changes in circumcision.Rmd

---
title: "Changes in Circumcision"
author: "Joshua Schwab"
date: "8/31/2018"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE, rows.print=50)
library(data.table)
```

* population for ALL outputs: men, resident_0

```{r}
date()
load("outputs-withIntOnly.RData")
outputs[, region_name := factor(region_name, levels = levels(region_name)[c(2, 3, 1)])]
outputs <- outputs[resident_0 & sex_0 & !is.na(circumcision_0) & age_0 >= 15]
```

* outcome: age_0 >= 15, traditional/medical circumcision at baseline
* population: nonmissing circumcision at baseline
```{r}
outputs[age_0 %in% 12:14, age_cat := "age12to14"]
outputs[age_0 %in% 15:24, age_cat := "age15to24"]
outputs[age_0 %in% 25:34, age_cat := "age25to34"]
outputs[age_0 %in% 35:44, age_cat := "age35to44"]
outputs[age_0 %in% 45:54, age_cat := "age45to54"]
outputs[age_0 %in% 55:120, age_cat := "age55plus"]

outputs[, .(all_denom=.N), keyby="region_name"]
outputs[, .(N_trad = sum(circumcision_0 %in% 1), circ_0_trad = mean(circumcision_0 %in% 1),
          N_med = sum(circumcision_0 %in% 2), circ_0_med = mean(circumcision_0 %in% 2)
          ), 
        keyby=c("region_name")]
outputs[, .(N_trad = sum(circumcision_0 %in% 1), circ_0_trad = mean(circumcision_0 %in% 1),
          N_med = sum(circumcision_0 %in% 2), circ_0_med = mean(circumcision_0 %in% 2)
          ), 
        keyby=c("region_name", "age_cat")]
```