JCPP2018_alluvial_1.R

# load packages
  library(tidyverse)
  library(RCurl)
  library(magrittr)
  
# get the data
  csv <- getURL("https://raw.githubusercontent.com/ericpgreen/JCPP2018/master/data%20and%20replication%20files/input/dat.csv")
  dat <- read.csv(text = csv)
  
# data wrangling
  datL <-
  dat %>%
  # select the key variables for analysis
    select(ID, w1group, 
           w1_54a, w1_54b, w1_54d, w1_54e, w1_54f,
           w2_54a, w2_54b, w2_54d, w2_54e, w2_54f,
           w3_54a, w3_54b, w3_54d, w3_54e, w3_54f,
           w4_54a, w4_54b, w4_54d, w4_54e, w4_54f) %>%
  # replace any NaN with NA
    mutate_at(vars(-ID, -w1group), funs(ifelse(is.nan(.), NA, .))) %>%
  # rescale data range (1-4) to (0-3) by subtracting 1
    mutate_at(vars(-ID, -w1group), funs(. - 1)) %>%
  # reverse code variable _54a
    mutate_at(vars(w1_54a, w2_54a, w3_54a, w4_54a), 
              funs(3 - .)) %>%
  # construct depression severity
    rowwise() %>%
    mutate(depress.1 = mean(c(w1_54a, w1_54b, w1_54d, w1_54e, w1_54f), 
                            na.rm=TRUE),
           depress.2 = mean(c(w2_54a, w2_54b, w2_54d, w2_54e, w2_54f), 
                            na.rm=TRUE),
           depress.3 = mean(c(w3_54a, w3_54b, w3_54d, w3_54e, w3_54f), 
                            na.rm=TRUE),
           depress.4 = mean(c(w4_54a, w4_54b, w4_54d, w4_54e, w4_54f), 
                            na.rm=TRUE)
    ) %>%
  # convert from wide to long
    select(ID, w1group, depress.1, depress.2, depress.3, depress.4) %>%
    gather(key = time, value = depress, depress.1:depress.4) %>%
    mutate(time = sub("depress.", "", time)) %>%
  # construct indicator of depression
    mutate(dep16 = ifelse(depress >= 0.8, 1, 0)) %>%
  # construct indicator of depression at baseline for every obs using dep16
    group_by(ID) %>%
    mutate(dep16Base = dep16[time == 1L]) %>%
    ungroup() %>%
  # categorize participants relative to baseline (time 1) 
    mutate(depStatus = ifelse(dep16Base==1 & dep16==1, "still depressed",
                       ifelse(dep16Base==1 & dep16==0, "remission",
                       ifelse(dep16Base==0 & dep16==1, "became depressed",
                       ifelse(dep16Base==0 & dep16==0, "never depressed",
                       "missing"))))
    ) %>%
  # labels
    mutate(w1group = factor(w1group, 
                            levels=c(0, 1), 
                            labels=c("control", "intervention"))) %>%
  # highlight two participants
    mutate(highlight = ifelse(ID==2, 1,
                       ifelse(ID==3, 2, 
                              3)))