c z4g2!l=;sdBo?o7WkI7ie2=QMHjg9qrX7Klghs)@1d>hW`7Z8yHwHSSWi`89Ut84k% zlZ^o}Pq1K1-n)$F-m5 z0xH?3Yx}QawRB)Pl@eeTTQj9onP`~ad|iwn|L_~T&JqU@sny^Ok9+FaK=gOyjdu3J zFlxMSa;dz@zHfy$XX-@EZ!qW3*fK5!OLB4F55scklUl$cA3l6|$l1!;kE-3ZzkHeL z9`P!3sw+@l3JhwxU5%{GvI*eGDqs2#m^@DBlqkWm`xm-3*2u z7G>Z%D%Lz3?|d#KChbao-#CS%F*TXYmVPTQT7OT^t?z}zApg86JCg8*YHEV*f~CPG zl0bRG8BxvHXT7YUeW51B2xrzg`0PT<|H3Mz7%25;i1Oxd@F*Z>hT!#v4)8IYYuLPP zrkcI%dm)FXYuv&3GkWjU)j`$ij!7Lox`YYFu!NG-*mGS>N=z((oGtr>P`YNuF{S_n>1ybuBwarz5Zrq#7$W$t;qIz|AEx4@VwcjMAtDsMT14p`0s1VzAv%P z4`1;}bNrBULR}s9FCL$-d&=1>Y*BY%=%3NN)j&&wK@L)-+o0bOi#++9SJC3zS9Gh4 z9HcZ$sFWYEHShyI=lrCqWM3K7H0QSt5|Cr-}FsXkJ1G!$S<*bxUq| zIHX7am<|sl#+~Xg)4p&%O5*15ZO;8$5J!RiV$mU=JFm5m1*xmsTWX`@OUQERdQM*Q z5y9LYxCG}7F}MBw{p%F&ZfwF4EL_B0tbbO7LWZ#sbfL*IJxR4=1|vqiO~v9}e4#u9 zW7?;k`Gtg1I!Mg#zn`fK8ja_k9|$7{8GU>a#?-b8JP$(qxE%?U^XKN(rDAP@d2@Dz zMrxb$=iYEdoQ&6)sxmO2EiEp-Qo`P(NtmRj*46*HfFJnN8!muAU2VRiVDoC5$ixE! ziyl=(W096KN^~C6^v|-->e&S3>73q(AQ{Wk)G=Q`5JCA%c$+|ZX><6!t94*5Y9JCx z|E?UachXbC1h%3Su7Iug-MEK^pM;`Wl zsM9mjN(}SGf^}xVffV&psu2asTpcFL_v1#hxmX_ka=q+{PB#k;482TeM^e3NN4_Z9 zsLYgU?tE_M*a8`?tICSzPtp{H}V9f&_ZK-_)U~ivAoI8 zNe7{Fc>}-$R~FstVi8rW#OK({{vYk<-E1j)g*o2x%<#u!tb)wdzrgKITho0u$HQvh zcG2Gay0bXn;v#cVQ<{rbFxIumPs$Wh${0ej{evUwq)g3}l%EdnY=E*$hVqzW z)<^rR!+D8)%wrQB?e~c*0(m>?$y|C}_u?jtQ0fl*e8_uxd$oC2dN%$?Pkg|eI4I~b z;-to`YuNJCBm0+I8WjnG=?78vW*fz$T1J_XZYEe+#WLZD6$tI$+b*aR?_Sq> zN#4@PO@9S?*|9pf?!|4Bt~d5z8q7;u_Iv(~*(hoxzS)f0aox|81OqLHPP`MR<0I4{ zj62%`nNsyaHXE(*2atKtf_uH4T}<}ZzSwPty6BOkmIlB(yS-8MBQKux!S{LiD$9oR zl9`Gis37mq@JkPqW${QVT>i};r&Jj*A!i^<+%%V7pJ{zGnyv0osq)3B+66>ufS)qu zAJiPZSq=_FIuID8&r%Hl(-Z!t{3lKmy1^(NOC~~r6T#?_*c_KY1e~i$`+hQltUK;) zr(ulhw2I#B$NJ&F>%J6c6eX)10z3KRI&q5SzqR@Sydx6hUf(aynEA3$$H>7)2)s^g zMKljJ5#HEtwk6bU+fZzGfhWOnRTg+d3Dgm14jji{?*Qy2!&NCjQW zz+Y!{wBzwx9p=~6d2Oh8(^~Q3DA%NvO8lUZzT2@@Q;qJd6)Hn|6<_-L(%!kguIiyr zO$C&@2u2gWTeLHIU^6-7=Cez8dM_}w>#WN_M6aH zzni+c$py>c%;VQCs>99RB#dP2S6f`q3l9)R0qefl71z~&Z|j{GWNq(@V;p~&_H*)b za2g;|ObHRa!#BKbVnqy0>S9VX_E2|{HpIGrA9k7sD*n-4y2#xN51@6h&Ja&Uyt8q> zzg^)nHNo|P)k+InC(k#~#jxV3`QPqtZ>^x~eCF8QuEUg_1?l9+5+}X4ZMqF^@V67l z#Gs@WwR;|3FZ1clJ%xpW(CI~o0n38&$#*3tY>)b$fLUM$^T58X{^qG@`yMS}dtFm4 z(SZ=+b367Q%hzDuWJ`^9%wJB^hDX{i#$|4(SR?evqvK{fh_Q`7T0)M4>bjD{8h-8Y zg^rm)H#Smztot98B&|?A5tV#>rv%2lI5Hx=M{3@c{BDGONMF8l z>^|LN-zLzpSXvOyUzZvZ=_;3O7 z0)r}RX{vSvF_i2i3B|h)7y2_rW!J1#3*NrSOUCp6e)ky!Ri`cBPKgFIbSkcOKg+gD6%aA;!B-iWw^C0ikckXTsQQT6uRT8U!AKRNWSTJ=*wB(c!OmzD0)FJyr%vB|DPcJWyj@v_7G(j z$g|h2VdIYE2*Y-c+gzc(ru7G(z2lc5shAe9pE^eJo3V>xP~LcXC6%1?e=K1LMVfdz z)e~d!-%6UkRN)nWPj`sjVZ5tVJi}>*kTPZdu8jl{Y_3XBwk*|QQcss2TS1;}0LIv)x+AM@bteG~xPJOUxGZ?3POLL9;wu83s ztkoCTO3-o9hKG&%H12_?s!xdajMBDzyG}S}4_9gvCY_qlEvVcYmQKZ~C@5a)RkY=p zEuc-Z^I#p9IhMn1@-u7Ufs=3MF^W=>$yL-wJDy2yabLy{aJ9mP1@he)XP!A7MyE}E z!l|;*q?ROeiD$3+yO{}^>;Jnz-OI_z*}DTA*`OCPd9PdAG9k*iA%0zW4f?)qX>YJJ z>bF2bru{>zaR6ji7-aYPw9T*GgnDG+)!&y$61tbE3(i;l?Be_K%(?2U>X6D9Z-(lu z0@3|WQ5V%kJYQLE8W!6qIZuq4{r@R{G%j8=-qTbt&QCvtkhVsBFTX?b;j|C(^F`{@ z*O=Y0E(Go}sGZtmWzvb=P->Kfb(f3uifgQ`O}%Ji<+-g}QP&tl2Mc!|9kNLlkn(sA z$C9c3c8ZbD+AMD`Oj`d;5Qewr@w<`4MBJZCc2-3sL3P%>8d zmto~7HrPGu%9<6zS#u%jl#!MLSKKTO5(XX(x24h^$`1SLXDI@RhAQ9Fx(+UWot&JOtFGa~(X zlz$1|^qV^iAWi23Hv7%i$+qq17T^!&s?|5_C|b_=QkXH@mR!ceXuVjkURiyG`s>vm z>wIk+$qsua8+ze(WcpAiz>xMsABbt|eN(usgtop$C%GYx!kn?jzj;jB|87xaP`|`6 z{+6Y>tGnB|_ZG#?Lv`uz#vLx*f{Z#bJF<%YEuz=AsJm(tgy?@P`T7?<5SP**oJS7psFD=4VKb%DLzU|F1z`tG=3{G**lhih%pxXmT=klJT@9*0Um2etQ@ z_J!P^8z_)B(L#tg&6*-TEiE*HKC)i{x!rwN#ZRH2e(ae9=}*)jdQbPYatEc6>K=c? zx$`#K67g?JBt1;D@fZav5dj$14A#fEi_*RPY7b21iqpZy&?pMfO#L8*C-;nh3TJwn z{q~WdgRVn^8RuS_HGU`UUg?^cQSg^y_-sm?l~R#8q(}tbR9<_WIM%rLJD@(|6!g)$ z5VXWlx0PQN+l16fVn42MDmZ*sDELt>4PqevCsGp-_n$(!`V_y0F7L;89x@Gz?-gW} zBR?p4A_l_Pc*x)|d&S<)zP@pXS2pNFGLa`2pA8(`GnL1=kkL$6lVn=j0xP+-4Z`03LaAX9&{hnCIvqP>K4Y1RCq}?#SOz)<#mGqn8AkU$!MVL7( zxfQC>H%njNt+&x8@z%oKA+qTX|Lh{3Df%*7m}@+_>eJw|BOFz?R^Fk*4eZ2s#^4br z{GW>x<;#N)+*8|twkU2@6a|?yQZ%t(u=CSYva2q%yQW$uZ2S3IZwM28E*UlSq|Tn6 z1yrv4rqaTKp{sk6m#98zoVv67$AA9llk8J~6#|m|E>~0KJoy~w=ogHVwho*Rx?_%-rw1M6VMYJW>Smr9|v=aSnkVK1yBo4YotBz zE`T!9Og)neC35Z7T#J!c*tu(q@%3GU~lE)af ztaw)ZINhP=wyOIaeQ|F?tP=}?PgYz0QEs2zjCJ`(sU~5e|{$_ zX*I8d+QS$?@V#J_yv&B_NFc+fR=IO|s<^_<5a}7p&0-F;|NU~fk1mSd~!+seQ6JQI7ur+10Ir@pv@OA~R z-&%$F@>eD$gXGNZ?d?JTw9`~1pbgd{p9s-94FMO^H=8%UdGbN(qwS4m{sUCU^{sip z=HQDcCCL_69uN~XWv3DUnbK#iW`JIKA*nLrFwPh~v49UpQkwXBI`RI*UnH$?KAsZ} z`bG2n(V$gN@LG>-weOYuE>pwG4039y!iYLteFN6Z!k$G0=AUdEdUAp(=6P*E`CsWA zo&)i@b>^2c$go_L-TZaMXM&nYg-?kbHn(g#L zya@Hc!bKe1>xD+&frUjf>&h=gBrCuc_@C<@U=A`%YSqGeHiEG*TfHoT8NoyTKYEOf zjqOAHG7(FaO76Z9kpe|+nW1`%===HS#2^RXHuU?qsI4XGZwu_rNv&wLy+5GI)vh3p zcT==?{#rc`rxsnZETFnV>I!MRldwZAptTm9Td=X>cI18+yzMQgs~Lpt?9OgjDbUK+ zD$+wB!I%%Rud!i#OL-|?%-^^Kr3v`ZAT2<1q?_W|1pMtXNfBqh-RR<2(d8+fGdOqf! zSFbGnKd$kRe3{XMKCcdG1o=2=zmd{Vr{437Ym@F%VhM#12LY}I>RT(Kf4RC}yO!BM zfk^sK3kA;_zFiA-8_{jQ8qH|ZCwZEKh ztU1+SCp>!aa1*WeK~q0W7c@vxr-8FHr`jZzG)%pEMMs-U3}vd@BTkBeE`NR+n3|4& zJQcdNgTz>+&p$f5(9Nva`)!j?V1YcM7grfFxLk-Ih{{~az(Q8Sfp?G`Z|?hrCxC*X z1@K#FD1rac^!Fi>)MYtU7B)8Y-G=r*iO)7l{mFU{N%Y8T?0EXCYO?;dKL1X7xFs?1 zh;3O<@`zqNe+fgC1ak=lCXPl23#jDX=NjvOiB58!Wv@hoF){sp{|-ay*|B$&nxqx2 ze+25;9ECmIqIrx0C!Z5-=PJ=hi5NZba{`wIJnq?IF-9GMNcG(D>Wt-_y*2Jnc@lE{ z$i?{JAo+%o&jebRTPfsuj6eb*o=_M)&eP&r3`puZYq*skKz3q=EG!gX50@Yq2QXc6 zYfq&H%tc-+0XPuevo=*{%o6H{SjcMI!`<-&LjmI??$ti4%hQYdFf1fKDweTs-> zow;9$%b`=Wk4^VEHwr+Ii0}M7GYDcbpqB_q1?8w^BOkok1IJWse ze`9u-bH*r*8+eEVDUJctsw+_h@Ad~TIG9hotx(}nPta84!pj9?lG6{1@I*m}zWK*p zEz6wI&C|6taR~^?qB78G2VZ9<{1xWKLY~^m)j49GHCH5D>c%Htr9%H>!R{HY{(QB7 z(C5$`Z+e{cvTd+|smAr2-qE0lqnY-K&av6iPk08M^mclk&kJ$O^W8*=1^%MjDV!VZ0an}ke z24?SH5M1|Wsw6sc2UpTw6jT{F(puGQ$(YOp?TSGI_qGcE8js}v`R|l+EUe7@Mx4&y zhb!C2*)Q)z_bEk72D!&)8b3_^9jJbU4|Ly7iq9MM?7r{)PYZxIWq!J*w*hV+BTLYH zKg|55g~A!06K3;+wKh2-D1Q6^U!3jv;2|Wz){nbP-mLx$om2weHAixQYO?Gkld=qX z$mtO3eMACtcN2<^lA8iUvs9nM#%347wL+?qh!`fbd*&3|w!ZliZ4(yAXf^gQi80GP z{=N^@D3em)<02+^ts#95yRkg6ymakTCPg`aL4=IF=!d$=8EE1|h1k&P!}oyn^EC&V#*u))&>b zAgZn0iGL?%$D^N~k$(EtoMdwS0eAh}&4V<+3R2f4eF_>7g9-njzu=Zr?zX|kupK&b z+LMHRoJMWK6LHAt*y7qh;qVG`rN&#Gz#oMFkaAvF8GrHba7qd$tcg!MDPzJuE0FTfnV(HnGYSkYtb-^Z@IInG8-UohEu z+Aa4-Mpu77`+5nISsDz_sMG_$2cxP*$k$@5{Llo>cg`LCR*Zh6*0H>vt5@R&k65}Q z@D4FYZY4)3kW>Ai!BH!iaN|Zj#59Bx{@Aktu}u*_^m`m$^@*y8oln!APlf@CJ+J)2yqnTF3rcv%TR=cC;1PT`Q>T={xY}^XJe0l@cW3ljZ&8MMaMx zxTxD~3PSI_0=4ebk0(*=Y4|HGJ6;zeU4%M1y!%T+r}3*kxA%%yx|z)(=F^!#dmxSy z;x1c`3AxTq%5kWfJPrMOb7ozFNQ+YyXf~4zTxFKclueq16sp|qspTB$`6Fwi_wy(G zA0m$u3d{SgXcs;67gJ^xVY67ptOZzESfHL1=Hua5WE;vF-c3^%aS{c))et2?AtLja z5sN1T6;Q%vZ1hj(IC__tdNlJxPF;jU+QZGH@G*GCH%SO{pg~*tQs&Xuh5*>6c!dv(70_Mn#fl2Pp1; zmdUzi5xA8F+#UsL?GSu?dLYR}(4K#1mOHhFLhCg4XExG|2JY|k1{AjzHSw5QcZBp=Di3=@5!k;5T;rx()bzn7GsZ; zl*Anm&J8o026BdLmS_zimm#=vrc*=?!)1?IXNk|(mdEPUd;Yc z+0~g>#cN+M>+HnBiy(^AM@P=9e#^*+I_>u(OZ!4tkNKoj$AbgsIV!XR&fYd=IYCGz9?j098m~>6XE&Tlds$>fnAd zQuK+IWQpilGg+iJd^8VR`0*nmPru{i{f26fp-CxZxCUg0G4my#JsrxP5u3?di%5Ik zF&|R9hHgi(6FQ*MFCUrh>nnnas|T@1+Hon4Sl;WoS3EkRK1K8~wgxtu-vSvq< z#>+Z7S@}D&>Twu3`p3kP@~T`3r%AE#k7%&)THov`NSf{pD@~=lhH!!x4826H`Rz&q zpv6sz9Yy6ha`oBbSZmDsb*hM#GFA>b))1XSM`TpnfObN@O?_W6!w@&aJt_`QR+!Y zd)$KRm|A>M1G!H}+GlT9g;k>bnQasrVP})(^%5mDgZnIW`Fdr9*dB=-q$E|GUHy2T z8Hzp|`+Li@`q(qOeHA4X?Hm-hK59>{@G7>SnSY zLm?R+OOd72Dm<*m%yieF)7T=x*ucah;gvJVs>FfeTjEqPTB=x)E7c+TlO!57cPFuL zgTzDG2ASE$(eIn5+K~ODx;pAN<~|SRr6|tmc`eYyRT|OmlWo2$s~Y_BnX)6w@tfRC z?X_(~S_!vTQmc8$EJQk?> z0Y&JZtq^BWBsmC$P$cZdY}nvzM(cOW#F+XZg~vW&y0GoEx(=B)SgP%H{ceQ^-r$ke zPjayMxaeQTPv4WgOPfRCPRmp6gw zeTp-iB!sxilH8A(DT14V7^i>Dx|R>Hx;Dg}Pv@-_dq|yiJCSAhhGyTXJwiKL)W*ag zQj_#^Ge)>HGR&DH#mWv_M=N9G0*TLkMnO6~x+@+vuiBn#NtOp|1;d<c8E!r%_T@ z|5bj%Dzxb2kw)8ZTUe`6mofQqhg|l?!w8kzF1P2I(^2;&B$!t_uF+4nbI``TR#zG` zR&rx@kQxCsK5f9O>iE{KsbID^#Z$1{w;nYp3#{M!-xc2h=r5Y~H7SFk z{)xAgTlt@RY(Po0js&zY7ME@zLiM$&L?oAD&Kt?s;k$o#$7fikhiL}IBpe3(g%af- z3%4jD1!k=}k-qi&OtVtlxmMvo>=pO*c-j~4@$hT*FEtNWsuOs4^5ViBjgI`g@xsan zF0H%HF7W*NVS4XM_5L^RF$RQgHfxXFr>jG^;`2Ez^OfyLc4wmPgy_-}sm zPmx2oK0$t5$mqVT$ALW7toG_<1aUPxcAHxeOLn7mH8roT3jQ)`CLC7QR^ zT09p%B!2o=DF4mEgfsj|l_A|?LWJbT9BZda9O@8&mM;?T zeDUO-TM&$&-a?<I7lC@SWk9c)(#6|;GjD!q206p% zb^`BdryW3oujyM_*8UZOJY0_-3FVzkYkMWJqxB#7XrI1qulAFs=ZWUiam2tYTE(M`UX&?$*B9!Xz?UQ6(hln_(bvl3|UNVOdPN zD0i5;9o4=HHWT&WVTDwQJ6iG4pJ-KSvX0*>b5<9gH)n|3LJX;YTYxLB!4#n$l;4dG z{Ye+yoF5-RE^hgh0okRig zb8QKxjzy(ot-{)2v4zd#83}kB4#sYJb@o+e0nZ(7s!nGjEd!8Y!Z8>F>CM+(6>jk=oa-B~%I( z!^jyDY&!5Kj$7hWUb>o_N#<)j_LUV>j@^OSh1k1Hr#Q)#ZrJdMB>If$o}F~gz$EXK z5A(hE_ehdsxtaE=_PUO}b1zd;9A0xLZ_&rr#l-Kz>{GI{+y<`%d5?Wiol&uO*k63< zp161?m{XBKje2GQ>M(m( z;&qDjEWLlik~(fXZTH#4UEMEhr=&`m;x_9ifj;iKPcBYX@|(6XDcXqz7zZ?oJ%-kN zKPK6PMFctaU})SOaT=#yhke7a1FNedCmjWe_ta}5O)X2@t1{NQyIt$gp@%?DEN1=m z*KEu}8u6mr<*MSX0V7VP-fZFOlO~(^_~2RoRktW4$X%OL>*f~j9Oj*2VMV3?bTzxWi!)wfU#atcN=md5 zIF#l}`JAYCk@+Q+wga^}x#BOothi8oKDLXZQ;~g+pWc37OzsCn5#?vI8t+<{ zE z=Fej)x0_-$Do0uTvt)+Ld-XzuJ+iFz;Q zvsZfDvTJ-XJhAzh=^;vh?$_C*^`DiNN;B1sM{7Aa1?#=xT@Q29j~VCFrH4H18L3`3 zH2C}0pSR(=thu$rUSt8Uri|zo%_DO zkDv3$Ih{WEe6II3Uf1ino>Lm$0yJtXY&DtCyy=a~U*eJ-_``F(Rin<`Id@4nTn6geQa-;qz=V4PHkcjbtG$vgmPFe3?l&&8U`J+QjDhLaZupZRr!qji!^_CYOZ_5tU35(2Yg7>df-L+Ky#rD5pKHi@V+! zFKc`mW(X@6NFNEC7>N*)CAUbe+y8doPyf4sFTv+GPhFV#=!cOWd2%d`_c1E0Y0fy%ZS1H zLUSxSF4VIu-p&rSV1u;+EK(cs{(LGb3JYC+f9D%Va*%P!f39DvTJ$@6T!R%82~Z=) zr45y`!bQFcGZCh3cVZGGj~vONaiSm$CI8IgjbE16&|119+c>_kJao(0GNxat7K%FF zh+8^A3hK$hdpyee!A5UH#P;gk%A(W6k>06=`k3ZY{qTF6s`bf$Y)Dugx2z*|ev2x^ ziwd-wMMYp9U7LS9@qsF@+m%_PR#C>*FQ@alUpqeZ_otFtq&SCWap$qN@i|dM@_ox0 z^E1c$EHfl@@OdUQ|NA)nFBPX6i}&7A{nHB#Q<-nn6JZ zu|4(mg1?ew8j+=JreoGph|Iqo>xs%MU(jd5X^S;dV&0v_>Qa8@;i^g8o8H^kip6AZ zC&G0AydYfxrEvV0(wFG*5r=&$;Z6tXkhLH%?A{NAMv|H>_u=(x0blhPkNM<%dN!Ng zyg8cQ8OkL9Rpv)`RR#(TgquhQE8Iaw!r+gy9ZK(-Gd&o~^j=SvOu{$$_xC3&bYE!u z=E|QQMtye|tY4!q*Qb!0$d6D}<6lkj<7VR&?nO&A&&P3Jls13pOI?D6XPsnI~D*`-!kS5?>3aV zDh2Vfo~dO{#4$v~~d`4VO$p5XQM_TQydIRCEM7KXJbH!*B`tIu#>r zjwfr!?eqO3#f@ev!f^UG*wDV<_v>!z=pjA)I-m=F(rKsZZevIApeH7yJ~`+z1=wV} z8k|q9ai#`hEYp~o0X*ELuctBn>39j>?JgS~rhuGN$^&c$hR~WuUG`awT&K-DZMR6J z6u!mt?~Plk9a#dQL~Q8f0~I^xc!$d&^>>aBe|df3p-Zu}VlFMsiRHdkTd%j_ z{7t#T}O3L!~XM^MAe9zEI z+Xxoz7H2rQiCvd(!?jNiS6y6q4u&4z^0WN1_WhL)qH5|)8jf=bB%L>#H|FbF65nqhScPf(g$$XI`RYB0a$_qUtwe!c~{Qwj`&5hpvYIbWAF` z&&SatLqTC4O%m`wQ22QwKp?iFIf>gZ;dtjR%ss;@S>LtZnU|0)43AF(iWt(kty(1+ zGPn$yy;FoEFjg1aGbQQhKc8k>Q@}mYphZ34#bt5lVZF4;#Rl#M6Ykq=_DeLVE2&YtM%y2EzHkL zE$S1K8zmFQ0P|~5^7I|c=WpGZlUFLy=+rfh>DY3sO9 zKC=H?9_*{V{<~j(YMlET7hKOucZsR(UA1JMf9|$%I#!S&<%`O%IvkLI<&K{{N6^c9 z%s%NH=h(GN#o9>n(YcalFJq=FcXYoE5o}M`SGqP<2P990kPa=@*8hzJ zb#?kn4eW5ue-JMM3Z5YcZ4i($PsY2^8&`9sfbeq ztz@*+n29e78cpAW)t_W!pcO<I!19k- z2AUtn>FRJJuahObk`VbMrq2>k_hTYG%zXU8_`t!>(o{Ch{PC>nsIS38`0`oWX=18vMf2;k$gnDc}CeRcjP6%1>n)!O8#* zJ&5{z-j?cxfjU!lb#+9|8%MY~VDbd&7A2H+v)ss$3K=Z1BmKM2{&mKn6KD?bl!sS0 ze3Vmq^K)e}pKRkUc$9&5II-j#zhp3<<$zSy zu80q+!J^+*E_{8$dNcWx2SojBU)|S+6MQG9rkuoO{d|olA2tuXOP|d_U&(M@=kib5 zA+N$&@sLEt7@qUmF3!