Replacing loop to do T-test in R

Question

I have a dataframe with the following structure:

set.seed(1)
dat<- data.frame(gender=sample(rep(c("Man","Woman"),3000)),
                 age=sample(rep(c("Young","Old"),3000)),
                 question=rep(c("Q1", "Q2", "Q3"),2000),
                 response=rep(c("Res1", "Res2"),3000),
                 value=sample(rep(c(0,1),3000)))
head(dat)
#  gender   age question response value
#1    Man   Old       Q1     Res1     0
#2    Man Young       Q2     Res2     1
#3    Man   Old       Q3     Res1     0
#4  Woman   Old       Q1     Res2     1
#5    Man   Old       Q2     Res1     1
#6    Man   Old       Q3     Res2     1

I have created a loop to do a t-test for every response per question, and join the output in a dataframe.

library(tidyverse)
library(rstatix)
data.list1<- list()
for (i in 1:length(table(dat$question))) {
  dat1<- dat %>% 
    filter(question==names(table(dat$question))[[i]])
  data.list2 <- list()
  for(f in 1:(ncol(dat1)-3)){
    dat2<- dat1 %>% 
      t_test(reformulate(colnames(dat1)[f], "value"),
             detailed=T) %>% 
      mutate(question=names(table(dat$question))[[i]],
             response=names(table(dat$response))[[f]])
    data.list2[[f]]<- dat2
  }
  data.list1[[i]] <- bind_rows(data.list2)
}
final.output<- bind_rows(data.list1) %>% 
  select(question, response, group1, estimate1, 
         group2, estimate2,p)
final.output
#  question response group1 estimate1 group2 estimate2     p
#  <chr>    <chr>    <chr>      <dbl> <chr>      <dbl> <dbl>
#1 Q1       Res1     Man        0.492 Woman      0.494 0.932
#2 Q1       Res2     Old        0.484 Young      0.502 0.418
#3 Q2       Res1     Man        0.500 Woman      0.509 0.687
#4 Q2       Res2     Old        0.489 Young      0.518 0.198
#5 Q3       Res1     Man        0.495 Woman      0.510 0.504
#6 Q3       Res2     Old        0.511 Young      0.494 0.452

My problem is that the dataframe I am actually working with is much larger than the one used in this example and contains more variables, so the loop takes a very long time to run (over 10 minutes). Is there any way to obtain the same output without using a loop?

Answer 1

We could loop over the named vector of column names with imap, select the 'question', looped column , and 'value', then after grouping by 'question', summarise the t_test output in a list and unnest (from tidyr) the list output

library(purrr)
library(dplyr)
library(rstatix)
library(tidyr)
imap_dfr(c(gender = "gender", age = "age"), ~ {
     nm1 <- .x
     dat %>% 
        select(question, .x, value) %>%
        group_by(question) %>% 
        summarise(out =  list(t_test(reformulate( nm1, "value"),
            detailed = TRUE, data = cur_data())))},
       .id = 'variable') %>%
 unnest(c(out))

-output

# A tibble: 6 x 17
  variable question estimate estimate1 estimate2 .y.   group1 group2    n1    n2 statistic     p    df conf.low conf.high method alternative
  <chr>    <chr>       <dbl>     <dbl>     <dbl> <chr> <chr>  <chr>  <int> <int>     <dbl> <dbl> <dbl>    <dbl>     <dbl> <chr>  <chr>      
1 gender   Q1       -0.00192     0.492     0.494 value Man    Woman   1006   994   -0.0857 0.932 1998.  -0.0458    0.0420 T-test two.sided  
2 gender   Q2       -0.00901     0.500     0.509 value Man    Woman   1001   999   -0.403  0.687 1998.  -0.0529    0.0349 T-test two.sided  
3 gender   Q3       -0.0150      0.495     0.510 value Man    Woman    993  1007   -0.669  0.504 1998.  -0.0588    0.0289 T-test two.sided  
4 age      Q1       -0.0181      0.484     0.502 value Old    Young    992  1008   -0.810  0.418 1998.  -0.0620    0.0258 T-test two.sided  
5 age      Q2       -0.0288      0.489     0.518 value Old    Young    977  1023   -1.29   0.198 1994.  -0.0727    0.0150 T-test two.sided  
6 age      Q3        0.0168      0.511     0.494 value Old    Young   1031   969    0.752  0.452 1990.  -0.0271    0.0607 T-test two.sided