Merge pull request #52 from rapidsurveys:dev

refactror boot_bw_estimate; fix #51

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: bbw
 Type: Package
 Title: Blocked Weighted Bootstrap
-Version: 0.2.5.9000
+Version: 0.2.6.9000
 Authors@R: c(
     person("Mark", "Myatt", 
            email = "mark@brixtonhealth.com", role = c("aut", "cph")),

R/boot_bw_estimate.R

@@ -28,24 +28,33 @@ boot_bw_estimate <- function(boot_df) {
   )
 
   ## Structure list names ----
-  if (nrow(est[[1]]) == 1) {
-    names(est) <- paste(
-      names(est),
-      lapply(X = est, FUN = row.names) |> unlist(), 
-      sep = "."
+  if (!is.data.frame(boot_df)) {
+    if (nrow(est[[1]]) == 1) {
+      names(est) <- paste(
+        names(est),
+        lapply(X = est, FUN = row.names) |> unlist(), 
+        sep = "."
+      )
+    }
+
+    ## Flatten list ----
+    est <- est |>
+      do.call(rbind, args = _)
+
+    ## Re-structure results ----
+    est <- data.frame(
+      strata = gsub("\\.[^\\.]{1,}", "", row.names(est)),
+      indicator = gsub("[^\\.]{1,}\\.", "", row.names(est)),
+      est
     )
-  }
-
-  ## Flatten list ----
-  est <- est |>
-    do.call(rbind, args = _)
+  } else {
+    ## Flatten list ----
+    est <- est |>
+      do.call(rbind, args = _)
 
-  ## Re-structure results ----
-  est <- data.frame(
-    strata = gsub("\\.[^\\.]{1,}", "", row.names(est)),
-    indicator = gsub("[^\\.]{1,}\\.", "", row.names(est)),
-    est
-  )
+    ## Re-structure results ----
+    est <- data.frame(indicator = row.names(est), est)
+  }
 
   ## Tidy up row names ----
   row.names(est) <- NULL
@@ -96,4 +105,4 @@ boot_percentile <- function(boot_df) {
   }
 
   est
-}
+}

README.md

@@ -26,10 +26,13 @@ stable](https://img.shields.io/badge/lifecycle-stable-brightgreen.svg)](https://
 The **blocked weighted bootstrap** is an estimation technique for use
 with data from two-stage cluster sampled surveys in which either prior
 weighting (e.g. *population-proportional sampling* or *PPS* as used in
-**Standardized Monitoring and Assessment of Relief and Transitions** or
-**SMART** surveys) or *posterior weighting* (e.g. as used in **Rapid
-Assessment Method** or **RAM** and **Simple Spatial Sampling Method** or
-**S3M** surveys) is implemented.
+[Standardized Monitoring and Assessment of Relief and Transitions
+(SMART)](https://smartmethodology.org/) surveys) or *posterior
+weighting* (e.g. as used in [Rapid Assessment Method
+(RAM)](https://rapidsurveys.io/ramOPmanual/) and [Simple Spatial
+Sampling Method
+(S3M)](https://researchonline.lshtm.ac.uk/id/eprint/2572543) surveys) is
+implemented.
 
 ## Installation
 
@@ -73,11 +76,11 @@ for the sample design. A blocked weighted bootstrap can be used:
     sampling (PPS) to weight the sample prior to data collection
     (e.g. as is done with SMART surveys). This means that a posterior
     weighting procedure is required. `{bbw}` uses a *“roulette wheel”*
-    algorithm (see [illustration below](#FIG1)) to weight (i.e. by
+    algorithm (see [illustration below](#fig1)) to weight (i.e. by
     population) the selection probability of PSUs in bootstrap
     replicates.
 
-<a name="FIG1"></a>
+<a name="fig1"></a>
 
 <p align="center">
 
@@ -87,8 +90,10 @@ for the sample design. A blocked weighted bootstrap can be used:
 
 In the case of prior weighting by PPS all clusters are given the same
 weight. With posterior weighting (as in RAM or S3M) the weight is the
-population of each PSU. This procedure is very similar to the *fitness
-proportional selection* technique used in *evolutionary computing*.
+population of each PSU. This procedure is very similar to the [*fitness
+proportional
+selection*](https://en.wikipedia.org/wiki/Fitness_proportionate_selection)
+technique used in *evolutionary computing*.
 
 A total of `m` PSUs are sampled with replacement for each bootstrap
 replicate (where `m` is the number of PSUs in the survey sample).

tests/testthat/test-post_strat_estimation.R

@@ -3,7 +3,7 @@
 test_that("estimate_total works as expected", {
   boot_df <- boot_bw(
     indicatorsHH, villageData, statistic = bootClassic, params = "anc1",
-    replicates = 9
+    replicates = 9, strata = "region"
   )
 
   est_df <- boot_bw_estimate(boot_df)
@@ -15,15 +15,6 @@ test_that("estimate_total works as expected", {
 
   expect_s3_class(estimate_total(est_df, pop_df), "data.frame")
 
-  boot_df <- boot_bw(
-    indicatorsHH, villageData, statistic = bootClassic, params = "anc1",
-    replicates = 9, strata = "region"
-  )
-
-  est_df <- boot_bw_estimate(boot_df)
-
-  expect_s3_class(estimate_total(est_df, pop_df), "data.frame")
-
   boot_df <- boot_bw(
     indicatorsHH, villageData, statistic = bootClassic, 
     params = c("anc1", "anc2"), replicates = 9, strata = "region"

vignettes/bbw-estimation.Rmd

@@ -1,5 +1,7 @@
 ---
 title: "Blocked weighted bootstrap estimation"
+author: "Ernest Guevarra"
+date: "8 January 2025"
 output: rmarkdown::html_vignette
 vignette: >
   %\VignetteIndexEntry{Blocked weighted bootstrap estimation}
@@ -18,4 +20,4 @@ knitr::opts_chunk$set(
 library(bbw)
 ```
 
-The `{bbw}` package was developed primarily as a tool for analysing complex survey data. 
+The `{bbw}` package was developed primarily as a tool for analysing complex sample survey data.