podcast_gender.R

# data from http://www.edisonresearch.com/wp-content/uploads/2017/04/Podcast-Consumer-2017.pdf
library(tidyverse)

set.seed(20210311)
podcast_women <- tibble(
  gender = rep("female", 2000*.44),
  y2013 = sample(c("yes", "no"), size = 2000*.44, replace = TRUE, prob = c(0.09, 1 - 0.09)),
  y2014 = sample(c("yes", "no"), size = 2000*.44, replace = TRUE, prob = c(0.13, 1 - 0.13)),
  y2015 = sample(c("yes", "no"), size = 2000*.44, replace = TRUE, prob = c(0.16, 1 - 0.16)),
  y2016 = sample(c("yes", "no"), size = 2000*.44, replace = TRUE, prob = c(0.18, 1 - 0.18)),
  y2017 = sample(c("yes", "no"), size = 2000*.44, replace = TRUE, prob = c(0.21, 1 - 0.21))
)
set.seed(20210311)
podcast_men <- tibble(
  gender = rep("male", 2000*.56),
  y2013 = sample(c("yes", "no"), size = 2000*.56, replace = TRUE, prob = c(0.15, 1 - 0.15)),
  y2014 = sample(c("yes", "no"), size = 2000*.56, replace = TRUE, prob = c(0.17, 1 - 0.17)),
  y2015 = sample(c("yes", "no"), size = 2000*.56, replace = TRUE, prob = c(0.17, 1 - 0.17)),
  y2016 = sample(c("yes", "no"), size = 2000*.56, replace = TRUE, prob = c(0.24, 1 - 0.24)),
  y2017 = sample(c("yes", "no"), size = 2000*.56, replace = TRUE, prob = c(0.27, 1 - 0.27))
)
podcast_gender <- bind_rows(podcast_women, podcast_men)

podcast_gender %>% 
  tableone::CreateTableOne(
    vars = as.character(names(podcast_gender))[-1],
    strata = "gender",
    factorVars = as.character(names(podcast_gender))
    )