%gBh5*;B6vVC(WLO_X8vi6t(^r=L!1V(r%cG&;HFevMS?oc%-n$lEl7p0j4CP<9 zb;_z8+2zAlqVXD~^Ky~g6upzsh=NwKWGsz(3@I)9Jszl#`FAhhc^!{vLyv%4$>cJA z5qKxw*jd-s)}|}A_<0VYo`I{7Q-q9}75CdmOCcR0C&G8s+is|v>9v{0k;|K{pcG8h zMc12wx7Hjd5?(VBdg6K0Pcj1dTT1h<abqGAweRD~%=hO| zRO=9}2O{h8^ttF8;l|mps<#(;RwuIRDN<2lLzVd8{H7p}9~Y=(4Ri|~*@wS>cTgHwUrBuxvEDjC;%X5jOL%D4-5muN zH1Wokq@(}yP%lQ zJM)umF_@h@j{DZSXQWsGqwBNkv43D)<|9BolGh|2;v07pINzfD#!_$^OO zPfvrJCmi3?upp8irguOnip_iFrw~IGE-QyW^$;(75r7L`>YbGLy*8se0*%YM00IGH{A5_0J~ZOH=U9` zPiatL_3=nk4H4xcV}fA%#Yc(lX(wsqJT|8M4;r^-BH7Hri53#&D|;5|Al|U>UYFVkNPrHUTLwMifmJ~uCEBPd2N}d;F0$R z`_$aqEq?VG8B6fR5tI1+S+EcAKCCFyC)@Zh2WmoF29KSMyt|_+0r8@Q_`f|-Gt??= zIX+kNLhqQ)tEDyiJW#EQRteX?3m!d&vW{~*!H-bFx*Q*~dJnW3nioTV$RJ~QjMg-d zJ3R`i+=xGyn^`0#ON%?i%=C)eL|07wS!>b@YDxwr%+e|W_5)O2{C&3tMBCkNFJOOb z@Ix={jB)Y@70tbt>`xr0Mn)`fWvm;fdNE~^qfqtQS*rad4?`6+{>Jk9sl{#YzI|Im zkpXpC!ipEM(1!(Ic(avZYxqAF&5N6Z65rLO*UhKkIKXxzx44KF3d6s>2(SaX+Ru&` zOj^yW!LMlw2Ug^+`numq-^i>ZBCaj>jVp83aVq>=7EDMx}CFQx9^I^7<(}TSs z93Vto!Hc@v8?!K}-epa%DB*l5jJz&g)&vnjKRiuAR6*=AYi!Cxx4gKsN}aCRerH>? z_BQ@Gc;havC;XN}{`8HhK#Z}LJ7lo;o>X>ejJGEEMeD89ne;`LKo#p=rsyD_V!CgB z=4E&%ME}gWZuG<;BIVSje=K8K`ZwoxT$KS^Ir3Ro30$S6v-EZV5snVfE54-Nj=Fbh z9`}-Tl4=*!a*=k~z;;*@)_!{6&UfpI)(Xq|Q~KFr-v#CW4ybYoa@Wj4k`;u-%~N1n zZ7pP&4c*dLNO~tkFlpmXKQ5MZ5Sf!g`CBGR{I}QNs>&OI<^N8iR(N8pb9`>{rM}ke zvUfI7J9F`16-+Rq93=_shKtniW-bnYtzVih-7X*2HKAL2+G0+I$P`rr50-ZjtfdYy zw{n*Kb<=P|fj1y7R{DFWEA?^j3`Wqie%kixA8}E+LB$iIF>GbNzv96Fi4!GlSu~Tl zHbmZIgNv4{bVu6=mVD+1bmFl8boU**99Ea@=4PE^ruFne>L|v4a^(sx9Mb<%2h5BD zPO(?J^|zlDQv=jfmyd+`xHE;$+x=wgc&kf9Spq*H|ET0H>sNStg={q&JwSLqFpY5v z3ac%(*s_l8>+M8CI7G~W;?gD8YHDR7t_262o@GGV%u6WkA}y_~KrA&+4=WD7i&oXS zm{e3_!X20zu16ej;Jyr4Hb>*5a*Y+o-XB)VdvsCi1|OKhaXMVTlMgifc^|2%e;ked zY~h{m|IvlD@?q-bc(A(_Ee=KDmSspXJ`6f{9re2FsLnK0+=#4IPz3ueUF)M&c?W-7 z{Z0D-v%~-6+zL%v#3QEaXUPg?kH;_^qH2_e{;8IA#*gN{Dh|X)?h7$Kw7!*3G`9YO zKEnrvB+|e2g=OGP9@=ZiHkSw$FRhHkT!M%HS=8fBP2E^dZ3uTY%2XQ-}+2XgcKuUApXV4Qa)InifIonn`>$&h1Y zuYIaQT-l@b#~*2Gum#|g^watUrvd2`n0!?8Oz_B@B@=k7XGbXiM^8DqV{g53dIR%b zj%wItoTub#r{o8oBA(sM)uh(C!N|1*))6%(uhVD!cw$n8GWVD?sYMv4s3YDZeOvZ; zOdtuDTv<1>K0E&rnos4M$2Q^+IFmy2&1f~B5gehM|DKDD$dx=B-gxH`c{PPo2} z?1SELs+A25TD1BfIpoHf7qQzMIM^$#THXtm(TLkp%{S35Ky+lT8nr$Ny2K`tslV?N zm5dQJr#QWwW>l-y(FEWB+9D=!PObtWh?W?{Gr!6EEt*hjmcvKMH_Qad+`j8DF-V<}`@jTh=(SNG?D2>Fy4faFjL)Xrwx%+Tl9c+1~FQuWw){O_a1i=!aiT}IY#W2(C1u3sUs?DQMG)mlg51U1)vIF{h- zJ%4`snwhvn6VuHdqW>e>youq5lUh>s*?e@O-+HyUtahP-LXXN3d5Vx30(OXpAnxgNg-K}oHbJ$`NNncvo_V2^dt)i8H zp1e>cnUKoOZTz838P=r$8-hwsY`!ac?%JnH6LtaJ3hvUd_Rjbqxt=ojMzOVBq53^^w8uPfb#kxs^-&R82jbb0eZ{vShXtcJ8eS0Hr9a zRbP9?1?(dF?8dEIHhEeS7qZX#Q^^BHt^`K|72F4w3Fi255sKlgr7a2shhU@c<%u|n zAhr)#RR$Eg83B#UOESx53#NoP7cE7u{y3}G&0s(6j$tMHsO+bWWfVk{?7yV~jMx~u z_q}$rF*^HHkm39l5ke{{)V=iSrRqBW%X4O;ij*I;%mfOiZAB(FNqsrtXWM<);$W7F z#jcZJq}j;K2wlF)q#D(oz7?YYCdx^0A_&!gk@*vuTRI#l8x~gYciIxV&*z2x@)M7l zDD1{3^L#+>b8tYe%7dHm9;^3uK1i!gX9)_r)y5dhMD`K#l4ks1P1*z%G&Q=!ZNV5f(Ah$O2FNNK=h`y(%t$IaZ zgs_t;w~JHeDi@UqrSq&e?){bPAX_=`V0AEl;H|MhH~pC>?&Z4Q1s0ROct zqQ}EHc6of5ytGYztM^_)1;*KBGGg0d;h{!&Q22tjPnvHkrPjKDIGgnO`* zwQ$U^`?8EjcMy4q_Sv>k>@$ZPtc5`we#vk=LfOOVCx3|tZdboMKp2!8!FM9NS zUUX;6&a2-)9*;7eC3I@}+go(1^&(xI0Pf7`vjxC9De+0{P9paT{Z4jg=75WxVo6)7 zjVK7N|5O|~>%c8JNMRY{>R<`{`01oOr}T4*OdEUqS}ul@vYS1`V_lqFHo6_(LPF>J z;F^#vuh?1;yDCzmjxq#6ydPKc4Yh(&qz;BR(Jz*tRXJ37W+;7@?Dh0}TP2_GbW;n!s`2I3CA8Bu7@CKE=v=%C?0EjOM5r|V@3!`%q1-U07o zsSV0Q){jz=Om?<0joQ$kYXhgO2lpV~ZIj!nvAjvz+J&0Xu+I4qx}VYF5f&_BcH0tA zrwhIBr6piSwdE+ttwRESy9Ok!JDv-_Xk({6HeJDmw-a@Bcf(jA|78%R?pd^vg<-U{ z^INnUM5Ox%#|i9sykrKmgrGpW$);yuf_gHI41 zMRi+X5fxZ|I+Sx%V;$j%`_BcPI^py#o9D^oRiS>1x$AUN8J{06)5C|Yt-eS!*oa@y zu!5lRHQlZ3?Ce*DxxeYF{*8g!Qv1 z1=4!)rF4EB@sac2V+bxcRy_~6HaNSSdoShUKArQRJrORr%Wox38FD)y*l2ibt$UYK z#O+eColn+y3HcDE+Dz2}04d&{R)TX8z0>G>rhgUW2EWQGnmlb z8f$0(*yH9S3Bw4Ee-Aoz;=$XH+7GMLJ~9CK@r}Mx^7adG*^iX&$a*hn{evr@(J5_h zw^DAs&N&m|W?b&$I-n7(MPZMesI`^ikitvKV^1b?qjg$EQ3+P*vsddsd9Qba&;q?? z5p7cLh~l0$i=51a)RUMrY>x=tcdEf8FuO1QOq!c+wpf%kj1)9AkmLzeB1d4|$Nnz3 zi?52T`V4$?^}6A$5SyyhiYw@1b6x3Y2}IrfFfiCa_<08ZxfP4RK<2f~j7k)BP~wXS z9wp1sv^2iwnevk3TXK6RCv$XiK<8MsNj9536UjXzb0kx~KK$m5&AakY8ri`(Jk|(g zO1tXTQBczoD&Q3hyreY)Mh6{mYX)OUkQ|7e*0}Q@w$>2w*yq9+&K7O3IxFVj>3QME z43XOk!iIR2Q;#Lse|FSstmtK<*~lzrZ1A+R^|m(QN>}wA!c^f%-Vv#YhpD4+vl4e% z_o-#pbyjk1xK!?yjtNwGWhLl0H-&d#fwbVJzdrQWV}7Mn%M5Lu0TrqHR%KCjKSs;H z$Hj4s6%Z03P7V%_3J1{u;Ap@2c5(CFNxh*&Gu--1;L7@pg|^ZW&WUkY2Q|9-wH6}C zCI*dQ^Xc8A7XVO-(qX)LwmPy`c+A~?t4KJ(1-qa$o>dgR+`Ct9q=&gTA$!ORe)(s6 zCHyx2_<~&njH4HEY^!yXpHnRnCM?a4F?G>bXM#vo**uugMf4acdt|M!dTE+0Ee~c!34N6iwEmD_Zf%+fc9s5B4Qf2m4=w9%8P8Y);fB>^%x2Y zmM&QyIZQ;txE-TrwjLp+TycwL`CV?=G>Wg5uF7;&VEe_Ghu`$6@I|oVvrT?q0dd>8 zN^>$$>u13u_NolpX9MjsFLK7aY{(2IZ)?%o@Lfn7UR@I7*-9`=$;gNveA11NdT*xa z?iqcjbak9{;WsbgJYIKfVrt5|Xpn2ekVaCC$)5D)BAVb5gwt_^R(lWyxK^B(i;Jc7 z19d6C=Lg=eC%dA~jKN_GjohQ0q4jYh0L7@OXiam*p$60NX9SAHe&ZWyjP$`oDI8`p z(~zuc46w=rTF&oM^|@CD;|rSOAAQ>|ZAY9bnaK+)^-KY=3)FC2MXu+0Sig?Ct|07H z$@D(IQjC0}JR+44=R%$63ZzcqGmANr19<#ivN-IsYzIt`s0GL!~Lw0(Y0q%JSlL-Zsd@IE7XPy#So&Ul9l63acqgg0E12&qr0Myf0(_*WlRVgU>Un2(PG z=0!6EY)S*90pqZPqrLBY{)*PyCo(t!yr39!- zcBTRlyYt07DKY?73{q=u17QE zDGE3^Imz7!LiuUqaBd?OGd;6Z1&tF2)R9tUuM~{HX6utFRnMaNDg0o|5}XJhU@fz> zD#2NAIW)iySt;!HJ{>Evpwj8WLpM5AB?voLFcoT7K~(HL`ES?haLC|*&+-I*2m0^m zj=1#UUdMN!7G6{cgB_cg-yBvfu16?_zu~XJK7)AGfvLlD7r>Uf#zn@J0)v*5>wN1c z$WWViZ_dyD7I0R@)e?TdC%R(_{r?@}ZlLGDl@)6EP{$=>kv(*15pR?wRA_ zKD96dU1s(Z9aDPjsf>Lz)^BpPn8~yBO zfBrDm3%?gw-K_-DtmI_Z;#0ma5+TFxdAGYngZY(6cEAyspp!-sH8nL*-;e;La)kP= z6GexWlsAOGeTU^iryD&PXH~Uhj02>VF2GXh+o?JUc`SB>& zjwI0l=EYyGF6~kbHaYy`q7@TKl%SwF2GkT1SIq40!DA)2ndOZ-y!$motQyY4GOE*s z3FHv>_@au6Mu6;u-SOY8DZ?-fEeuTHZwq?NAx1FFen?+FyBNKEVPYok>xN}+B@E2- zii(OhPwHGHq-4x>UMBHnv=(J8>KxfERR+DBm_Y6okG*eNTw3bs;7}=bNS)HduE$}ig8^fu z#T1aNU^5Kj0O(mT$iTYm>gqB`QGh+}(5qQM_M?tl0zUzLHW3!`{WYPk7|yfbeW1HL z{ODwDg&PVGq2C1v5#$9xV0IP;>oB_BXtS1Yf4%Pg=vKKFrGpG72Ntk2vFBq9dz+2H zOt~s^R8n&P?ZnRU03*Kq#ewYsvm@<%x4i}`%FEXVL*=kamsWj>Ncaa0Gtrp{mOZ0) z2PIq#ehuHcVa7D=Eq6OnkfBv{6|V(Q^sKP3y*&zKXtcC}Eu|_TZ_9mlVEesmTsITJ zkBW`msT6GC$?)+4R1%n}ac9KD!ue*w6=0GFevHU(bjk-nuKh+XH5BF2(#z=KPAx;& zEOp0fLy7E`dimYaPjfQJJZhA>SUmEaz%%5{=JKqILtPHEv3 ze#Rh54j?UKcrjG|@xK(5mMVp{O87cpf=Ea-SbV5t!wf62gL)c$rNA{vxs#ORd1 zN2{1IQ>Tck<@3W03=Us2ID=4s($LV9U9#`GOjGH7KJqJO0^B3W6&Y*L9(Tb%JemXJ zbX>`25ri9nub@dG+qp@nlLYCQEhR&e(wZcG$&9;C8mO*iQXgCunfAd2==}Nft)sKw zzoUy^d1A+o9pKDr7Im$*&6&d`UM$+tDXj@629J72qy-2vH7WAPv4;XrGtldrQ zEk*7R7#?6&n6wNm>bDAZ+9Oib#P>zUW%eq3DvTLI_hQzivM zP+NO$VZhhgSbhJ(Lu>J*J_Xsv3okg~I&RR3;MdDGDCTB>px1Fw?fr&%-{;i%v-l7?y11-6TF#))i_Xq zS>OyZ7((y% z2e@>H5)SMn&CRR{@x(h76<>KU$rqtEcG$amDwDL5@Z^R|VzjEW5bpHwBYBA+`lCt2 zDT7YnzwK7)T|fSsd>Fgp&w2p@gBBm*qT5fWM>O#?LRJlH1nE`K z9FS~L7k*Pz%{)Ik^3*AHQT9y{+>1GUUzUBsxpCFD%76GY2upU7coO*J6|#R6(S`Wsw|U>OaakQ@(8kT@&*4W(L#{rLH(V4{@62Vi~~a_b`iCR zA;1}>{!d=Bd_L?UQ3(Jb&v7yqr6Z$t5{Ev=vclHV@8lndCmjyErAyJCg@AGvmgSrT z9uK?YR+$w6A^r3qmJLi*er;RWWVlT+RyIFG)AO<=!{R5qH#y_HB>X$O4T@f|ccac8 zUS3&WcMw_d<6in&yMt9_r`+mUNA_5uFP@_r$pT7|rs>|QDLv0p6$ma^l!=}*(G!ni zTU9+5p4SWtouHU<>+HzL&9)7GUF}c#=zqfv95eS`4pA%dFOCY zf9s*H9i6$fGxz$Eq> zII=wOKrG!drrdL3a`-TXp)nG8E&&a-I@8tQhS};&)8-~CBE}Y4Z8Jv2Z(hC!QNv2L zeW?nV6PkNPC~9X`P$%F!KO%xl^>WxyhI|Bf^FQn4s$2~6Rj#>j?`l_VbRmd!e?SCk z67B4;OtH+kpM=s#Ri#2)ukYSwn;0{xxG_DF%QTxyk##>cokR?^e)HXSOfp9Lw8V2nzI^+pTCJbOb?~NJo|A%HZs)jVN|fF@S8wlnV5EB*ow8eFRDyj{ zQ!dAzl3YC|B3AO^#YaVpN_`0WtW0#yxyLV*nK%7PgRsIbt@$0a;)Qe41U)VmH7}n% zM6c=Hst?Kr>6how(-5&LXJD3p)q$qezn>#DeSC?efWX4OOp7J3?9x=j;UniotXxBz zt_T6)0+yHKGo+O6CV#Yp|4!57RyGET4?}oLEtd?!x6#tWA;b38)LlKxFw^My>}JCa zzqtZ22@ecbeTG<;d_{JQ!@%z|!!<_3LrzEHQWYBHoE}J<*rnCvsctSKUoQ@tc}c8* znx?n0aMfE55cY!3Arblg-2d;j0KLuF#h30)M&aBlF;P*Qqa0!MJ~h9#>RGmpn1=xu zXK1ysxXPYL^+N}es}gi_tVfn%H23@hwP7eQPXPgwhr`9sbBcR5RrB6DVOBIaA4mL$ zPk<(q{_FC#N69^wb#3pm+6lwW`RSKnppfQLWZOCXVD}l#y&xyJ3cF?BGfkgpgfUd$ z8#e(Z##IOJgC;=4iEDovIY|#9rt~6fE39R<4u?8y=-;%o&wYBwkhjG_Tj}?&Di?f@J z58b{t@8egG3typz^1*kYhFMv0i>M2WYv$p)YQeqE@D`30%kRx7#9}h}YhGu+9pW`7 zh%EU(`-nPLOrdV8%pIR}7yT2Nuj(XUz*8Xxm@qOBIzAc;Q1L&tyiSLpkA8dc*k_D{ zE>Gi3K-@}X8Otb{8_hNj-4K*X`tvCiS=p#9)l{4f1B1Q_Y3|Ke_UBFV(|(`#vZN&3 zaUosZ)7r6B6e2>~g3{yaOeL{7{^Z@oZcOBG{eHwM|LdM{kEBs>H9AEH9l21;e}BA$ ze)EzM#LKr89#6t!fgUTgeau6JuzA#;=wc8Xw^C9J-cEOwLgw&XB%y0zWYuPRF8uGV z-g{sg+(tJst~1JmF8Frhld{4G_+RhAz2QDJ=vSO=n$G;&X5teQdT#$U4v0yWT7G(8 zL!HSbAK3XB_G&4b(~w{8&R4kDNtMVqX2yyZ6xW8?i}Gcp$wKCXLOtP;)QAMZWfw~U z6M-;F(oP}fhK1@#7HKR&wC%(s9MbZrbo_0;0H}P} zpy(;-`OyAC0VSsxcQ_lxyoG%{?X^ewlhjuvEnU7feZ-0L^k2}S`gNqf0Spy_I`(n^ zGVc&vR#05`UFPYaMz$csoQwtV?4AcVa&j_kknzZtLq%d?@{X{NA4 zw9^HgNb5tSnZm_)LZ9OsqC=~V`}$}Izkq*#(|^nqI1U5q9dy6s*($!#hETECd)9je z=iORe>%2#@EBm_KE@p+@^{P^>aNASmWhXZ3KH<10WtX0^Bd&B~%u}jJi_^QET2e(O zG`U(tzw)zHQcLZ7`Fb$-q3_U%Zil$&J^zE1uj_E5f__aaF_VbLzX0$-45k&!8Enh- z23qzfcj^OWU&?(7(QjJaFc$9teHML<^$G!o>81$#N{i6GgX~Ex^HLFqBulQ6(5sjf{wh@!C zJugGm{ayyY24HT3^Uu;atQUUlp`&=-oYv3JVxV1bvCI*?L)36Ey14p%rbthUKK8hc zvr3m2>DkoDpZtGD(Mm{T-ecIsNJg5Qc~*~m8)(<+q;MHd&DTS@{V#Sz^j6& zJoV>H*v%}So1T%eEZrPLA_;Fv<6zU5yy`bi3CtpKkkMRycY3Jj4+;Z|KUb<{&4a!D zaPZW!nIC0tdIz_d@Z~0p@=dxaarD_^TrsYs+8^*OD=Iz0@Fbush~huBuacs85B0L( zKO%Ng6Mu9~UftPuC&&Q$K#!=+1lqj!9op#a@kbUv(PqJuqCfE{xtX!j%sLG)oXh3x z_K*|hQ>WG2e%KNtm!#?1UHZJGlF82OA#$ewm!5a>1&L0ZynGEke@Y~?g3Q(Lj|O{) zTt>Elf*Yq6#>0T=QSB_-_=gaKJ_V;ZN7_mHBjhMcM;}+BHcM)P$n<4rZQ@6?|1^M7vaa24S{aR-{ zLaXe@<53o`b2@vBX@l*8U8;hV?|Q?0_xR3!{oel|=l?r6VB;{M)`Q!KE0vk|f#6kw zKEUY1QM)X@+YJr=c0l~&`~CEeQ5z0gem2TE?b!M^vqLib7rz^4|cFb4~<8g6XU$lA(TcFc)X|zrEe6-h%A3 zv3sUnddAtJY9R5IpQ(IiyfgRq(P^YWTro80jML6B*GuiQE?|TSg0B27_n8rGHTB4B zKDzo+QC4H{B%<}+=A?%)I|}Sf-%0?i-e*;!8q7R-up_XV5bwu*Z1A$^CX3s7HbeLB zl|OQ1XC{c`K}@kq1t^CfGhE|p^6ts+%JNqkcF(CLU~9#t#AthDLnSqww4sh4{tOuA z(G4|i?GlD9)zA8=vD<2cL%@F$?(4KldXXFtDf&c%ng0enCdL{QPm$Y%CmB!q_;`A3 zL$%X(M*VnsY)>h0GWaf}nPk_!96cfL5^m+`S?aGsrMnFj)XB$AVsW;Iz=b@ZS+8{9 zQWHV^%gW+IG?5_7JKZ8>H$fWnOM4hj8c@R!`~nQGvY>OrMS$Pyh*Cx-DjF(8A6l32sXTwfJqIGZZqVQ_hjlZJRLgv=jKYR|>k^aAr za0sm_VZq^#EusdO>ft+qp)}YHY+sj};3viJwRfE+RwMOUgyPP)upZm7H;K<<#-8zcTzm>`3dlS_o8n8J<~J=^nkWAYNTu> zHT(^~za4f1pq#(|(5wHlZO{UDewv#?xZ?F^Ja4D z?w=ZQfsPu!ynUDGE4_^b)&UrQt6`R(S^C#=+F25AXs+2@$(}z$isr4HhsBbdc)pPo z1o#ot(N^liVsI;(=;LjW#JXJ)vFdn?XppG|9x>q~%#^wHy=$!XXOnw=^v$!zjT?{< zeZn=)I?%NLQyiaz;oz%T{TEzfNp6MQ`#lTiT3-vcNo8{@k+Z@L$n9!i;gvqehg~+2 zK!f?I-?3F*RJtypa1<2z-?wNoU0bU8($loE8~OaDnd0I(<7Rr|ac6i^m6WarmO_r` z(6O6H5jw81H{Wa)B6moG&qnO3mparqgXZ>+nJB`+mrMtL-VY9R_l>DxrNk72)w;G3 z7*LB!QrpY}f`N?)RPI2&-98LH;;;R2H7miaoc1V|5WO}9wn)uLa+;WR_xE>r_n2+H z&%ejYwCY!Nf86?-=VlAXf6d?Z9M*NWia*ny?&MsWZMPBATu;OE*gvm%@z1*Jy9lF8 zTpOC`*R6Z`h=%|5<}DPPPaX67n!ATtVz**)*EkqZJ|$PCAEd+d;&M8F$PqOsyh1I6Le%`Xzqz~1Iag^Yuu_FWBe<2) zT0i-u1RA~T5JPA8B^w>_=pL2;eBL$pvI<$)h()&DESjmYQcr0^w6p_*sNWEOZFg7K zr#40MhdgN=l@St4RC}9uzm&llJv5156a@5G#lt1vTve$G_QkIci<^yn`{POm3H|0? zBNI&s!F zK|#pa|F#5Qif@BpST@n-p2l9*0M*v4cB{P1ftHq*2R^jK)qgaWJ!