同时对R中整洁的数据执行多个T.测试

我们可以按“因子”分组 summarise 的输出 t.test 在一个 list

library(dplyr)
out <- df %>% 
        group_by(factor) %>% 
        summarise(ttest = list(t.test(value ~ samediff)))

out
# A tibble: 2 x 2
#  factor ttest      
#  <chr>  <list>     
#1 give   <S3: htest>
#2 impact <S3: htest>

输出存储在 列表 可以提取的列 $ 或 [[

identical(out$ttest[[1]], t.test(value ~ samediff, dfgive))
#[1] TRUE

我们可以通过 factor 并应用 t.test 逐一地。最后的输出是一个列表。我们可以通过 lst$give 或 lst$impact .

library(tidyverse)

lst <- df %>%
  split(.$factor) %>%
  map(~t.test(value ~ samediff, .x))

数据

df <- read.table(text = "id  samediff  factor  value
1   S         give    3
1   S         impact  4
2   S         give    2
2   S         impact  5   
3   D         give    1
3   D         impact  4
4   D         give    3
4   D         impact  5 ",
                 header = TRUE, stringsAsFactors = FALSE)

要增加现有答案,可以使用 broom::tidy 整理 t.test ,例如

library(tidyverse)
library(broom)
df %>%
  group_by(factor) %>%
  summarise(ttest = list(t.test(value ~ samediff))) %>%
  mutate(ttest = map(ttest, tidy)) %>%
  unnest() %>%
  select(factor, estimate, estimate1, estimate2, p.value)
# # A tibble: 2 x 5
#   factor estimate estimate1 estimate2 p.value
#   <chr>     <dbl>     <dbl>     <dbl>   <dbl>
# 1 give       -0.5       2         2.5   0.712
# 2 impact      0         4.5       4.5   1  

下面是BASE-R方法:

results <- lapply(split(df, df$factor), function(X) {
  out <- t.test(value ~ samediff, X)
  data.frame(diff = out$statistic,
             mean1 = out$estimate[1],
             mean2 = out$estimate[2],
             pval = out$p.value)
})
do.call(rbind, results)
#              diff mean1 mean2      pval
# give   -0.4472136   2.0   2.5 0.7117228
# impact  0.0000000   4.5   4.5 1.0000000