R：每个因子水平内的行之间的 t 检验

Question

这是我正在尝试处理的数据框：

m <- matrix(rnorm(108, mean = 5000, sd = 1000), nrow = 36) 
colnames(m) <- paste('V', 1:3, sep = '') 
df <- data.frame(type = factor(rep(c('T1', 'T2', 'T3', 'T4', 'T5', 
            'T6', 'T7', 'T8', 'T9'), each = 4)), 
            treatment = factor(rep(rep(c('C','P', 'N', 'S'), each = 1), 
            9)), 
            as.data.frame(m)) 

我想知道如何在每个“类型”内的行之间执行 t 检验。这是我想要的 T1 类型的 t 检验示例：

t.test(df[1,3:5], df[2, 3:5])
t.test(df[1,3:5], df[3, 3:5])
t.test(df[1,3:5], df[4, 3:5])

t.test(df[1,3:5], df[3, 3:5])

t.test(df[1,3:5], df[4, 3:5])

我试图弄清楚如何遍历所有行并从 t 检验中获取所有 p 值（以及用于识别的类型和处理），而不是手动计算每一行。任何帮助或建议将不胜感激。

Answer 1

类似这样的：

library(dplyr)
t_tests = df %>%
  split(.$type) %>%
  lapply(function(x){
    t(x[3:5]) %>%
      data.frame %>%
      setNames(x$treatment) %>%
      combn(2, simplify = FALSE) %>%
      lapply(function(x){
         data.frame(treatment = paste0(names(x), collapse = ", "), 
                   p_value = t.test(x[,1], x[,2])$p.value)
      }) %>%
      do.call(rbind, .) 
  }) %>% 
  do.call(rbind, .) %>%
  mutate(type = sub("[.].+", "", row.names(.))) 

结果：

> head(t_tests, 10)
   treatment   p_value type
1       C, P 0.6112274   T1
2       C, N 0.6630060   T1
3       C, S 0.5945135   T1
4       P, N 0.9388568   T1
5       P, S 0.8349370   T1
6       N, S 0.9049995   T1
7       C, P 0.3274583   T2
8       C, N 0.9755364   T2
9       C, S 0.7391661   T2
10      P, N 0.3177871   T2

编辑（向数据集添加了一个额外级别的“文件”）：

library(dplyr)
t_tests = df %>%
  split(.$file) %>%
  lapply(function(y){
    split(y, y$type) %>%
    lapply(function(x){
      t(x[4:6]) %>%
        data.frame %>%
        setNames(x$treatment) %>%
        combn(2, simplify = FALSE) %>%
        lapply(function(x){
          data.frame(treatment = paste0(names(x), collapse = ", "), 
                     p_value = t.test(x[,1], x[,2])$p.value)
        }) %>%
        do.call(rbind, .) 
    }) %>% 
      do.call(rbind, .) %>%
      mutate(type = sub("[.].+", "", row.names(.)))
  }) %>% 
  do.call(rbind, .) %>%
  mutate(file = sub("[.].+", "", row.names(.)))

结果：

   treatment   p_value type  file
1       C, P 0.3903450   T1 file1
2       C, N 0.3288727   T1 file1
3       C, S 0.0638599   T1 file1
4       P, N 0.6927599   T1 file1
5       P, S 0.1159615   T1 file1
6       N, S 0.2184015   T1 file1
7       C, P 0.1147805   T2 file1
8       C, N 0.4961888   T2 file1
9       C, S 0.9048607   T2 file1
10      P, N 0.4203666   T2 file1
11      P, S 0.3425908   T2 file1
12      N, S 0.7262478   T2 file1
13      C, P 0.6300293   T3 file1
14      C, N 0.8255837   T3 file1
15      C, S 0.7140522   T3 file1
16      P, N 0.4768694   T3 file1
17      P, S 0.3992130   T3 file1
18      N, S 0.8740219   T3 file1
19      C, P 0.2434270   T4 file1
20      C, N 0.2713622   T4 file1

关于编辑的注意事项：

OP 希望在数据中添加一个额外的顶级 file，可以简单地在末尾添加另一个 split + lapply 和 do.call。

新数据：

m <- matrix(rnorm(324, mean = 5000, sd = 1000), nrow = 108) 
colnames(m) <- paste('V', 1:3, sep = '') 
df <- data.frame(type = factor(rep(c('T1', 'T2', 'T3', 'T4', 'T5', 'T6', 'T7', 'T8', 'T9'), each = 4)), 
                 treatment = factor(rep(rep(c('C','P', 'N', 'S'), each = 1), 9)), 
                 file = factor(rep(c("file1", "file2", "file3"), each = 36)), 
                 as.data.frame(m))