`+_^){XG&*Iu} zwYv6ZIQL_8Oq>G6haHYvB{hF!$DN+Ir{UU6I(gx1Tfwtu$lIQqE7W+Om!+RA&cg6y z_b#;&D5-m({o5t8gI_6JkO7KLl?QkrW!)oVG{k-wjvBGVKYaLPAu}+3SiN;aOw%ym zo6K8o0KCYgS4|Z-MZM4U&+#F+v@_d*(!scaTgjpwAvUiJk1b!i24!Vs96Nt%08m^L;|o(+Zr_+_{n zPYzHaCizP7%lv#qZ}dDS+m}Wx5XF?_nCclT1p{m+xW`;qYW5|ZqdXbWvg(uY999G{ zvXDg-Y?{^qZ$Y}Zj_hQ%Z{9x2xWc#6<_GS-hmXY@pWV1Ln$!NSdfz6E7AGc95@sDx zwQa0=QBtBY<#xXItsl426Rp>vrHCG?O{8Dy!XHlrCHG5;Et~bscXTk9EKwYLKRumi z!~)oMmgkV{`~Jj&1C}g-rg{Yj_N#n=So9!Wv(W5HeV~zzjm@LXT|_ciKd_~M$?G|m z{r8m%xNFpTev6ClC7!x@;I#W4=4v6DL@n$2wg%ReHav2eJ)WsxA!N=v)2(a2b07sa zowl*#+-=Kkiu+B=s*MGBG+>>td3^tUw*4vCbIB3Wuqy1vF$MTDAO=JBv{O^LS#+!X znmkFrTXNs4&ZIi4bJbP#VTTk8N4F!ZzEZ|p+Cry=J(jQG2*=W0DqN4Jl0zUN8qax}idVh8RkW5fE; zKtr5tA9qm>Mod(RG*FVec}Z=dwJ%3<+TP`51qW|*mZ0`~3`@?Dq);;XB9yAyk#F(w zRI#~Vs_^JtBNnCr6I+N_4s7y8%t%ngmxXba!_{%;(Pu ziy~~Pp5<_6ct3ZBct8Q3kmte~pZWcC8x8zl23f|WXx#E}{1JpDj>R{^^5ZxereeF+ zBB~~8vcB&jz7i5h|5?+0Ljy4Ye zoxZ(Vs8i{#Aj5t>Ss^ii-e``UvRbE)ClTg3ZMn8Q5$snK-xLj68G z{?0p6gz7DBCH?FU*#Vg4Vr}~O&j5LYfb7cQXH(0d8f$Wdov3aDlSpDyXO{6W199hV zn)&%(AFUI7R)2N`ah}sFx^#GTWVmDP{*?D%WY%Wig&RmIuD+w39uTnp&fLe*bAn3@ zWJSy6YkZg`cu>!gii5AL?F43G_XFfLTDa*H?rW4!L9Ke(z+kaFK`LY_ zhcCJR23PbZ*1+SX7MS%&8sN8PaM33orJYK@{Of0*+}b~{b`^Sr`b1dOtT;W5T6@1x zp=Tqre?R)Gsv8=DupvBn@h7I&M)nkwyz{Kp*e=#UqnOk=&I+7s_)OkJb+xId9k zIh#M+llNob=l9voN4%&AzLXbQt6MMV=F2fw{}`#aCyyRSb~({C1ht8JYfOneag^CX zSlkYe*1F5elgqGCjpY$V<;jh~Cl-=^Mg*S-Gwfc2sLm3NZp}6?%?2XSIY0`hHEx**`-aEY%n*7c+1pau-@-9D+4u9Xa84zmuasV@}F*b znw5n#h@&G$O-4+|P8zY0Ji1Mo`|6p^G;yU?J+3JlVarxA^_Z5tC8xc%NZq+M^jYGl ztZW(7xKGdZ%+a);mkf!xeL})*JGV1Sz}5hxpWx--p5zmtk@QV(%Yq<-KkDm8qDPJt z6&FXxC{sSL9T8lT*tc&VCfo|x#z+RL%6|ACE zCOlzrY-;t}uDH;$5W8ZlUvDaA z4H7P2_IlHpSjDG$b1p(|F+yIB%B#{)@WnpPuIFHM#W%w2+TW+*aD}tM!qz#OqM{-& zC0;7u<5nUKWaKtnqv45hWCuecaCflh=v(lHz`D%VQCC|}?8TOkk$mX|Civ8{R;*Ix|p)KG~hzW2IF#epGrrCusU zA%6I+qv|u$dwi!}EUr6E+c*Ox@-CbAIVSn?shOxiBbmMkGTx_ou`DTsXKBW3qdFMIJ~kJavdoz4d`!Io*!@K(*V>DTQA* z;`0xeaXz~9-cM&X<=_!H$=k-t`x|GFT#l`WuIu@%RRM8Q5PdE1~rHiG0Y{ z+CaHU_+--ErEe^13cDKupn@(h4;f?$E+Pz1r5%Z@SPb=@>D)Xuer4JMlR6-@QESB4 z$Z3>9t?$0Z)WOlO2k$F?Jzn;SBJjkGW^;n1ZA>rBZc0L>k!Qbg?t5*BJU5^8J^o|!67vCyBM>te)D}j#lh0TxLKu!I_ZF>qn^X(h7mBA|$_^+gzb#SJi$#@3uji+-@O;lieZ_OJQ1a+2DeZ@pwOr{&X37o|$?XyGjjNRc?q=!@q=60_mPzjr0 z5NrLzxsklVu6<7<(CD5rPqpJDtC7aJ#P}n5MjFu8*hP(Vf0pP+#nILE%2AHsss(wXrA)zv08$hY&ZB@%jO^#lkus0gp%hpDr342i3vV%fln% z-idlXLJ>hNc)w1MZPKV}^Cs=Ly`wk~Vto6=LpB7z2r?A^*lxQWRzLB*PZ4hqx*q5j zUyI|uHL!wvTg{phOwWBs_aSR3lGpMs4lrEFmU++ zPjqU{KE4{dY`)tss@BD+h04(of^E&sTaQdLRGo9ZBdFHu(x;rFap1m!WaTvv6^Rhz z9`T7ULq)-Z52PvauKyoX=N(VwAO8PaW-=nOsVF0%LRMKhM%f}l6yb<$k#SNeduPwk zAu6(0C3_v&*?VVa^Se%;@Avok_Rr_>aprxW_kG>h`+7aE*ComvOf5=U7ru$a!z>Mm ztxl?*)@IOSK&6nT_#RcDZNlis>I*|v%?&4y&6A~Bm8qE*Tq+<1c2eC+TGy5_zn8xl z!tQIipJEm7G?%6ouotSe!LsGWN4;<1Y zEE&u!N&5DTP)Na!>+lUw0Z_X6xDpk4-RaH2T;zB+(@PR3*z0w?{VOFHaDg?3Oo%1f zi_4SI4}XFWpwmVFl&QXMkpY{hL2O2txjrlO)|~XgFmrXWy{IxS9Qb*%9SPf7YnmS2 zYhKwa(+P~w73`O+I2iA+31W<}U!UIG++1Ie$mg|PU4Lsc*n{q|PgJDfx0=Z}$aByj z_rbh^Jt_oG?BAD=NkB%Kk-=G>g__59e=rn~z9=%WMc7;+_7f;v7l|bM0}^Dl62NQQ zR2WAIo;xCo)CO;(K77d4&9#q|&e@wd4PZpOzZ&etT`D}EKUeC*mahHm1}Q-Y-M#E$ zj{XUcVcNk;8Jvp7WUw@SPvf%m^K>sqH*;!nE)d7628*r09cKtSjGWFYbb|SS+eqo? ziesC^vSsvc>)aeso_kfhsA@QnhV2ojW5do zN`+FVksvo=H*1IPhSSL9qm}Vx$Y)Qz5nrT1ZIdBw;03g?kor*%4Ehc7LKZg#7P1xk zu;ibCt$opckrWw*z6B^Iv0mnhW75-r@_@&l2Ri#Ih;(g9iHUX-J%@-B|ZuB*ED^X?DXX^0T zw|yA0l47I)$f4ndAo5&b@9>r)(y>vh)?&{(g1I38^X=&(3PJ3L4OGasF|umdNOn%I zi04rdd;spxqkNfYEQ9NP1Zi7Net7Kt>_Ocvc}8yO!yaj#zf3X~|MY4`=u_JnvKZaw zmRRXnX%)$U-0Ex-AbIvh*N8E*cY2k;?(I&0gYlK-l~#I_>Xnw-``q@DNUVb?(xjN$m6l*&tTaRqJ*T_lJG_(V=2+PX>7jAjU zW}zIUSD!ac>8addblZ+@I;cY2+V-LkYPxt&@WAh zEWN97-XUeEN>7;>JZk^s!J0u&M@R6l1f?#*NMXh;eQVn-{UVJDmP^_1?`Ifi(_qIS zV*#0f;rZ`@;aOH{5et{9urD4RWURF8T z`94-BqUo6yf3!+L6~{w6g3HL93E1D)Uc+cL3%4z)$gnoRfk#%0Aa_I6vTJ$6o;tMZ zH%~PlUN6w4_h&ybx3src9!7q0Yao?NlEbl>1d*6?sbKXeMRyf1vuZ&haa%I1CMg5=!G?qJJR>)Fu3v=_0uuW(nu}j0jU?y1)+W2sIS8CyNtw$B;nY5ucLe0h z!D1AUh|D;;BC#ab$fpOUV#Pvg-55eoLzkjse>ox2^>zcQB#x3%eogHSiOi-Ll2rPm zMt{@B*&nlKefe7^nswBIe=mzd^z*dyJ`)!_Wp_jv9*y;I9o_C6gWAu-!<`Rvic0&v z<}1Z3^oMk*Z2xo`Ddn2cS*$>QADqpyHaA!!k+xDpFkMUPkQ6Z(5A}}VT1R?^*k$sG zOm5Q3$XBm8b}_33uUj$8Qq+!J%3$?1tB^%vZGdL}&0o$Fts?HU{y5Ry-u^zFf><=W zj5@@ChKIUJQ-6_yCLTov@pr_?b-@JY>9SAv->#X^DGb>&k(v?A$;ae%`ATtIBK7zr z7UK4U^+6!P*R7&j?BZ2c?uB>NTlugumj8*1W6IBUm=tLGEN2{3sVBz;)XSUhX(70P zM9gHpmzw|~4^7l_T8*<|1mB)cQrvF;0bcT{w=Z4lx(=XbJp9gd9#bbN#Hn#l2eY1t zI}lQX(|@vG7HXIDVz~^OC^gOaQ$x>!gP>}1$2o0IFA^{TP#tn+)rGn0@s~zv8a4?m z|8#Y=Y>YT1DXM#IE$erNBESDj3L+_n(~~T=nKNPR?tu3Empd#n^2!mb7Af3g4#p%J zD)ydyz!h04B@?MK#F$SzHZx9kE4`(lgwC2vJGJc<^HXsYWwJ1J<(&Kj^t6;U*Y@dj zol`P55}BJe=1$!W*2p1FWpQKG)ihs3_aki^QXRDfIOO+kw7Ob=*X!}>frS?YRE<7{ z|6M@J1^)Rn(!KX;FAd{bsqw$u#*(xidS=L2XZVX%#pufH0VAUE2CEtj41jQWu-xvu z+aEfTPkisF4JAVMVvD<#&MHqGGa_L%P)KT*-0S{aXgMJ^^M(ky&d=gYQQPQUZIGOdamrz_??if~A#&o|xC@5#-$P$^lgXU9#+Du^M~*5i3zIu{0vEdUUgTmS3IdHa z5^I{sOfRX*MQVA#70Y`9M=&dQFd%4#dBRAdu5Mb*EMw94YW{HSp%ZQeaq#_jQ8q+g zx2ZIV);3A74ezSvce*&5oYpWt_%wpSllz1x{hA{^aM+ z2mvmOi#h0KsCakj!TB@|E`n75CF6Lx^f1~18o+tKMg+_G-qp=D-ROBEhcK7_QC}gg z>G?j87Iyi+%W4Go`y($lK!fqmi8=ocsVgp5wM?M|t2bbd+{3A03`u0Bp~wVxf}QKW z_h_nD7}mKEji~v7C;S^%gF2C~5zEVZ&#`9#r?9+O@kVzCp_JT1zDDynFDfcX*CiPk z(FMun|04=lpLZ3C)56iE-lmrum$kAaWNH0Q&{~-m8174S0T#V`geDopA&pY_88ruk zz>q+gOM1pP8#TZ!O9v-0TVA^~gIbeJ=Eib0Lp{e)ak`;%6@<0Te{d(Jq2;fCY>tm6 z?0QlY=1;2Jy%oXFPK=4;>hR7EJdvT{auLxaGnrBCX^>(;uF4SNR7FMjG+YWSnUl$p zODb6?-_Xtie_62anL8(my1Y=Bl5}aJs~ko}8VmKLxO>Ov>YJYZZ^^E~H5s_1aou9Q z`atO5IgKcnPXI!x6!(Z|M#FmV77{YS?OhqA)z5+TrVzF zr!ms(9l_l${)Ni(NTVuNC;e0zg@)2O=JI!b9Ms5@=z~~>YWBFB4qy)=bK?N}PCiY} zhqjoBaIUFQWrs-LClW&7MfbEPOV!-4+ zVM?d4E8T>9RUcqjzS;<+3Yci2H zrvI%DSyA$|j;jdWoPwLX^v<0v6$p3k|Ao8BxGXFEvk$w#GIv*6nb8m1@a;Z>jJzSQ zEhFlS?AvF}vb6V>koYl**V0G69~GZuoQ6YCwQK&);mv+|8XgaQ`I{e(>4CcjszSmmmt<)z?;nBBf77nOfR z+8!_#8C;odKrlZbYZma{$B~DS?0!;gJ}D*;B%^TxN0f~^SQC8zG>JhL+&P?TIb4o* z6g8u~sT0x&g*U}Xa2ldeofDe9@HVXwbzp)B4T_0OgnGkS>kD$An=pZtqx8uswtXd%`_NQEMs8>~@O~p;JJe4?uRaQPnHjLy?CEfP+~2 zNH00qMLABpvo;JAY(ddqDun>aBJ%!gj*fB+2S+n}h9Yv~M#J^%4p}@M7Gd`PuHtEj z0cWFf0Xyrfqv5%;EWsqry#&IWuQ+U?TCIlK_A}cUx_0ghb*<_FlRTyjUidD*uFQ_- ze{4%X)#qH+at^Wd?cfd1td0Zg%< z?QbZ8l!%v}Bb)2i)4%+8qAt+m4;A7Y$>wW*@3!r%tiNgO@SRtGL=c0fd_|OI)B`u& z2rk2fI%H1ft3nluTOo--rf>iE-g;;@fo@N{EQCzo@nlS-{7;&buG+QA? z$W@YOJBdSTPav7y)PMM4-B}4X_qy5&{GYsup4t`az0|I5WD=T?{Cp93)`_w?i)k0* zDa&v1XP@DSQpuzpHsbZgf1hwH4LA4hM%H-?tulx_h2M)X=;fg;60C2KrXnjw%>HcY+b@qmNx zN(hi?PJiW7ysgv+u$vEme{iB~Jut3!h+UOo_iJES(!oyemOI;QC*j;vQ`46L zeU!Ch`ky@{IKaWg;8|D+Y`>=BuOK*C-~hs25pcZ<*fO<-A9Y-1}B=7{Ec%r^R4 zxXstsS9z2f$pYECWPi6QuTK1SnvN@BwTLt|V)rWE-lx8VIn**w!1Irw=-s$6?N5N*j8?grya5zn3A?E5X^OnC`}+EE zbDjhyzyF=;5xvR%qubP3>X|6kL;NLW>FJqNub5@ke0co~%n;#f!l`+|)b%-I!qhTQ zZOg;HzpVJ9s>IsB8fE571o4UzyhSL74H7NTKM#qaZ2ILBqs$EuKjpVO?v_7s0u{A| zKE$i-$(j8C0^#jvhd73uzhCKE4t+yoL}$KaP?HN?fr}P+0o4#8x6%ZBeJcUC1cAjc zj4$+z!TtL(FEo++#>VaJo1ByN{lGA;Y|k4A5Q4H~0{Mb`FzS`0UK6|Mp_jLurc!m8 zA<1(vel9Xd`pHIM5+ALSnVEU9dZx`89(S15ci80ClkYU9L(oOcuD1lS$~0EMmRdRM37kBJ)GBjpM-HuV1vJ@(6C=;o-}Uyj~RrY2UpY)z5Ml&K@(S za{s%Yf)qjby?;M-Q41?v7UQK!*Cf&onuxqL>l`8Sap0-LY%COf&X~%c4k`&V(yj0M z&3$8S;uQmdj659SY^)ZR%No`2ATQdz7M?ecYi=fY%|npk*er1;ZH^wz;4g7!tIof> zjomqf;H1p2WtoFdk)7G9p^(!o^%UQbZqQ=e$i4OwgL!4VkiM-=5Fl{i}YsM zBiAoWl|0A&+m!;FG&0uzl|>TZVz?DM;%t=c8;S>}g3Ny|?tA4JMBTYCGdpXaN{uK1 zd&K(2jQHMZqRE^{=yzj{vdjv-(+>)=2835}*wqo!M?Vh%odRbimJ z_Ge&+wjU3RR(LAsxeeG2pds8+l1S^h!QzKCUTx0l1wRv?ta^@mJLPujWcr#i7F=?+ zw+90s1d7js@=vrgvW2DEt6%ZI{m_H1BqM+Y42I|_DcP`YeztwZ*KEglAAn{AEl$ao zWLG-+U=Bt7BQE4Ue!N&xz2S9!rBr2fFQb|IG)PJ3M40(tmh8Ro zczK2$DMTF7Dqup7T1xm^is6>Q6P(6FrvN|NKL@~GTlIZ$mzg%F zK!3U(lv7l&LKIk&o6*bz#YTC$;)Y@&8#8Szw?iwSh9hjoh$pR#}kR=I7Em^-Et(glU&4?JD}zV@}^K5z8zz6NZkk>;D({Qbk~AUUiWX_i&B z`&N!Yp4#5K6BrMvDia-Ez;Dud(n}`TNm-RYJQWsk4fl+M^E;OF-a0eGo9~rV|mp zrxt(6F|E*2pf$M+v@pPb=k61HBL$fiR2l)?`@hukq3_k}IBJD>>?kQ!fTJX=i;0N= z{s+a11$qUpmyR343929eKpchXJ5*F4T-L~GT1IuhIiV?94F1SsA$NZ<2jfXQd))X< zs5zGm9%Nd@dvIO+_B3!3`hj;q+k2QM(zuk!^3I}3_^tc->}r_g6ClT$3RmXezoNx1 z@)g6?78X$Gy8p%R-;AGWj%m2f0*#92yl5;zJwpAB0R@jot5Pw73uJuIKOUwrZ_;RI zq&fEKY+VfeYS>rDghL9slxdl66aaWQCz$~_7kJM+MUS}|qnnb08GS!=oedoZdiVEl zIbLGKLxT>)iBqFHWubzX45Ujmz8p_VZ~F>X8+zf?p|{4_c`I&P|NggegHd?qv)a8qYPkJhPwU8t=I-3EoNbrLJlMhMB$WOR#mKE2^W9lz! z?7F4g&)6&dOToc|%PzS+>zGmC+Yvd|h?uRsrpC**t z5lUb}VN~F<3)Ub|JA+2@%*HhtK5_t>;7uTLQ{5c5AcWz;ZSWUxnpxS#roL7aqNok~ zl|Ws8q20H8KSnevx4#&u;;OG-U!VDo8B=m+1adGbAt4e=1Hjipnh2d<;1g}m27BWg zui>Yn+{Y})T^d&9V>0lw?C5}>nVA!3@=}X)&yOa7&5ln2OH;H7X(;%*3caXz;JR68 z^TNw3IW#*Pt*L+LU9;p-WUjwC4eJzGFY+8@OjeYE`QcGWkGi@*!wadZ$4tlVDZh8u z1ijyFd@$gIV%ixWs*DZ<=oKSIKTw8zlT_r;0P z+>{X@*Oa6r%HUafSLO9rjNeB8Y(3dxF;I(;9plr$x=TCQen*CQ_&luqBt8m z6TjduCSQS>WM##9WUlNFnQp!!mDzanP7bi1q1jR`EdF4XX%Y69>W?z1GU%dc$MZR& zB#Wc9)}vBT8Ear-0)Q4Iy*TZfQTUflB1-3L`At#<{r>hMe;hNcFmQ|GR}MJ=Vw>z~ zR#sN03ZqPz(1FcJQB?Q8+vQ}`S8O9e;SOQ1BJd^LuTYAEyK~Zv=xR0D`B&I*+P1!E zEs$Z=1^b*!ii>fLXPsX8bT*vC8-9h=lXaU$9f{l$7D?y%iS4YfCxNEM)?{V6pi9aQ z9v*j}wXmTgJIWU=v~0Z?aD{^V~8L+Ie57TTvq zG6E-KB~XnU)C(#`ED>UbT)%1^rkF4N!S&-%V2C36PfDPDgw&Hn;p`Y>1%?hdV3E~Pqqg8D&q$I z)2YC%1VLv5nEh${e$WaavFx5PiL(1SXl2>^reqNA18#0mnar7%xhxiOMDu(3FW6pg z8_wPnDodJ4=E&v&q1fhqIJOfa38NouEwD7-f|ypqHvy%98FJf2>))v=eMD7Iw>96C zv)HxHJ4sX-f9kYM%_2uo+eIbZ(p&1@`>Vajt0lK?M{zxT;acVTd#`$VI^u9lMDYJ! z+9691GNM!>e!|?E$f!NFGWrKq9E8+2D~1pnSg(epoGbpaWaTDJ|R%Kz&FgAu!j8=}&z$0*UQDQ`EKZkIsT&Ieov|z9X zgagi7v=TulEMf3Q_xK}ud`HA`Z{$_~8gBYG&+kP%j7vxu92)uwSgDM^CN5^_fxKDd zWVdThD~-Q=gJqW0F9BvRHVauq)?af6{BwZS1NCtiMh0t5+j1o^ujyzlNS5jNJaik< zKaF(I;laBIF2JSWhdoeXgia50ZB7^`&L!vCM#tnA&e#6~o_GC8B^ydmP!MjQ&s|_d z7C;#+R#U1y7NnNjx6d=Dt~n&w4C3S1zuP-wo%BY}=zjL7REp){(4)Gew-6duh78?t z>S+L?l9B(*YH!H_@HaR(d0d&nv#`DIP##QG_j#nHS{`rZhgxa!1_S-XJ@9jYJu1&Q zY3x;Xe#R}Sl`eJZ>2Mp?27puP?>-$Ywiy&|OFOf@_F_OTKnn}V;&kO8jQG3?YkGUm zNdovT*1HARa4n!&G&NMNplE;hvq2AuAC?2}=4W&i?p{@0Sa@9pjn{uYiDXxymt=K) z87G3F(dHz-jpc|+$T8~kg#2GC1E2S9(lx9Bd-S5}83zw4A;7%ED3h)(MGNbsE+8yS z4uxy1&hxAh;WpToq;KX46__{Rs!BTMNt>g zW&YVNI1r|gA1t=YY2T<6qJVaVOUDTWGG56J{|mIm6`Uh8Gd;U(|51l;GZ~ggd}u~} zeZj`nD_ZLvey074TTpz^ETcl?JDYB?%3J;oKEtvQq>$aDZNkKSmxo6a4Gv=zDqp3( z!QGnTsb~U+hY()2I;j%;e9PVvt&^uKEhdxE{U&EH+EP*lOT&@Or~nL}=h_6ZRz@0x zl{qV*9I3tkad1t0e0=$U6}i$s!FHg|8@NwF-~hIHQ+*!awDzR%tuV?0g4Q3vpR!ZD zn&n}joA!$!wuUtQ3~G{#e2&?$ho4o+L?x+ZL+wMB<_UYqdyZk~ty#H{p+@SOiHb2F z7WrH*Es}mwbnBJ~T9~=Nn^cGevWr6?VFw17jJn#H#Ij&Z~7lTYBhan)yZQ#zOCIpaYcegbHnnWIa&3LokLQ1S5&>t`vdsLH3BPeJAt!x0ND$tt5NR^ui2c!dJydM9ASrkomBsCLkPLbn*^QA;*FaZMI4OY#dCB8I{9!MJ`Ceh zt{AR&Va5!sZu)dWDE`MNE_<*_P}F|V&81E{lNEg}!0131%Z_K;iwu@!Nl%`@TsrDY zIZk>wRI#_Z9ju=C;o+#{@vmOFLJ6%j268}xg{)6rhX4$n$0OvtB?|Fb%5TRq;^H20Q zn4NfR{0WZMRs8`ug8K>F(kHV{lw=4+$fVRo*w8>agf42f4;o3ye|0V_&=pC|bE#xI7)!}OrJF7sWSjMG11)qfMN_#JdRm9wRHC(cPqybH!6SUiv~i8l2eYQdgUrq2XZ-Cu-cEn{=e}rB zS1TK-Fw-IsZ}2b0>l6~p1k0vi+@4RweNW#cih1pk3|g`c4Ck^VyLj0V81$p2wv#Ha zUm!EMTOSJ#V}{fmJw1b)osl+3dZ1mY%Nd9!2_;YKdWT1$=K9z2);&{Jpzwu{G{4|V zY-^)5YN2)fO>#Y^o97<)I8@!NS}kf$V3HxVXlgoXq|HWe)P>{$+In~vYh}l@Nb-sR zw1YNc+0QjK>V01u+eH?!0UL^wBwCx9LC%_VP}?!p=0HAwT1h^r8g_I*p*e zh<>uOgM&lI7x+1%p?M^~FUn{eD7j~7vq6_4gXwOiWOF}|$1Rd)?UQstk85$cg%UY? z;8$?#XmgY9=2PS=j9pq=yZX@4nknb3=UzKgjJtf9^XkkD$-V`GA(FLocUS2vSY%gS z4_b?Tq7uAAIjuGcj&@WU5Po2i0s5!2K~z)FRdUT1vwWuL2c!_4p79bPl)!LyRobK7 zjMyKGoSk-v+a_(UY}xiq&N+d!)hVxc)g0tKS`?A4Vm=tUF>-c~EL8*!J}9gOQtj1N zJ**CdfX6j#(cWu$;+;#|`=D6B{{ofgP=BT8;-es6{nwY)&D_qat}1B$Y@tR{3&ldp z?q8>nPma$%DANf3M;QkQVK>c1YA%P=p3Pz!DIX$jE7KJY`mW4=KV-N z21rv}AG)aY5+U*xHppV)kitHH5vUU7+F5ir7>9pNlA6C{!}H{ZJnKsgzGfpA6@Aya z;6heBO;phI<*CtiU<$Venw>MFq&&CQ*BxkGi7*!L2bYZ>KJ0?GsCU?0&;X$UfTKtr zM1}*Jc$1Pki&pk4{X|BJ7qxQic@@D^_)8HZ9&EC6eFY$!2k_5pf6qpnl{{Aa_Su^R zh~yH_6^7l@$H4D@a$_=a2n>I(!)Jb`O^Bkija}x3 zJu3_h#leMW$UI&C2T;tn=K4}GF`d-4MsS%H0f>R7Q=pNCW+geb>K1Z`fyYm1?{-a{ zX)xQA2WsoQTkm-W9z13mK_+Lu=9Ki?p!Jmqf{VNxZ07s(y+!bIZMZFfUhd=qOIa42 zGTdZF-)nQ06~(Ru=G6hg10G&47Uq5w@F&;Dg*lWZ4ogEN?G-!}zd!1=OI`8(>)mdT z>B)^q>!%B^PCz#IL>86=A*o}6{bYsR3+Za-+@2pQ2u2s0W5iE1I;ND_p&iUVPCjsz zU=wB{#xZ4Iz>>dB*TVY(Z$2c&sZ8Uy_^yI2RgLMv$)tx_MIY#3XCbN-|f|^0Ez; zD=CKeJIC&Ub_SQSm`H@@D1a4Tf0Ts{egBbXeo6ID%J`)WsV5Kv?AdAkOkWnFH0kWo zul0eD85$X(vMGyDM{^DCuMOj0c8!su;ELWD=uuy;vI!o_U{?Tp^Sw8KS?;=IJf~6&nVh=bdrxJc zxXqt*jnL#5rObom*|pYp6e@06s7hK)Dy$cMP61L&utWY3fZ)z}Pl?lq59j^+(xgy| z6?3PTdB7SaM%CzK{)@k*xt-bc53|hW0iLJ_E%cdDri_LcIy9AZL-EW2$O<&?tY(Vc zP$OV|EG&j#9u8LV?9u$nCmAmZ$^J0UYYC-;)g{WdYmN^90tCX+I;G$xrFkMEv;jm! zZoOl|HaF|$4uM%6BVuU|AnV{YnFTNvgSssq7fkP(*I4|BRl%dv872fK#h?){ZtcVi zIE2V~NXCVxIk3s758LWp;&Rd)LxQtDLvKMF%sv0{E@p&g`fZ-yV&OBrFPxXO=N>52&wP=;O5drAqY!KGFPz zC6k|Kx4Ri@1D@%0l&|QUf*4UHY^W8=E{ep5X}-DeE$Tf=jG9>nj5pmw5YUoa3JM+s z;(4$xTsKci`{HZ=*UAwly}(XMv2eO>P7gRJc)BRPDYQhKI1>`+=zXWy%xj(D1mbX? zpkn^BtABg>2KA=^fTyU)QR8kKo+%x9JVGr|k+ubqy6vF^h;L)EVv09iM5HaNZ~3s* z&^cn{487kth)~w$jb(CjfH{J-4(1a1igCuD`=QWRoO<%;vm;%^bV3;uv#;G*N{nBD zEblR!rwY-;wiii7WImjNdEPXYdsb(`rjv0B2QwU8q{(eADlwNJ(_@c=pDWi>t8h>?@T*OP7u@MBnaouDu zfn*yngr;&i(GI&6ZvJV)xsN?bBb$>uf3r{OU&824 zaVJS1)uGOZ_*WXSAe&c(MJ9H_xIZADFdf5_ZBWrh9EE@!)Pr$5vtm#&1+AcQ$(sD?k1Pa z55z>ZU4vN}sjudl7Mly4DO?G@iX_Rt6)RpGj2*d`(~_^Z$%!$>|DNC-?xeYMpP}jy z*^J6-<3oRxbXrIO+cwKbH+2lDXEN%246 zUKq#5j|R(uygGP>MC^}U^wMP#T(5cd!_|?A7sH!}|3f1_9}z2Qx#Xr0Ze^?4lZ%8U zEHxH?;Ne;U2_6qXw%){ZE9N;7VM|&>c<_;h*&`r8Y2eGa@J|%d*rk(+8t{+v%RYg5 z8^M|SgQ2s4KKI`TCSzllgaIb1yGe!6eJje|(_ZQCq7{-ovqMdlT%v`&%^+WKf0|da zw}{``J;DUoo)EbKwqN2b213oDq)2=tN#+l2&NwQ_=^JYi8QUxi3_giezecXAE&i4#rKW z6MiETYvK2B1=S{`t$-hoO3S)nF6s3+)@n8it0qe;0#=%qw`6HzX$ayFUX4F>IlqJ${*1^X4g^v>v?D81vT>rISLg9G z|8q>eI5e$@GblH91B^J6PaynV`{%mYn*)o00^$s~I^v z(n5O!0i(ZFbKm(+{}YO`f9ZzQP;{iNc#2Aj5ed(`76@*_SDpUhl0d&bes;HGu@eYxh|dRSAW)&7V1E7a=`~D z_E|@VUr=ZpVm}v=e zL%u%xw~@3iAG1niJ}D=R6?qqAIWNg2iGa<>dVwBED#xH?5SFV^a_yZh|f z321dOEQsr{(-R=H<46LUs}D&f41xOG`d7VMNnauPYS!sgSoj=Ef2Y zM($M0hh`cMMhtj>6VKYNj%VfyQEUtt@JoJzL9I9#S?@tkM2&M8G-%z>ymm%jfGD-F zBTq2DH*2xdSFlE(7c#tmY5(d(-6{Q#$_xc>&~o5^z-~~W3)6Nz)3=E+R@wsZ+@3ex zO8{bY?7{t*y2rx+V?FI8!RZ6C!S+jvltH2MeMwhiol+Ua=i*|~&ixbLzS^@|08yGB zs1gi&GNcqVSFq;$`iQX}9BzzeD~s;yV(jUlzUd(frag_t%K$Bw&rn`**c2A`IHiC7 zOKIsFc!5(bfXwBWQo4Bt9WtSjcpma$p9~GO_1gRGj>bz3Qu5}5f5E2a_R1-wt5sv+ z)A6@OXow5V>rwGudoc<)Vk)OjPt^b1kH>FjGZtst$9tAtwG<=FmXtgU`)Tif9G!;b3y#jM&(_&?u zeg|$MBL?#w;KHpV3QuX+Xc#&Fty_^yGw(H#Mhit6eVV0s*41O4_zlMYl3 z+lMEU!kzWdUkeI++7|&?-erpWa5vwNjFqKg?$*#U5+N#>mbC~LT7m4!23lg>a-Nrk1XH+ zD;DhQCU8@Z>vpJb1H54T}H9(h-Df9X1=9l}^) ztv#!nu+@biKQQ=otr)hyqWr7EJ}IWv5@b(^&rVPNIb!V^^alNPud;8e(EOr@9!X)~ zgyK+x0|OW|fgcl#b<+>xctI9DmW1vK*!2d6U%Nqw+^q80jkpkM${4MpV4KYZ4{|A! zyn6Z6h?9X+9RIk@)2DVx9}GD+rJe=diC7=j8n<lUbm1xwCXg;cPvKlOo(K4+lTd^uC9V{$`~{mMOp zl=$t@fdSdb$4J=OvuAa6b>|HJMyKuNWUJT0Zh79Rlr5yv*Jcn8mH853W&k6;8(bQt z%?nmlhNyEu=bFU^pMF$p?uipd0?5 z3!JD?cEAT75%&rG)56w2C1bQp`hWlaaTSNe7xFIxAShqbrGei3$#WY^vwc=|_>r?S z{j4;CNzCPa*J4z&yA(pZ!5np?ijAocJa zHiht&{dH+}3ESw3J-}aA-2xFILa<+%N@+C6tIuerhH(mFl9CzL65jr`rKXG_lhCc; zk4nQ6mSjGd6!7|kJKDw($Xt~oXAl_)2??MvvKArZzu_1vkiguDV%Gn0^j+dg&W);B zmW3?|33c!h02LbOr}FkJRI$y*H?)&I>wdLhN4QcZ3f9MmF6Mw@+4Xl>R_$$V^ms-S znlXV)i8{uGJkqDo@EqMNBxW>|mpC5`0OcM$y**nev##*ctyT^b99 zS7hDuVY^s#i+OTSTuRF9V>@JQS0!Q!V65b4A9VOQ3Q3t%JepHzmwjI9^FVcJT+VGUA2~S(7zqb7zO>2>)hAi z2UTFVieULnVuMnvBo_83)P?hsXlfkB$I-+2Ol2;C*dn@KhKOG=e@YdKn}aW8P%*vdAEq`Wpe#SPl$TdHIAO_yj7`GN*!w7BPvp zF*V_&M3kTyx6j6t$x{+ODuV@Pn8WaP$YgBRCv9ng?CRW}1-MzqCbJ<=U^oNJ2B}1& zDtyepr5OolME&McmfPrAS6GPnhK-sO1Nn_7{{*JuV5GC>_<+UVG*NqbC?RVD)Mm$v zthgJC!1HH&WSjuGNVLx01I*(XDR!cl9wA@&TZC0>g~U{0ln;Er>3aLbJ&Gtmj%639V7cEIC!q@J_;(KoIp;x&4X$7v`LoCmG z4fxqyff)ewiB-PfP6WOWAH4NW-`;VK=VW##(m>DN&C^XdVlqW|40E11&DBd~(zP)R zM>7M%iS5Ne1BrzUp^Pq+K8p;tvr!A4bm>+XsBTNy-xMYX?Gh+e$eEz35H_)Y1j?}B zOUh+?=+ftHBw!{@e>#@Vo_UZtDF#dlwM`-gQog%qx@h6GXeqRNDOqhNkaOH~X@%dBGyy{gmiY}UZ^bMp$CPx6t3=Dp_ z+(JqNSN6e}Q8#z=UYZDbj_tdf2Nbn%X#>AA>1K$;Is?}-F(GG5pGCk7C7VW&Du5@! zcJsXG?s)?sG1yLuF`PpFfVUI49Nwh*;Ot%;-u$MZp$|5VFhBND^P)3iqLNs&@4esW zLj8MQ?egR!=7oocmg9n+_Ge_3&+srNN$@cCfPXtIcgomp}%9d;Q}V8c3`rX!g_w(X8$cPDKVr z5T14){jL0?;%agVx{p~|S@;)i zKiSe^-l|6H0NbOj9a$Ij^7GfPUp-)U-SYDAcGtooNnZ9Z9@@7QY!W(FM4LwNG}zjd zWCsRnRgu%v)59>gC?Nr%N+^|3gB}l?@yJNlf$>V zeuBpX2BYN)tL)NC!$a_)a1iX>BwD8f>*C|%nVFe?@dv|;b8>Q?@{@1s@t?JZyBqBC zz>rH^Nm;oGmnILFm*<(2?|IJ#+Kg6LefjcbaPiz;CM45YSx?>>xqLwry-&>*4tUnT zPyr{`$YmfiD+^@>e}s=pOG_JUUp&00jsG{s8u2gIJy;De{(b@CzKz~2u@kcYk3*kzDv8$>E_gNrT3wyc+@EvOI zJd^jMV3Kh9;OBgrd+&Fj^PcnnT<3bZ_78RITF*1*i2J_B7;{oWXUW9mKqvfx z+|8{1$B!SwC2+eANsr*r+L8`yK4%g7O_sHph1M0esFy$iI=(wR&6SzS%eyRrr3wCZ4X zGU{DTPp@S@w?DkXN*vz4?1-3s$<-g!+E1{ud~_O~RWU%Q$M}}z=yCsm9}@z-rI#bx z4BeCy@d)LLT;O_UB{EXdE*j@Idt}?CCh9g3Az4-Lg=~@LpI5jIwY7)fR)96)gItuq zhb)>gv$0X~THWUSeU9uBY^CQ35!^MXW4OeE6Qm5Q3jJ+sb7&)`K@kqnJm~0n@`IKk z=C+E83eE3xn3@nvkG}ghs~a0P^l;YC^3uYz(c#Vt+?g64xa_0gg8EBp;12ihEzcpl zyJ1vxGkNX;H<_Dl@1Otuum7#a|7_!LZ$SM2 z)*bX-t)bm^?2Nuzu3wa!#mLB5r;K49omWusZJ*WzLP$w%EgT{HHi5|47k&ePWY>WU zu~?Xw$IP+fGA&LRHp@#MB%KK%siENrV%?nRC8=&7Gfjx5JqFhik8U36+38;Cd~%yB z<;g#*i9mbDw)nqT^Y?oEFY^9>BoCpS;rz(Jz-GTZt^d(RN1<-R2E~SX;Y^v|7h|7=nVMI)-FS#wi@Amsh5ka#u#U|mwsZh#N2rk9=FkoyZ$19-El0?lYQ{;B8|Q=RbOgpl*GZp(f;q5i#>oU zV&QfRJM8Lin5gq!sU9I=*H_om8`({J#ck1=pPTCQo_rwSWJFKxo`;5O!b?A01@8|60GXLGD*P0KZ-*IWEn7SZkyd_t^?O z9tp&y6l6bEuNxU1^&ZyIE7mWkpVm103MKdoxQG1&-qBj{CtNlj_|+oxuHbb9!k_fN zR_c~Z6A|W38=Lv%(MmqeOdvw{$7(kQl(;~8{&>5J%6GlxqVEz3I>Ou>tGfHR*D2un zMo4F7W~Px-qkC5@BRM_}LdpzjSWkj3E`UJ9VpmgC-Nr%eXIk*{tv2pXGPoy?`11@dhW$0wxZ6`H5YNI`g&Y7wibL|1^svxF91eu~4 z)O%og*&`6wu2>1!#*iR3JJ}Zb%;8JnuPJdcQTZ%nFr|9^nC*J*U~m5vPPl*i6cmj& z_eM8&zB@_oe7&>1y)Aw`<gH3w_xJbrh?pwiBe>Pk4CVrM zMr|Yy`lEbAGHPr0YG%{evcU_3D&}J0k03qf0+jtZr0+r@;e>iYCv*`Xj0%xtYJMf*ujO=05OvA#?5ZF z2lIWAa#>hvwfjGla#d4aB^p<5{X5L= z*v(-hq|(s;Ya3PDYz-w&kA9PydR?8)fD1nkGQ&Ba-lX>r<8z(u^j)oEn$7_IAyp#N znH?@%nr;o*?>mnO`iKbzxZ)I;>nD#nr}y9uIN{cBi5Ipea#1w?8||b_ zVq4%Z9v&XAW6f0WO*HI-34QW}``oOQqjgr{vUt4`ez)X_1_s~3JC&e zWRvFa(JK2%?6)%Zxd&5ChpR@-0sb{Dcb{y0aYjV9)Jigg2BF6(y zk3;ckQ`bKimNvaowK{Y3|EKQ~-yYJ!>Ns7QJmHvoX?A)rLi7wqL25x5ohviggs^fv z#}&9JC~QBJr^MCBACmhDPA^82)~y490LnYhXw$^JUDepa{E5SEs*23TAwx;HOq2h7 zVTH#E;rdyW?>vk0#F)5QEZ-{bq9VqR4mMWS9k}p3uIy zzB*r z|9ebBmua(oDzP{92szV18|bH?pdcC(CGztnat3{SS;@%gd-aGZrDOmE<46ht*4=#s zBANicgHp&*Svd9EVbWW2aUVCeP&nXcFbW?bC6n=`PGE2GsGNjzm2JZ(o8&HG_R0xE-*k?8JbR5+j zV#vL}!gZMixw5d1iyapcbQ$UnBbn*B7zioN4Bba0cIVQiY{^t^v6J{7Z;uesEZLFn zHo=n_w{9F996$u)e`NFi_b18IrNUAVN-93>JMM{qqg&fE$QbjU@c`)=g857qb9P^W6DxO>Ah8PpEEd zF*j`j%y1k7XuV_o${T*6ckryu=Sy5?JUh5pSt%s^yyU)M`+DbSycrSwfBg`@tu1Aug2p7(A-%R?&jcqNOGt zzy29wTjC7(9!AtZ&s@+#tPdC~pr8BIQy@3UnJl@;?%PK(4D#2hCTm^p$oYJJd{O%P>h>M$LWQ5e~a9Ou*(f4367fx0nqNyOkLPU$78!0(=W|G>ESjr%e zA449$A};<#3*u1B9;irI9WdXY7PEI;eW&BuuabJs06%zsh=X;XE+T^Nk=@gAJor*# za`=7nL~uF-6?2xqmW#k$Oy=wVEJY5*G8Y8o&t?>Iha4o~)m2s3#I!XuVq&85ii(tl zCqUi|Z|B`4@Fxv#M_CC-kDip0$6JH=q6_I%Okk5QF1=wD@&|B*l~%Ci3c|8HeT?zX z3kYs6G~;@Vvy7*SyORJ2?KVWffL}0Rwy6HPpbAh~D&BTgyw8ppz=O4>L&usH2*10_ zm7n@t03ca?GB0!;)HX8<>|#uS@l%fJe%K}d6$i5(7ue@V^6#o0&VoD3uz53T;fHL= zR-o4XCKWF}F3xI}K~YJ`SClwXjt`!G3vlGgs%P^rL1C-TXoE^?ZxS%}YmW-LRR#~& zngd(VN$-tTSJ%Z2@YC_p%9<+3cxptiooaISQ283*R^@wesLFpi6p|f6u{HVx_gmPVB*(Wb zbF`8(5qtowzTD>)qJ9oTx>y|#)N}5Szuo?s_cF*o`>3FaKp_8PpC2mWeaK0@+H5sGeSfoit5q{Ux5E?mMC&BI zsb{%Ob|bTY0as}3@~L`%2&t(skgcKsen9cL-Mt0i6M)v%xB~Z;2KZ1M1(?)gNZku; z#N~p2y-bP$7%4kevjzVQD=RDEv)!gs@8+#7Wi^eR!Yc3IKZ{`zzE4?%QhN+2Fx}mL z0M+Euvcj>ZaJj5c5{JtT-oJgi-t+)DK_LwY>A?jxPT7o{KJ)D%wxVG&36kLi~+OXL@wj2P-uL+XM&N!Ux zFyEI_56>~7#>T=@xA!BwdArz&B^Iv3q5qFDm35-NBMtQ(TwH3xG~w-lc;vcc!0(VV zu&~OKUTT6)6Mly)H62lt9^dbai+7?-#L;K1*SALi`asMrt~SK#`%az$JfJ0w=yqd+8Qdo$jZdhE4V#$0~8| z4fbAays)P!7gkeKN zL;Qk*A876E?7D8pe}Mrerggj((7`+=NZQ>VU!BEu@+R6lnU= zBqc-e0l6^1i}{X>jrjq!!4r-9oI4> zw^YS)l$Dc*HCy+-LeBUum&?ojfK1TPqBVB{q@e!f;Fqt#lQEz|0mr}0KE32=levbF zvcUd3{|a~&oUs5d3OOwvi&i9ZX0743s@#v}!`1qYM^K)C+F6I^j1q=r6Nyno zUiT}SXEWPZd=+yJkxu$3qk9~VG!Pgu9vtjfcz%5xmViMnqSF9{x3B;6spffSpBgX< zxffC{B-f3Zep|Pm7aVpNW&qS%H`?Ha*WOM9;&b>^;g~+VATUL^I}9lwbz`+wd$xV}sV47pdLUMJ=AcU3{IyOLl*8 zAP4J$#L3=#TO@*ggywrUV#x}(t3{b2r{q#EUNL@qRLD~IWDP+ZM;X$z-xlO;DCJ& z4u?1zd+@0}3IN8cDHenxM^G6Yzm{1HzE;_oAvJN+0GRIR3UqJgzbHD2Wi0J{b0|%H znhRSA+F8IY2m~NJIJC;1o~)fZ?t&A!qI44ww4Tux<>f6b!i^{h3?!Yy2EZZVKuuHzq{UAGJC*TldLL*Dii^d6JYhIU z9R?B3_nYzwz)cn|t~Fm~`0NZ&$Ix*|-s7iw|4ak|>Hp~*Y@pUl;Mmtm>~K7QbIwXx zoDmJWOCDq@JsF`i-v*zHH=k^ml5!XhCD4I_1@y%ms5TMJ@uFIwq48MMX%f^3-l*RIZ&@6T2Y399%DB^&Bn$ zAj{RT-dfb;m|s!hdUCWs8V+em!@2rb-}$q^iLQILzpWV-{3g$@tB3*w@cHI*jMDaS z;9sVIDERWuGZdxMt0Re&gTtHv*lYkfZvxR#{1yzqH~)CbRuK;Zh64q=(=5%$Y%pW zTNpVOj4QC@UsPmj9rp`FI7T z;&#WgJx?_@G(0FhJt&<#UiA#crF`*d44hB^#9ai&(|_Vlfi$QC6mpe?(4|pQvYO&K z0TR~AD*=b4U%#^YZFO{pzXGa@qLlpDGpoHeTqO`JqqC`H%ITS~L zW&7&~(-;!*-@k$HuIGmXApibBQ*8rh`|C$)>VN<1f2;AgH6YMR_$RRtVJOy7Tr*)< zVbwK|qx5TO=?ipB1M>kxZ^uG$fQA07-!v!->wII&FY3NDgfDsIJl~RbG|L1^bFZGF z)Wb?bO!ShB42!LW{u`&dpx;9Az_JyI<=u^m2$H^9=ot>3UP>?6y@5fZ^e*`LVv~B0 zj%U;WY#3S|D))0MUI+h1#gox+GfhoR1B1Hnz||;sSyjmH&y%)G%!^W-p`SbHF%-9tGcGfhARNrfRa)Vh+C2Xi&8qE*nq-X zIGnXpX}}Cn+GrzM)9tKWS%A`uH&52v@YO^Yvmvp*Cc1W!=bTJzW1;A~scA#(XdQsU z4YRRIZ*hSmK7jI%cULIYnL?pf++68)hcWux{mZ7Sz#zS0ao$u{`}0)5f#QICyuMZ0 zd4I%4(E0ipC`@=0De`i{UctwS0e&|1+i2&Xxzu{&d}jjH{ccQy;nC4L+x|>gwFjUj zA0Lb~pTK|abSKsNW#%mbhbsxA&7Vh~K$bHNo zyG8;+?lHqNVfsQYdW;I`Hf9UM8pm;Rn`D>HtD%0NH|+N@)&by+I1TBO`|~wWUddHU zqmc{%{qLs)dAhj)7V=?XMa3o<+=AfV;Ut{CBsBRErEDXw!Ky(ibMok?P$e-{Co66i zav4?d0COvaqM$ARt2JYvN?1E!FIP~nfl&o?J7ISjN=H4O!Q9MyD%oZzVT!}(jT>dd zLT0#J1X)aiUr?(R<7JF0fCpvYuV+D9VQz|tp}f5OnaDwA&}h_fdU81av=xzK5w|`L z>)S!~Kv`B+wuxx5A4~z`ChDu+?xX^}^|QJ7C}i^H!2;pK?sagGm`<&=)K8C*8HIy%&T>n&PPPvW=JgeJiko97O0 zwJ|?x1r_8C_(`#8qv&MVwa@+i#hf(D@M&Z!MVhq{O}>riGV zxpBB$Inx2wU@WxuuCEA920`e^>w~I0nl($DeSc8V1V@Qc4d>!cCX|py0h&V}C6xN! z0Ga`*G&?`PtC*QM7}ek=QUQz~l{f(t&3uUL@#H*BLshk0t3bjoDRBe>{mJ)iTWwCZ zawSpqi;Wpn&2RPjIqbxEDa>~uL^}es0a)TeDG3@?YT(I!LpB=Xom9ebeLI{{z8laA zDE5=+ucD#g3!~Pd8m{)euLR2Dpi9le&5d6`;69*n`1&ZZ%}%IHf?zvTs^)a>UNZ09 zZj`#51I?Pdk^^Af{@8&Tl>}!26?KC*@_V>ynuI^3d=NaDt#r>{y@WDj(6is-avD}G zpiBg1WS87vzl#bBf6XlbSrQ-5RPW@Eh}CLuXE|Xa4Z8_)TR~x=Jk*}vox7Oq@_`(D zV;{gH)b6%GRYpZp|Axv6nYI9iegd zsCMPnLod{m09k~+y??Y=$Zya^b027PriY)#{gpzRh{X+^GEQO!L4tOgSl#_ z3t3ShjJQI5czaGB_1!2Y4M*Not3k1(aT)2;enoFfXzF15m#>H@kY?i8k8;XEba#&+ zOk>u)IB)f3J}oc+Dhhyx0IB+}RO^A{j-3p9^dTp~ltNP9%uEu<=@^K%fA(f)XD1a8 zo>L`NOeAGW>Wv*4BU;Su*+R49B}%6TknhyAb#xfTPob7l4~1CQXniw&e*P_2x4rdg zbi%W3c*s^#OFw<5B&0I#95FH5!^;r_406d}0UI+Q`;R~cKlTs;3EAgO_ZqLg=};RM z-e?vIIV^eLL343hy2XaoK+LX-??aEVQJw2uyb49FTesSS&O%}K8fZjK;HNVkOlqlP z9YTeO<&O}o*s(mxp+NCU!rzCTq{oF9fk0#T^$Z6QyjRnTP74(ZHL~Qu+?QcZRegTi z<)-LPv9SZoY;Pw&VeI`ArWhdWG$3bSvw^*csA7;U6rr^S@dX_1IRzem-WKRIA`*gh(5_*zPoib<7LTh?b!d>6`&1P3$$2c_|NZPxTlR-?(M$(m zTaO=MOg|-P&C?;>U+4!-lJFU*B3X@%;vHQOFS5a3eVhrf(~z( z`zmJ-F1AWy5k1JQSZ43wkOp*d;!}QUDc7tD>PqN~s2B(68n*faEXDKn&rlk7O}=y) z1JcgrE2N~8Zi6aNCI#rxZ_8h^2oFl<8P44aW@05z?LGuKp#M-L!PLjDrKIfZSTf z>>Hw@ptylnT7xQZEGn6aP6b_P+KexSQi#ON39YXu#pU+$org_{1UJ=@QcrFogQhrL zc59Qe`hPEJ%)H1FdDZ^@rvGrQgR!M0e^=NmvPk(El1LYoA5E0I{$>Q8#G^O0qy5dT zS1+#4ZJsw795fl%8a_VtSIjG4%E&!fEXaI&HYMn z6kss?-6dF9_$I)5Q0kh5Qv&7YbPKm(vJLR6u=nO{3WVLsrWDYz($dyeR^WzY8gg<2 zIAy=}z{K6zZ5_8l;o?P-{pKeHVMF%SA3l5_d1jHBm38ONo#(N!&_9nRou{55lcN|9 z*_H(UF(IKQv}eKV$=|%GU1DsoSjutWlLB6XP`D|r{a%byF5@vpa4LvFU|V-dz_@HE zE^58+)N{_pd-(k3IV*jvI6U%Co#at1c*`?0e9lwv;0+QuDZl`rV`Go{H}Q1&%tpnO zF&d6;$k#O8GTMy7silv4vFx}wX7_%G&S&T3m^658Y%LCYu8xI;h1GeknOa-F?y@R? z71>@IZfk8_`cnKIO6{mZ=#4e=Q0vNDoZP|;%#pvIlj>VtOrM9_!e>u*7Wx@hvR(cIHt8x0InnHNj$_gbZ1B#)e{r%(U__!Iw{=?n1LW-AeA|mi^9|?Rh z4xulD_{*oms}-a7pfCWX`qwENI5lGq#v zH?Us^y=wb> z6>#`s{MOCR$LHMs6~mgib}kG5*!{*D&)CpTpm~(aD2dfiY3A=W7O5vWk1AnD9psj7)c{;_(Lv@ zcQ{|m26ons3nrM3-+bkwq@^`G_#KKzO>br!UzA`L9!C%f zBE!S82pe8P^m1DrGw?tL)4>G@?D}PNLPC0tbOyh$(BKma%$l2GXIL<0%+063Qu)89 z&asagnD~evrK(pDxUQv&`zi*WbjC0MCyw!?0>{st{lO^i8d*xg!omW)RozR=9b~Cb zDK~PLqmNEInR?b}f3Q4rbb*3v!M+F+H8GdiPHGI_`_n zw63d(%Gb+Fy?`ep-`LJ+hUyEKG18qTyt_^Bf3&v&(K%o2RclAbJk(Ydl$5f(q_jne zsDIogwntvIwSz!LbZBDz@nuG~wQ)<%9VYj<*Q0o>ri39D7L3uC$kjxx`Dg}ATp&zZ z9#=x(U#c#ovA#h=j)T(|@v(AQxv#suOtRQqQij#p{l&9h7?NxqftnlE_{WhEy~bbe zR#w+C7JyM>a*CFaA`D_nOkDuPVCCb@ged} zs+c$Z4!%wbhrP&^;d^b&qsNAYx=!4bs?d+S;9Q9yQO8BZXRvEc*gsH*au@D5dkt=BHlwu7SH&?Bo#rZ^TJo^p7n zDw!*2SA~W5K$l~^Rft?J;%ua$QDY9ltgCr{Pm+V97#^oPstrh1o^qFdt^MrW9MA!! zeIAy9CjY~W_%zIt!n4nF-fyl#*Q<<-OdRq)Z=%P_Hy!J15S(D3N<-5-L;4Yh0XxZ@ z{A)CiCTW?#7ZzYFXB&Oq1FvXnay)2%vQLV>x3iOs&-zmQBje;Qt5>4#1rhCcIX>My zZz`AZfjszypzG}I^2r~4DR6xKhbzX|Uo_?ID3;TIFlvxd>7MV3-pDo=o4Gn3&+WJ8 zT>iRxluZF=hFa~?4V*sCG@DWK)cAxCCso16m@KWs2G}p2Un9ja1FvTq(e-iQz2f5H zGV75eS*oa0G)I*y7(pZEr9OeTNf;a)>^RZDa^oiu4uvR#tF6@S!E~1eBML-~hFn<- zS{`edTB8-E{N>s_^%kftntg|AY`a~A4MRA!9xH}YQiySGH0g!!HC*xX@0E-dSeTg? z26Ln0-dPo8bNfEYR{ISpQ(kDVKTDo1tfA`BMSR7;@({Q2x9-r;n|bA0rFcdaq;}1^ z$m%LkAVgB{>ugu!7HUgwaJLUS%z{`%1FQ z{GMbh|1Q$~Rc6sPgc$&yQo+ErVWgZUVG@an6M{sF`5$O|C$sM&3AM#jgX!P}LRRV1 zWegq3?w%quZ*@QJ2Zbf&z-4`RS8wl?^@yp!3jjfjx8sU$g_9`$EF?_uod1|8E3^!V zleFD=<(t4#VDaKu9ba)BkHciTqhLgZ$KUHb!l+r@fozXI>3QC8f&NhhZWd&)NI^6X zi^(Q`%NVxPN|KVP*+*^GOUx?6)Y=W#u*>+$EaEmMf+OT5gpIAlvg^Q@LTo|^*Jh0NV(}IM0Rd7DD%diOw`|H2A7tMn zs~)|F6e?$S*;}_DmnWo@bFZ|BOCUd&^mnBCcowNHU|gc>@K_vRWZ5=vv+Z{Qsq*~z zm!2y7Vb-v#@mgW^jwzJh7c%PA0zEJM z46Oe}xR|Z*+?Gl;A4=U^a~E%7fQP&CV+%}Ou0oTM6bU%0ZS8hJXEGNAQy#!$eMX2* z+^U$~Mu#Q9Fq2R4l5CV5f3c(r)VrqwOui&p;c0w zSmRkcQ)%gkTQ_3oHnz8Qc+CL$;Ryu~4piJ#8s*Y8Z)PF}DXGvp17-}Q74nGfU|Wxg zo^ozJ?r%OhP#Tt<1^`Y=t0wNMQ%V6aO7F;5X>M^5up-0ERJ7U)6k|F)-eqk+f}*IL3ONVp(zkElj&@NdJH>DZQ|!IKcI+u+eo|A<9OL+{N@3%n+q2M6d6@of1%uwg z&7z8wi4;NO;Jk4o>2l>J5tW`Z4}0#jfuXO`?HZXu^!iwCWK0=`R$?4oeO|Xcb3jg) zDJlj``}ux2=QB}L0&CLba`U;%hlAKV4BA*FeU@Gdu~Zy>A&(yuE@hm&NDaXuC4BX3 zvRQKcXL7r1-__g@06qDQMkSz=L2k}}S#A-x3y;x@sW0Iz9av^TY-{P=me)q+bV`^`|1hN?LsWDjDu!k#O%Vn2@ zjss)#H1Vi}>3D+Z3H3BNGJ;7ERm4gN9@p!fw8bp-?{n3=7ptSr_o?6s~mEJpS7 zLTUsGb$ooBgA~8>;nIBb@aYKT-W+}cV&W|*OQ%W(o^(BDf`hq3Twsp#`t|DoBV2!e zOnmt8q2^Ld&H0{NYRp?;Kb51(B@LQ6ioovxWj4b%@$&KEGd`k`A@mo*~F=3f=L`uUf|?h zEd?Xln~7>{Xvn5|3U_m~-sohJE1A%d{ZWt?8rlKy$P<$M5gMQnXbXn(wZX%a`R!ug zBY!R~vfQ~XCt>i`V}(`MN-zl!rVsG!xVX4hVw-A1K3-nnbWi{}ge=0s^E|K`1D67Y zrr})~7_!zoXXoePVW^-!45Kl4&y&*cVMUEPMZ-3Jq|sk&u0Qv?dHhNkKOD`_T{!pA z`Zp9z%I<%E11SPvIWhd0-o?hohW2*?Qc};&*)GVBHTJ`bmgaDekEWNDRdf>sIE_4u z(DZhKzHn&lVJoH8Tj%9T6;;%_bMXpS*!ibzige_>ripvqD5HcltW=Z{9ew#JZhyO8 z2V3iMFds=#=N~%gv7O&(!npf$MtZvW#*cP9hX#_`98aX?r zjK2O?z^&9YR!O}c>r-$ci@EFl>(9fuvAKx2#52?ZW@EYg`1+Qb)PJ!ozn$N0Urlqv zqX>>Zm=$hoYcufr(uhGRhealmk@vh@cqTHPtv2c1)oWz=ZGK4nKQ5&)`b z(KT*vXXwfSGsl~$F)T(sD(_t=jQ4hRxhzd}F3eh2dcy$4Y;QgM6{x0Ge3 zEbeFTJp5S0LzP)TxL(BiLj<{M3Ql5TqUMAf!wiN5@I(lG&R)+aVeTin+uEak+`1Ct zC|J!S;|EbR;>pD?j4iNGyh1@CMt>g~y^;%zFQZjL%l>cc#SL09uV~|G(0r0b={zQy zS~6c^xpxO##v3Q#HABfoXpuxfzeV>ut6+d>|Mxs^Kuko$rPk-F*j*DJa|aUjpJZv| z#e}Bcf(RWI6{VjCMaS0zX!}8N=14Z-sQgE(XWM=o8UIeE(<{d%0k*w+sQiw6`D5J@ zV}-&iPiud9dHh7BqFe9IID}3};R8EAMujGlCQKHM%Sb4vh;G*tf#!+){283yPT<;w zLy?YA)w_a8dc|-_K@f+8#Kd%4F*wilMj1}Qh^HD(Z}K$f+=Kv#Fqogtq8|g7NDte< z&3ewHc0Dv9I(n*%aEVe5U^KIC((>+do<{DtBe=?J#+!tM5#ZOeI;m-Cla)4Vo22mG zyf%gI9)qzpHM_7*R+5=vrLwa_PsTbr}%`^pXo3=k__j{}dl6SlBZmS)>R@jX3)RrC#* zdnYH&J}}7Y7U@gpRRUh_)9oA)(r4!5d#;|bT+Q*8!Kw+5eKQb?f@wgfP?vz!X}BQ1 zGO(4s4-ovy_XPF8cvhX+;i7>=+xh#%_On-QW1xXqCQlJhhQPQ*X@xz1=D*xHZWiCK&PlJx_&<_a;u=VB#_7r3NIQ*a%5kbe# zNw+Ri%00aPK`0_NGz_kd^%iT25sKh6Yf4_Phx)gq*SeI)oJW0QdV0E20w?l1t4_h} zGDWBs8;k$JR#$ho<|f;^`;+Xb&f}w_S=wwT})r>5U)jg+L0kPjI^c5UH zMofG&&#xsIT@y~^VFETzFmbOM1O&zmxUOSyFqcRMvi_UagDV38ZOmFsaf;dV6QEG& zc(4g3-G_WSdyrz%JF;2eviz0D^|+gsDE8H>rL{FR+g8|{$ifeCELv7KlM)jZI&Zam zdwF%<2rJTM+jkNBNHbhTf>&1q zYN(7{_0oN^Ia^};^{ci7tw!Zze>EuRW)p+%7)$FX53=wfnPWQW8eK8aHhE=vP&!02g_y(XW zQr#P+Zx)nUX!mrpIKo57y=(tFiOx{UsU-_bpJbKqtp@m?~jPmhgY29u=EpfHOBc>*ebkJ`4ps_KOK0b8nPX55H8lfcjA|TX0%KqRRIy0Wl4)(Mu5wvy zdEMiqjN%uwpP$my@c!naZyz7RRU`USl7qG(tT{ut$`ne8y7~%ru5%vCU#0h?JUn)wrb7Hi^VMeI2ly4{ zWL$IeY2fLh8RIr-zD5?t^ssv{9rW%1unJN%3Z{Fh{2C5P?CEQRy3>QbL?IYCftK6Q z1|UxhAOvLai;5ariu)X6n5cG~r7zaDwXa|GWmu*eB~%x`6jNqwZOn9N8)gKTYA`=e z4}q~{l?YA_=rV-?@SY1OmbEV(&!=S-Myi1p^#X%c_sy7j_%g9Ep zzVnODAROI4S_^uuD5(Xvg5vwW))6QZVCKv=HWPB_mj$V_=ExSvtBKg4ds1m<=-ya_PCxNri)Pv&`whU}y1#8+^OU;3^*IuVK;smM(oElnebu38?l+ zJ0n-uO#l;i)jD}F!7*En#j@q|1a|LmE%4OHTb$N!{al8&I+@=}?|^lnd* zs|8Yjwc;hfxDBL4X9De(-H+GnY2cgqwKmAw6v$| z)3Uh?Y(IejLaBv>tr)T(EJ)l?X|$uODu_Z**U4+3*<^SNIO25!mN}6p-}&+6hIgbO z9$at{j)&z96O3`Tf!+|^LY*Qv7+||j)N3WvgyR7Lhxj`ongyWl?wOHaR}J5~<+mQ@ z;#AxA2dn%1{;9$eZw$SfkoPTfz%>A+dx%z4@Y@eDU%Pg*$PG#l$iSXEYIF_bbQ~PL zi!Zwgsi>Bxr!}lKz&LbuN#b?CcAy*xT>kiQH&=(!yZ0FCfof?IIm0icW(uHK3KFK{ zlX#4a7f*kuooZ_aV!`9V+%(Pfg;}G_6zF_PW8R-{X=$0oM?*(vF=m1q8vV5CN65P@ z@e6yDZXDFKsKk?ZsTp0`YklgWz6O*!;z!J~!3HgF5l&|2oLiO4APdG0mI}x+fa;q- z_M=%a=d0AaBvuVF2Yp^|m)}9tz~uXW$fjm8?FZvz_TV zo#%~HaClx`W3;rN?rCeAX~UPi<`=Y{iO=G(Hle~yE##OS+Z{is(zg$_|GXisEIC{m zmeo5$Jge4dZ$-QxazUL3gZ{<2a5#R`o(RhmrlnYQhXBli=#}F509B>c%z3K62wIn1 zc`+($JKl*`O$c2;75SpFb8s**=`J;NavihC1o&>hgH4Irzg|U$LU(n>PT^9gZ zLS_+0jTVgcPf5MG4&khXoNU**t(XU`ZEe4X^0OLfq%U_aGV<`mD6+kygY`ZT_I`K+ zwcau>y-B)zdIql(Hi>zy2RZwWK`&2U&BD*0J1{)^H2yjxqlO;|yG5d$Xd?~%Q_t2! z<=1e8O}Qq^pj}e$8^|cF7d!c+Y#O1d(()D*wk+#{2UDeL+u>ZiaA%`BEj$`ATT;{k z4;psCF3KtDoV(DI^0_!V`6Eo^tKFxFZMCjE6R?Kv3GRa6Y(bO*2r7CK`=;0T5H}d0 zOKqiqR%-bZDQGSu7QBjiemY8A)AV-sjML|8H$U^3Q>Ap?BhH&-^Pl}s_25vj_HRS) z;0hjD^_KqnPyFGZ!ItSCt5Azw$9BGQX3O-VeO^8*@1UxW)O`KshV#&$$Y1tXK4iV%4BsSSdxvo!7!=F8SJ<$E` z;RUP*7>f}2F+CGIrS!kV@zOT~U$+SOwYEk}L&M2eQ85GqyXvfOFnjFO=qCM7;3R@k zyRjNHSj>_u1O(E*;M$zdP)|@AwBPc?7s^4u+0`V#!nM$+fStsQn*CH`9?K3^@-#DyBFZ}hb?Y14)o&c-U}&&{{1RL z0<>vp3LtjSx)601(tl|1CMvVeH4a>IMdz~oI@EF}6QS4d;w1fnPv*m*!^P{8K4PFC zcoS9qwal%Z|5|2iLCCLDtqEOL^vh!qWueU07qWc{(i470+z;`AibaNbaJ)pz`^e(2 zsw+Df&(?(*K6iBCi~;TACfQ`;<3IGhWCpbaPTir*TR5R>KGC@#p&&I|kBwBx`E4)9 z`?z^O0p6eueODpz#PX>1O}XBzaR3c(S@qMXOQRjWC>LqNl?kf8G9Yzf=0Mj48Lt)Q z;|%O_51Be$XkW=2S)7|2&Q>5QAAkla&^hOd)$8n+A&{txn!iKLsl?@jaEcs&o)=~( zdSPLGZ^qdcvhm+}Rbykup=tdaLJNlfgaQW^C?X#ieKHQ|K;e{NI%6p67d=^BMdN*B z+#>M7d})eDBdBnp7H~@b!|I6K5j-j~vfIp!fu~KI*Y{*{W?agr*h6ASi~dMyJ=04? z7`-KZA36PSsf44|MWGnPWXbvyj=G_b)AW8(EOXE)0`&`G2Zjb_=uw;}rabTQe_6() zUO8qR-@bQQ$;ni$d?j5qip}vFHW#Rmp1huS~UISSwn1v$Bw{62~kiCg$qZtCl$^&|jV*$icBPl&@u(10t}F z9qB7Ax9A5@&1BWilPZ^y$%ROn_4P7$@F4j^JaBK&6N4W{dxk^m+}M8d)&=l@OnyP& z1|xe6paK=|W7KIbO)ju{n{2LDbjpX+sYxF7$Kdlw{F}FKbzKUl3Gi*5JU#IYP1}d= ztwQbm3J@hY1+%!H6CUw$p0lvZGDq|zg1)w zLHdZ(E|I3WUbJB+*D;yyu($`Xj8xuXuNW#2*?_qxOP;l!Q1?`0BJPMJM) zi-gjq5>k`3^yy{UTDxuFRNZNHP-DFlB0xOw>#7e-0K^^r9*7%zpLo{q#HHKa`SU`6 zuZ+6-XXw|QE{l(dh-i6q5#)hD7!HM$&>HEfYO#cL<)|E81_@lQclM$SOW;=w2!yV# zyct!1CA*X8Y=;Z3WNg7dRAepH$a)+b$Qc5X^EVaY|D=)dEP?Yt!%w zr~2|4F0xqvm$eP%91kbXg_KJ8A6!->W!Im&7Xs6zf$dL$Vfz|?wAWLVJm$1g)~=ny;M`4ZpOAMN3c6Ik|@qoB(HK~t2zEDF*AjEh5AWjIem zc6vY0_bi!Qxso$*lzc?TIp@0we)!y9!D=G}7Uaawdy;4-C5~w68G_P042U+6l7V;M*W_#ZFS(-lo zclro{u9L`^LcSgxGYIc?aEKICwYu3G;hn%COau1shE?a}=F*D$Xcuk4;Tab5Vsqm2 zd2iG3BZ4N$&#f_Wtz%NkwMaommphRHiL5FN$pCnrAx^i{G{xDbQf7Akoe?`p$cUI> z<;_N#Oz5yw*lEsr*03-Nsiye+)#FC{b#zp z6`|54Q;G`=?(0d+L*~$b6&3e@q`iPF1I4xGqw#oCpWP^`qBW6= zYmd-F_EHGe12)e`)h0`w@0?kG7Wl#m=^78VMyOZ}l2~_cD&#~s29{CaGX?I#_GO(s z^@o<+*r)=qIt2kihQT$ohFv5S0ZoBc0i=x{>4yG}aK}>Ax3Qd)PHkhG<#!a9stpe5qtin|*=T#dd>4l|7sGTjoEJG546(4j4Je zm7k!<0m=#RUKpDIFc5j?Gh!r5odI9Eva%8@=hg8;phC{M3%u^mDa=xLL{~XL>0acT zS**Q)^X!0I9_rxVs~wy2yi}%s`H{Bwj+X|tI_Ly2O43})0Z#FHZNvNdQZ?Td-%%9Jub{*HiAB> zLfOk`Cbaagb;-J%FfA<#Yw&!6yQ~ZWoTN)XLaA0E93+wQ(9i-h?{Md`jo-GjXJmwIk&J*x9M4hTxZU@4U)SgQe9q5#p4T=;r5W~wfB?;{Tgw^3Kj_`u zESSqW#6|09{I-UcuQ=LfOM0zF$*|*r#1{MKF3aoKP6%H3NqbywdYkNVG83?<(QUM+ z^yo$BGkxJAh`p2LvVwL$2VcC{ z^(6>%XVX3wY_@pU?V-P1q{`}!ft!CoTB&MuE~tM*s3s6hKzZ8NzeIy#a)Kvjel zceKh(P~B*CCSM?thUk3bGkYs&eG#zgX)YPNvXRod;oA~|Pum8_oY)=1lN(A>FfzgK zPC%9w(G6akQGP_pf!*v8l+<*pYpzHxbf|sym9gb(*R#K!Kox$`y+M2a+gmef#F#q{ zm!?EjRQh^FqT8N5^Yx(*%lxF*+@rr$O)c5HVBix!!)y;1p{7F$0E(nVT!Ve-GTai7 zq{c-@_uqF-Eli*Prb`Th72?gDjMSTjhQ~70BB@SOpBX*1jxG)wey&%^<0RmN;EtQQ zxpjYaYM_mU0+DMl1?RC1GEQ`NNcV*3na_C9@&=p4p5ztx8JDyOq3b%}{gj^1?7QGK zO-)-b(qqroBf$;(c2p%NmXR}wF3xsiOVRl?wFC)Sl^>f$f+fSdz*&@JfQ3CpU(k56 z@}58GK%;tEN5EwH%UW&fm3Daq8#XSTGF!if8K1CA67p+BT{VM$rJ3)~(xvSX<;X5e zXXoX8fC>QKtI#ZU4LbNDW(aNdr&+a1SmRWjeR(|xf)DYq+^vuGnz71TVs;Ob4n(Kr z^Q!5`HQ{;JTAPm#H-uwT*;jE=aL^fK2 zRf5r6z(3Z8Pkdyemimgy2l)rbqNd|pe}$D@omKp^3Nl$9UAcME&(DvUU(x9HEbJ;K zCMHJt!976LCc8)d{N5`(Kbja&z@bv9|(HOZcvts}W zm$l3vo^o{+eMjHUret^YUWDFFmU&^ZtdaELiHXIRfHnZY3=9k)^?L<68j>||7P2%; zfS_&#Sss#=JvQ9#`n_7V>|fJZ85u2$4^7bjIL7eskdug(W)u1~UnsmO-e!{AZFTMg z0_#Xq+Xb8xp$SGq$VjYlVRW6(Mn-ykSK+RS*F7&!Bk|TiZ-|46kx$NNT*)GYzw5wk zt2udoFZ1m1_4WO*v#ZfyWsdt_|1-zUsn-}=nt{FmioDn<2f6+C@<1+$2sZT-4#aP= zIsJh8t_$y`ILoXV|LkevZ(~QEECr2Ci%duWke*BHX z-fr9_B7GS3C@h+QJ}tvu25oaRJo`aHhR`DM4edjeU>FxxK7|PTw0c!5vwlbwW4Jfp zwY!HR-rgW$*vZ(`R5HPSZ`$ewI;${hrkUG^>xS~RN@?imfYsGNhlowSXwRLLx;m|0 z!F!Unf6q1-WYc-#m4+IzLv%Ag^)1#xDaK5C@ZsXFPJ6!%ePU*Jbgcb-&Pt3Me6|wf zM7kPxT<+nz@&rm5qtd1zh-Q($lM-bT_oZCFzSB>%7hJcAh&;8?wO5ZhI8>?A#7_hn zhFn=Q-iQJp(uxSQDjQb~ogNeH2zwWun=6&o<3Lc1uDbPfQD8))`a?PV4us6U;w;(2o z-OXFK3I_dkb*Zuvic_-=(XLFAvmj)!@yctrNx{heH$XA0uz85hEHz}l@Eu=WP$%LD zM3x~3b27!iUiy)V;3MPJoO9nG5BdG8C_c<$T+ZLVJ}&nMtBH`1{N3Q_?3LgUx8?8P zK(pQ0@;DvqTBH8lGgvDKR|)&PM;~+OmV=gM#h+X#GA1v*b?acSh`Y&mkm7;eF>b|? zF0903jANJ)8f7FfO4$Z#no_KOoZT5@3I34q;OY<1y#coZ)?|<< zl!9DrYNc>`=4fIgHC=v1+d*X7sD$_M^YZ3dJ~S06_9(nAO)ua~tCNRmP;loHb*)a~ zaD5mvW}VN2gBPf!SXWPvA&0*@J|a+6pMPEP+e;b3xA|tlg*b@i4Bn7U zmG^ojB_F`~`0vUL8;B%}IPtK&iP{hrsror7PipdD^dnRLDFH#1lk}pyd$;RPQ0OBp z4TT!pR0G0g8bWE0Zv{&l)y?QLSalr(G;i2Hb7IOux=znrSXfwheY#W@9bnvWDMoij z|JZH3$|DmGsk!#-#;{xa?dCizcp;Ydc!%wtPI8mBL8SKb&CUmvl|Z&lZ+qjBj%~A6 zmy(K_N(_Wco_E+0PS1EIl<*JKX=*3V7!I?W+PKGj8oNm0tl>FIuQqpKty*_S$Iddp zh3n4Lju=JwB?Xa#>a&fxWsn6H?$F^!}LVLYaWP{MUF~`pkO%$<)x-F%1 zsM1PpQjK8A&h$b%47|9}XVvgMc}3HdjY!8yLbo@2pZL>8k#225cQ6a5FU+@)bn{z; zKovB4M(pWHK|X>YwKqJ@r#?q@Q_t=BswM&r zumzd0Y@nI+gw3*>`JZ=gBS~(O(6>w{iqGXD1mdmp$R4_T)ObRebAAEAx_NN$y6Mqn z?at?qATK*8NcGlRQ|uy()TZc$!*$wY2xL5hf;$(q0SVaz&RKQ5e`gA-;H-O3HHzZs z@Y0KG=J~U{5xzG(4SLQ+zx4gvZ#ZmnZ3{`g8aD#^q|EgaxSNP1D9prZ&wPqNp`2s$ z0t-PT0f5}Tnp<-;X@R{5{39gEw-vW- zvuU@DgAd@Jho=-fPCy|LBk8VZ5-_a%L=;9R=*m2)9_4aVv2lde+gr%Y%gaS3g5mQDIH$-ENz zc0F!7i>OI1SiPQQXyuZJM8YB+xrKqW?KlK%x$!%a28B5Tfmb`+S zohz!O%NpSe^;A8bMI-s^6l>DG#}Ajtgy;`G7)>>2O)=FW4Jwo_W04 zp|Y|PozB>)P{hB&=O=Y_86w!@Zxyv_Fs?LvKh zeYe(FsT2(jP4v$u@Et7K%CV9Z(j7IOsE^o5uTj<17z{ja4~EXtGW$8C zpZzY%rQJx^*grlqr&^g$-lGOJQ&a9$9r=n8+0hS)W`F^i?JA*V#GH0)s;A-54T?3o zZqNTLtb~Nsx=uz$(KC{(-Oe4!?SOqf$v77sz3z=7 zgTXeSI=T}CPsK1h;sY<9zNAE6i9eAAab|RjKfo<;6EpkYz|Dl=QuLtlqeEu&jEtPJ z02VLaC}{(7s3)zI+R<}>M)?ca8)9PN_K^TTuy=CF`uO?+gQaWvxY{4~unalyF-Sq61}n4-K+bTsM{%Q*D><^2{iVj=?HWHfrsQqmbJ4fW6kOD-|gwMp+|Z))yjW z?5B5j8db|4u3d(U2E8yeOQM53$j}eOwutU&8-9`Q9(`|f;F7m4AvXaOnXjk_iodQC zs+(p|NEx_gcCV|x>x_MEMohLHdb#EpILez=$l1P$VBm_e`F6wH#%2hmAiXfJrk{M` zS?Ltb(+XMMz-I5Uni77XT%=Vj{JQ}W#B}gcu1qX_q(l*x`@hdJg_&b-aqL>RzdS#N z%p5WZK-(zT^MS|6*{coXLYAuzBSbOPMEcS_BihE;FgawMVbz<6b$D-O9oGK44xO;a z0k*Wh?TAD(vN+VH%;9|h@oRyn*JEpY>afL*attbfHWmN| zr}=S#wBtt%6tGTtlti5PZg z&xvH=ad5uc&E^a{Ex6z1k0PK0y4-F38;WuF8O!FC>Bxu%ooRD(Gnj9r_q&==xqbZf zsqmDMKPNx`5}bd-r$Paia-K}RxKTwV=}i~jTwXOd6i!a)s$7>JLQfh(egq*>O38o= zp*sz*h16w~AM+9@29InN2s$Xl)8b8FvC;;prkMnhze%CUa0@IJP)l!(Oa#X40H7s; z4HlJb%(dEC=*y2DS2jsj_<+58_bcL{6neHMV$JyZsV1IfHfVioi{4estF)XEY9{aA zqC=_XOJLKO4=gPcPVg|0X!~?YXDIn`A9xO3qS(XM$f^e{l$;G6&-l74YW1IWUL-Oy zQA|Dd;R6g5&m}6{wM%&MKSLsOE<&P-z@{usbxwPy8(@GKBHxv{? zWM6>m>Kr7f`wMQ)z^6ohp-8i6W!@GwzB$}QnFh5QNK1h6$KU~$rtU*((@MrlKh@ek zMI@mlVK}tIq)WQGP6Ya9_+SMKZ3~c|59I+ca&mCLF;@WsWK!B1Fry}hCUH&0Z?x- zrpj*!s?(X_nMAZvKOk~wS;)G}QeU4YOHo9`uCM42W9kA#M>pe^j_#T;8FgG815Pyv zA<^8hb^QSH5?@^H#5y1I1`G67_1xaAQAp2x$Z8T~MI39BfA0o+-AW-irSvxfz!!Ao z=EfR=N^XEw3554P$p-1^>2Yj3FL~|mg@Q_V0z4?VO>HRth;}r1n@1R;)#C|(w807` zv7aT%cX+>Cyyy;|65&Vm?d@C0+QAmbrgOzw4>t{I(g~~Zp2CY4FM=q^wXFncDIoVJ zwYRZvA^VA6W==#B2ZxNEHb436v3=#{j@>Ybr57elC_p0FadUzlV-oq%(B>~l~w5CpN+ta`4>uQ8**krJB^g>S3;0<%$WkH zoL?2}EjFbOFL}@0*{w5~8I}$9VboCLCP4MRf(u~U*&Cq25Ldn9{M(gkM)qr)}!a8A>f>aqIYJ?ItbR#?;f=>rM+{z za{`(L-LGVp~ zoZ}TE1aOmIGT~uifbG%>%AmLcyxaM!G7yIx%mmRYb?R&EU14N@>duL^PQ$=h*=Q9F z8$2)-TwNx+9YuH($yVfOwdk?~RK5xvHX$0PK3m7ItZ#NBfG0ktJ@zZ4nO6kG3tRQ4 z#-xNK{Ul&IJ7XyGB4X3BJ#zU~-PdKQqPF`XtuUp1Vqu1m2l9=#wHNm1?Cfml+?v$^FmFXmJ*v0Jy0me?aRMN! zl4`l#y)Gz-pqvwYxs1jJ;+%1Q*FcL>)TKg?-slS#k~~{&a1s2lT#jyGuRkzS)Fn|q zgz&1_relgEJ~;*yPpOzC%?ZcJ+dmx^dH&DD{)I`$&v8?Qtoj03k;(imj`hd zE@Wu<7G-1zS2jWu&|^GQocZVZ3^!~Dv2ngetQyxrwBLFXNCt<%5mzIc0HZFE6S6ob6V>|Ps%^E^9JIoAhczV zWVjn|`HlyxiY^Yg2+7;lV{0Z9REddJ-h){0=v5BjT4Okvr*MzldaKj$XB;rtEeS_~ zSBq-;2hIM%1|a_7G2s@03;}q&-_oqp^R=&?%TcD-z+{V1pX|wpp#g*mv!#1EZ2ZF@ zO|sqqKNicBy#3{qKpPRZg#`p4B-s~Gl6vLJm221hfWU03T@Y1Juq3%c;(y7*mi$^D z_sj3kg9I0GugYu86sh0yNDV2eF;oDcJ3GF(b-vjjZg_@UJrj%gEwA!28tCg2dmGwV za_L=QY(RHnY1ti0y$U7!sC!3g7fkn$MZ|m*uk2i*<4!G3lQv;E_hG;BGX?7&?rXo9;WP ze)(HMNVy^*Vf`P26qfL3&ujn=ZP;|qw5(=zI%;+{J{^UKi(O)+U@J+kp zZsU5S&sbDf1m)%WgHnseWqZ!cwn4eTyD<>D*z8$KV9e{$yK#J4(OE0MjIUg+Ku)Rx{A7Ef+ zuJ)e5W}Z|X+-YH!2m7YW5<5nJ9ym>zq2^^c#I!5q1aYDRKqZEUqN@?7Ge3WD*_#ag zboI4kY5s?*y!X`w)l{Dri+=Z2fSHBG_2up4%l!8m219AjgSLzY{$9xOYa{_uxFZ9E zQek)Do(?4XCqFo65I#t#Qxv_&%}Z~9$mEPVWjbAb98M_|Ou!Z}f)U?YtBu0n7 zZne9*Ul;fJ2z=9LAsMzG1Z#ku+2^sE%=GLm)P?qNqmzD#_E{5_Ff?Y|zueHZZ)wY- z-$ZUb^V$5q#cB=8&4-*p;9MpO421Fx=-XD=lyU~#RxSc4I!HS6C zzOEH)({98Z_CLl~^VBe+LoD~^T9)YVE2+QgKdC?6H)Bf`6z5}8468GOf2q}(0fhma!U+o2}QvQ#?+>Zt~g0WUh>M5QL<~_5E}GoAOyk- z4ihX0Qk)ihn2nqOi3{lL=Sg0cRu|<9yqn(x;UKI<*u?5|;mu*DcggZUrZH4RWJ!K9%Ww=vJZV@M`FXnG-1$ZatP_e>-!+*Fw6dCM5B63zSxN^W@Qr3g< zNK;;cUoyw=D6L#SC51Hf!%IkT!KD7Wn+MJpu+EwUq;pWPmIuKC4Lm@^i$E+?eU4m& zVjKx2a&Xw2+&gzADIJVT;*o$;4pi_#(-}w{LzJAH(!#u9ytgpPItdB_qlss)UG4+0 zoBKSl%fD~3uNbPzRz;2Dhu)(ki{+8KJbfw-u7!|S%;STiUo3I)Np4;CrG$qEgc>N| zm>3w=2MAxSsPNU-ZwCE&GyFz@@T0MN*Q;vU)3!kZRT~f#@t+&1$_5C_nd@p^w_r_3 z`U&|pE+E#YhWW{N>BK2X&&`ZVpV_@ps2}^Kj>oeveW0$sbwtGnWsg2(oVMFLRs|c6 z&%VQ$n=z54prNx+WkzB#w4-P1_YZRmi{Y{_l1PcQ$=Jgy)wP{3dhN!rptsS3PVU6^ z?!G=>WJRzBD~cCXy~fe+F%y>Z22H(c8(NBW1j-1POD#-bJTvMcB1XgFRfoO0riPk| z3Lz43B?>zN!|a12=G(V#d#9^F^>_tn7+qd3@cF>+9Rkn<6a;4?^2D|@HD#lpiaZ+I zQ(R1pKNcghFkxO^sF*%pR)tF=MgzrV9GoW6>hkvXM&^qZ2Jerw)YKEoso2mk(Ll*b zEGa4RC&woo?x^x1aBZhYSz~8xIa5Pi+P43;2p{%7)m~X-z6G#E%u1bvvYGSOiWC0 z@nBGhWN_j@00fSzvk!f@4u513xNDPuy1E!PWV>;T8lgth|w_~t9(mn;5Y<+P*7+Wr`1ya zdrZdo5;Tcz%ZnHu&~I+KZombHNg(`e@~R-5djPxM4%EblRf>p{r8f|wk5u5ah;d%n z65?a>*8^+pJorjB066thl@}kni+F6RBpFnz&mx$`vRH?U|-ApTXv4eWr+0nC!@ zbAakSS0L{D3;JDuUxxQmmq-^O8qRF-25JNo7iB9g{SE-M|`oFr^IDioBD9ntH9VOAzhCQ-%332*8hyStpRp&*o{~%jUoN4@}Dc1pT-44ltCc2 zD;psF4!~{+x#%nMPwv30<&jN6m>qC=Ngk@C`u{xL*;za_n!-83zXpzHIIY}Ty?v=k zx+dl;>dr;PwG+bdNe|fwzXRe3xnn%2P0(rGJ3_qGgH-={g}m=Se!LIzZnxH3lw(*o z}jWuDyP*|wx0JjX)JkpB*T8UvRkDw6VMHX^7- z5es1aDbQ1prbx^38#W+Wu-kYJ^C4sxOmVI$I(4I9La;r!AdX@>JvsR_CYuVHP&nL| z^G6gSQs6`mPIp*MK~bOBR;iA=`tv3IWN;9=s9^YgA3K+E0ZM3KpBov7Qv&kfFvN=k znI|&b`b!#Il*xliQOC)}1+&IkB>Jrb!O^X;IR7VWm?8V`3sP)whS4oJ!8?}O+4!*j zyRLxE1mfS-1v}(nDax*smxyr1w$VeGjikw;mlUhgtlRA?c zk;aTfl9_J$jk9Ipra&IPdPg*n4%G&n-n$(?ow@$MZ*nh+N|b8{-bdwR7!oTopmhHo z(DCG^oAUDVkY-kj6Duow0N;bm`k)}5HRL5)1^AHs6>K)iqr@}NEgpC~A{)Q*IM=xT zor@G7BmRxdA!`554hmb-{~RLq|9|A)sq+8eh%r40-E_;7&b5q~K*k29`bE07VgCyV C;A$)Y literal 0 HcmV?d00001 diff --git a/exercises/_11-ex-foundations-randomization.qmd b/exercises/_11-ex-foundations-randomization.qmd index 07638726..2073bd6a 100644 --- a/exercises/_11-ex-foundations-randomization.qmd +++ b/exercises/_11-ex-foundations-randomization.qmd @@ -1,75 +1,84 @@ -1. **Identify the parameter, I** -For each of the following situations, state whether the parameter of interest is a mean or a proportion. It may be helpful to examine whether individual responses are numerical or categorical. +1. **Identify the parameter, I** For each of the following situations, state whether the parameter of interest is a mean or a proportion. + It may be helpful to examine whether individual responses are numerical or categorical. - a. In a survey, one hundred college students are asked how many hours per week they spend on the Internet. + a. In a survey, one hundred college students are asked how many hours per week they spend on the Internet. - b. In a survey, one hundred college students are asked: "What percentage of the time you spend on the Internet is part of your course work?" + b. In a survey, one hundred college students are asked: "What percentage of the time you spend on the Internet is part of your course work?" - c. In a survey, one hundred college students are asked whether they cited information from Wikipedia in their papers. + c. In a survey, one hundred college students are asked whether they cited information from Wikipedia in their papers. - d. In a survey, one hundred college students are asked what percentage of their total weekly spending is on alcoholic beverages. + d. In a survey, one hundred college students are asked what percentage of their total weekly spending is on alcoholic beverages. - e. In a sample of one hundred recent college graduates, it is found that 85 percent expect to get a job within one year of their graduation date. + e. In a sample of one hundred recent college graduates, it is found that 85 percent expect to get a job within one year of their graduation date. -1. **Identify the parameter, II.** -For each of the following situations, state whether the parameter of interest is a mean or a proportion. +2. **Identify the parameter, II.** For each of the following situations, state whether the parameter of interest is a mean or a proportion. - a. A poll shows that 64% of Americans personally worry a great deal about federal spending and the budget deficit. + a. A poll shows that 64% of Americans personally worry a great deal about federal spending and the budget deficit. - b. A survey reports that local TV news has shown a 17% increase in revenue within a two year period while newspaper revenues decreased by 6.4% during this time period. + b. A survey reports that local TV news has shown a 17% increase in revenue within a two year period while newspaper revenues decreased by 6.4% during this time period. - c. In a survey, high school and college students are asked whether they use geolocation services on their smart phones. + c. In a survey, high school and college students are asked whether they use geolocation services on their smart phones. - d. In a survey, smart phone users are asked whether they use a web-based taxi service. + d. In a survey, smart phone users are asked whether they use a web-based taxi service. - e. In a survey, smart phone users are asked how many times they used a web-based taxi service over the last year. + e. In a survey, smart phone users are asked how many times they used a web-based taxi service over the last year. -1. **Hypotheses.** -For each of the research statements below, note whether it represents a null hypothesis claim or an alternative hypothesis claim. +3. **Hypotheses.** For each of the research statements below, note whether it represents a null hypothesis claim or an alternative hypothesis claim. + + a. The number of hours that grade-school children spend doing homework predicts their future success on standardized tests. + + b. King cheetahs on average run the same speed as standard spotted cheetahs. + + c. For a particular student, the probability of correctly answering a 5-option multiple choice test is larger than 0.2 (i.e., better than guessing). + + d. The mean length of African elephant tusks has changed over the last 100 years. + + e. The risk of facial clefts is equal for babies born to mothers who take folic acid supplements compared with those from mothers who do not. + + f. Caffeine intake during pregnancy affects mean birth weight. + + g. The probability of getting in a car accident is the same if using a cell phone than if not using a cell phone. - a. The number of hours that grade-school children spend doing homework predicts their future success on standardized tests. - - b. King cheetahs on average run the same speed as standard spotted cheetahs. - - c. For a particular student, the probability of correctly answering a 5-option multiple choice test is larger than 0.2 (i.e., better than guessing). - - d. The mean length of African elephant tusks has changed over the last 100 years. - - e. The risk of facial clefts is equal for babies born to mothers who take folic acid supplements compared with those from mothers who do not. - - f. Caffeine intake during pregnancy affects mean birth weight. - - g. The probability of getting in a car accident is the same if using a cell phone than if not using a cell phone. - \clearpage -1. **True null hypothesis.** -Unbeknownst to you, let's say that the null hypothesis is actually true in the population. You plan to run a study anyway. +4. **True null hypothesis.** Unbeknownst to you, let's say that the null hypothesis is actually true in the population. + You plan to run a study anyway. + + a. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.05, how likely is it that you will mistakenly reject the null hypothesis? + + b. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.01, how likely is it that you will mistakenly reject the null hypothesis? + + c. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.10, how likely is it that you will mistakenly reject the null hypothesis? - a. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.05, how likely is it that you will mistakenly reject the null hypothesis? - - b. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.01, how likely is it that you will mistakenly reject the null hypothesis? - - c. If the level of discernibility you choose (i.e., the cutoff for your p-value) is 0.10, how likely is it that you will mistakenly reject the null hypothesis? +5. **Identify hypotheses, I.** Write the null and alternative hypotheses in words and then symbols for each of the following situations. -1. **Identify hypotheses, I.** -Write the null and alternative hypotheses in words and then symbols for each of the following situations. + a. New York is known as "the city that never sleeps". + A random sample of 25 New Yorkers were asked how much sleep they get per night. + Do these data provide convincing evidence that New Yorkers on average sleep less than 8 hours a night? - a. New York is known as "the city that never sleeps". A random sample of 25 New Yorkers were asked how much sleep they get per night. Do these data provide convincing evidence that New Yorkers on average sleep less than 8 hours a night? + b. Employers at a firm are worried about the effect of March Madness, a basketball championship held each spring in the US, on employee productivity. + They estimate that on a regular business day employees spend on average 15 minutes of company time checking personal email, making personal phone calls, etc. + They also collect data on how much company time employees spend on such non- business activities during March Madness. + They want to determine if these data provide convincing evidence that employee productivity decreases during March Madness. - b. Employers at a firm are worried about the effect of March Madness, a basketball championship held each spring in the US, on employee productivity. They estimate that on a regular business day employees spend on average 15 minutes of company time checking personal email, making personal phone calls, etc. They also collect data on how much company time employees spend on such non- business activities during March Madness. They want to determine if these data provide convincing evidence that employee productivity decreases during March Madness. +6. **Identify hypotheses, II.** Write the null and alternative hypotheses in words and using symbols for each of the following situations. -1. **Identify hypotheses, II.** -Write the null and alternative hypotheses in words and using symbols for each of the following situations. + a. Since 2008, chain restaurants in California have been required to display calorie counts of each menu item. + Prior to menus displaying calorie counts, the average calorie intake of diners at a restaurant was 1100 calories. + After calorie counts started to be displayed on menus, a nutritionist collected data on the number of calories consumed at this restaurant from a random sample of diners. + Do these data provide convincing evidence of a difference in the average calorie intake of a diners at this restaurant? - a. Since 2008, chain restaurants in California have been required to display calorie counts of each menu item. Prior to menus displaying calorie counts, the average calorie intake of diners at a restaurant was 1100 calories. After calorie counts started to be displayed on menus, a nutritionist collected data on the number of calories consumed at this restaurant from a random sample of diners. Do these data provide convincing evidence of a difference in the average calorie intake of a diners at this restaurant? + b. Based on the performance of those who took the GRE exam between July 1, 2004 and June 30, 2007, the average Verbal Reasoning score was calculated to be 462. + In 2021 the average verbal score was slightly higher. + Do these data provide convincing evidence that the average GRE Verbal Reasoning score has changed since 2021? - b. Based on the performance of those who took the GRE exam between July 1, 2004 and June 30, 2007, the average Verbal Reasoning score was calculated to be 462. In 2021 the average verbal score was slightly higher. Do these data provide convincing evidence that the average GRE Verbal Reasoning score has changed since 2021? - \clearpage -1. **Side effects of Avandia.** -Rosiglitazone is the active ingredient in the controversial type 2 diabetes medicine Avandia and has been linked to an increased risk of serious cardiovascular problems such as stroke, heart failure, and death. A common alternative treatment is Pioglitazone, the active ingredient in a diabetes medicine called Actos. In a nationwide retrospective observational study of 227,571 Medicare beneficiaries aged 65 years or older, it was found that 2,593 of the 67,593 patients using Rosiglitazone and 5,386 of the 159,978 using Pioglitazone had serious cardiovascular problems. These data are summarized in the contingency table below.^[The [`avandia`](http://openintrostat.github.io/openintro/reference/avandia.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.] [@Graham:2010] +7. **Side effects of Avandia.** Rosiglitazone is the active ingredient in the controversial type 2 diabetes medicine Avandia and has been linked to an increased risk of serious cardiovascular problems such as stroke, heart failure, and death. + A common alternative treatment is Pioglitazone, the active ingredient in a diabetes medicine called Actos. + In a nationwide retrospective observational study of 227,571 Medicare beneficiaries aged 65 years or older, it was found that 2,593 of the 67,593 patients using Rosiglitazone and 5,386 of the 159,978 using Pioglitazone had serious cardiovascular problems. + These data are summarized in the contingency table below.[^_11-ex-foundations-randomization-1] + [@Graham:2010] ```{r} library(tools) @@ -78,55 +87,60 @@ Rosiglitazone is the active ingredient in the controversial type 2 diabetes med library(janitor) library(knitr) library(kableExtra) - - avandia %>% - count(treatment, cardiovascular_problems) %>% - mutate(cardiovascular_problems = toTitleCase(as.character(cardiovascular_problems))) %>% - pivot_wider(names_from = cardiovascular_problems, values_from = n) %>% - adorn_totals(where = c("row", "col")) %>% - kbl(linesep = "", booktabs = TRUE, format.args = list(big.mark = ",")) %>% + + avandia |> + count(treatment, cardiovascular_problems) |> + mutate(cardiovascular_problems = toTitleCase(as.character(cardiovascular_problems))) |> + pivot_wider(names_from = cardiovascular_problems, values_from = n) |> + adorn_totals(where = c("row", "col")) |> + kbl(linesep = "", booktabs = TRUE, format.args = list(big.mark = ",")) |> kable_styling(bootstrap_options = c("striped", "condensed"), latex_options = "HOLD_position", - full_width = FALSE) %>% + full_width = FALSE) |> column_spec(1:4, width = "7em") ``` - a. Determine if each of the following statements is true or false. If false, explain why. *Be careful:* The reasoning may be wrong even if the statement's conclusion is correct. In such cases, the statement should be considered false. - - i. Since more patients on Pioglitazone had cardiovascular problems (5,386 vs. 2,593), we can conclude that the rate of cardiovascular problems for those on a Pioglitazone treatment is higher. - - ii. The data suggest that diabetic patients who are taking Rosiglitazone are more likely to have cardiovascular problems since the rate of incidence was (2,593 / 67,593 = 0.038) 3.8\% for patients on this treatment, while it was only (5,386 / 159,978 = 0.034) 3.4\% for patients on Pioglitazone. - - iii. The fact that the rate of incidence is higher for the Rosiglitazone group proves that Rosiglitazone causes serious cardiovascular problems. - + a. Determine if each of the following statements is true or false. + If false, explain why. + *Be careful:* The reasoning may be wrong even if the statement's conclusion is correct. + In such cases, the statement should be considered false. + + i. Since more patients on Pioglitazone had cardiovascular problems (5,386 vs. 2,593), we can conclude that the rate of cardiovascular problems for those on a Pioglitazone treatment is higher. + + ii. The data suggest that diabetic patients who are taking Rosiglitazone are more likely to have cardiovascular problems since the rate of incidence was (2,593 / 67,593 = 0.038) 3.8% for patients on this treatment, while it was only (5,386 / 159,978 = 0.034) 3.4% for patients on Pioglitazone. + + iii. The fact that the rate of incidence is higher for the Rosiglitazone group proves that Rosiglitazone causes serious cardiovascular problems. + iv. Based on the information provided so far, we cannot tell if the difference between the rates of incidences is due to a relationship between the two variables or due to chance. - + b. What proportion of all patients had cardiovascular problems? c. If the type of treatment and having cardiovascular problems were independent, about how many patients in the Rosiglitazone group would we expect to have had cardiovascular problems? - - ::: {.content-hidden unless-format="pdf"} - *See next page for part d.* - ::: - + + ::: {.content-hidden unless-format="pdf"} *See next page for part d.* ::: + \clearpage - d. We can investigate the relationship between outcome and treatment in this study using a randomization technique. While in reality we would carry out the simulations required for randomization using statistical software, suppose we actually simulate using index cards. In order to simulate from the independence model, which states that the outcomes were independent of the treatment, we write whether each patient had a cardiovascular problem on cards, shuffled all the cards together, then deal them into two groups of size 67,593 and 159,978. We repeat this simulation 100 times and each time record the difference between the proportions of cards that say "Yes" in the Rosiglitazone and Pioglitazone groups. Use the histogram of these differences in proportions to answer the following questions. - - i. What are the claims being tested? - - ii. Compared to the number calculated in part (b), which would provide more support for the alternative hypothesis, *higher* or *lower* proportion of patients with cardiovascular problems in the Rosiglitazone group? - + d. We can investigate the relationship between outcome and treatment in this study using a randomization technique. + While in reality we would carry out the simulations required for randomization using statistical software, suppose we actually simulate using index cards. + In order to simulate from the independence model, which states that the outcomes were independent of the treatment, we write whether each patient had a cardiovascular problem on cards, shuffled all the cards together, then deal them into two groups of size 67,593 and 159,978. + We repeat this simulation 100 times and each time record the difference between the proportions of cards that say "Yes" in the Rosiglitazone and Pioglitazone groups. + Use the histogram of these differences in proportions to answer the following questions. + + i. What are the claims being tested? + + ii. Compared to the number calculated in part (b), which would provide more support for the alternative hypothesis, *higher* or *lower* proportion of patients with cardiovascular problems in the Rosiglitazone group? + iii. What do the simulation results suggest about the relationship between taking Rosiglitazone and having cardiovascular problems in diabetic patients? - + ```{r} library(infer) set.seed(25) - avandia %>% - specify(response = cardiovascular_problems, explanatory = treatment, success = "yes") %>% - hypothesize(null = "independence") %>% - generate(reps = 100, type = "permute") %>% - calculate(stat = "diff in props", order = c("Rosiglitazone", "Pioglitazone")) %>% + avandia |> + specify(response = cardiovascular_problems, explanatory = treatment, success = "yes") |> + hypothesize(null = "independence") |> + generate(reps = 100, type = "permute") |> + calculate(stat = "diff in props", order = c("Rosiglitazone", "Pioglitazone")) |> ggplot(aes(x = stat)) + geom_histogram(binwidth = 0.001/4, fill = IMSCOL["green", "full"]) + labs( @@ -136,63 +150,76 @@ Rosiglitazone is the active ingredient in the controversial type 2 diabetes med ) + scale_y_continuous(breaks = seq(0, 16, 2)) ``` - + \clearpage -1. **Heart transplants.** -The Stanford University Heart Transplant Study was conducted to determine whether an experimental heart transplant program increased lifespan. Each patient entering the program was designated an official heart transplant candidate, meaning that they were gravely ill and would most likely benefit from a new heart. Some patients got a transplant and some did not. The variable `transplant` indicates which group the patients were in; patients in the treatment group got a transplant and those in the control group did not. Of the 34 patients in the control group, 30 died. Of the 69 people in the treatment group, 45 died. Another variable called `survived` was used to indicate whether the patient was alive at the end of the study.^[The [`heart_transplant`](http://openintrostat.github.io/openintro/reference/heart_transplant.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.] [@Turnbull+Brown+Hu:1974] +8. **Heart transplants.** The Stanford University Heart Transplant Study was conducted to determine whether an experimental heart transplant program increased lifespan. + Each patient entering the program was designated an official heart transplant candidate, meaning that they were gravely ill and would most likely benefit from a new heart. + Some patients got a transplant and some did not. + The variable `transplant` indicates which group the patients were in; patients in the treatment group got a transplant and those in the control group did not. + Of the 34 patients in the control group, 30 died. + Of the 69 people in the treatment group, 45 died. + Another variable called `survived` was used to indicate whether the patient was alive at the end of the study.[^_11-ex-foundations-randomization-2] + [@Turnbull+Brown+Hu:1974] ```{r} #| fig-asp: 0.5 library(tidyverse) library(openintro) library(patchwork) - - heart_transplant <- heart_transplant %>% + + heart_transplant <- heart_transplant |> mutate(survived_better_wording = if_else(survived == "dead", "deceased", as.character(survived))) - + p_bar <- ggplot(heart_transplant, aes(x = transplant, fill = survived_better_wording)) + geom_bar(position = "fill") + scale_fill_openintro("two") + labs(x = NULL, y = NULL, fill = "Outcome") - + p_box <- ggplot(heart_transplant, aes(x = transplant, y = survtime)) + geom_boxplot() + labs(x = NULL, y = "Survival time (days)") - + p_bar + p_box ``` - a. Does the stacked bar plot indicate that survival is independent of whether the patient got a transplant? Explain your reasoning. + a. Does the stacked bar plot indicate that survival is independent of whether the patient got a transplant? + Explain your reasoning. b. What do the box plots above suggest about the efficacy (effectiveness) of the heart transplant treatment. c. What proportion of patients in the treatment group and what proportion of patients in the control group died? - + ::: {.content-hidden unless-format="pdf"} *See next page for part d.* ::: - + \clearpage d. One approach for investigating whether the treatment is effective is to use a randomization technique. - - i. What are the claims being tested? - - ii. The paragraph below describes the set up for such approach, if we were to do it without using statistical software. Fill in the blanks with a number or phrase, whichever is appropriate. - - > We write *alive* on $\rule{2cm}{0.5pt}$ cards representing patients who were alive at the end of the study, and *deceased* on $\rule{2cm}{0.5pt}$ cards representing patients who were not. Then, we shuffle these cards and split them into two groups: one group of size $\rule{2cm}{0.5pt}$ representing treatment, and another group of size $\rule{2cm}{0.5pt}$ representing control. We calculate the difference between the proportion of \textit{deceased} cards in the treatment and control groups (treatment - control) and record this value. We repeat this 100 times to build a distribution centered at $\rule{2cm}{0.5pt}$. Lastly, we calculate the fraction of simulations where the simulated differences in proportions are $\rule{2cm}{0.5pt}$. If this fraction is low, we conclude that it is unlikely to have observed such an outcome by chance and that the null hypothesis should be rejected in favor of the alternative. - - iii. What do the simulation results shown below suggest about the effectiveness of the transplant program? - + + i. What are the claims being tested? + + ii. The paragraph below describes the set up for such approach, if we were to do it without using statistical software. + Fill in the blanks with a number or phrase, whichever is appropriate. + + > We write *alive* on $\rule{2cm}{0.5pt}$ cards representing patients who were alive at the end of the study, and *deceased* on $\rule{2cm}{0.5pt}$ cards representing patients who were not. + > Then, we shuffle these cards and split them into two groups: one group of size $\rule{2cm}{0.5pt}$ representing treatment, and another group of size $\rule{2cm}{0.5pt}$ representing control. + > We calculate the difference between the proportion of \textit{deceased} cards in the treatment and control groups (treatment - control) and record this value. + > We repeat this 100 times to build a distribution centered at $\rule{2cm}{0.5pt}$. + > Lastly, we calculate the fraction of simulations where the simulated differences in proportions are $\rule{2cm}{0.5pt}$. + > If this fraction is low, we conclude that it is unlikely to have observed such an outcome by chance and that the null hypothesis should be rejected in favor of the alternative. + + iii. What do the simulation results shown below suggest about the effectiveness of the transplant program? + ```{r} library(infer) set.seed(40) - heart_transplant %>% - specify(response = survived_better_wording, explanatory = transplant, success = "deceased") %>% - hypothesize(null = "independence") %>% - generate(reps = 100, type = "permute") %>% - calculate(stat = "diff in props", order = c("treatment", "control")) %>% + heart_transplant |> + specify(response = survived_better_wording, explanatory = transplant, success = "deceased") |> + hypothesize(null = "independence") |> + generate(reps = 100, type = "permute") |> + calculate(stat = "diff in props", order = c("treatment", "control")) |> ggplot(aes(x = stat)) + geom_histogram(binwidth = 0.05, fill = IMSCOL["green", "full"]) + labs( @@ -202,3 +229,7 @@ The Stanford University Heart Transplant Study was conducted to determine whethe ) + scale_y_continuous(breaks = seq(0, 24, 4), minor_breaks = seq(0, 24, 2)) ``` + +[^_11-ex-foundations-randomization-1]: The [`avandia`](http://openintrostat.github.io/openintro/reference/avandia.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package. + +[^_11-ex-foundations-randomization-2]: The [`heart_transplant`](http://openintrostat.github.io/openintro/reference/heart_transplant.html) data used in this exercise can be found in the [**openintro**](http://openintrostat.github.io/openintro) R package.