假设这样的数据结构：
ID testA_wave1 testA_wave2 testA_wave3 testB_wave1 testB_wave2 testB_wave3
1 1 3 2 3 6 5 3
2 2 4 4 4 3 6 6
3 3 10 2 1 4 4 4
4 4 5 3 12 2 7 4
5 5 5 3 9 2 4 2
6 6 10 0 2 6 6 5
7 7 6 8 4 6 8 3
8 8 1 5 4 5 6 0
9 9 3 2 7 8 4 4
10 10 4 9 5 11 8 8
我想要实现的是分别为每个测试计算一个配对的t检验（在这种情况下，这意味着testA和testB，但在现实生活中，我有更多的测试）。我想这样做，以便将给定测试的第一波与同一测试的所有其他后续波进行比较（在testA的情况下，意味着testA_wave1与testA_wave2以及testA_wave1与testA_wave3）。
这样，我能够实现：
df %>%
gather(variable, value, -ID) %>%
mutate(wave_ID = paste0("wave", parse_number(variable)),
variable = ifelse(grepl("testA", variable), "testA",
ifelse(grepl("testB", variable), "testB", NA_character_))) %>%
group_by(wave_ID, variable) %>%
summarise(value = list(value)) %>%
spread(wave_ID, value) %>%
group_by(variable) %>%
mutate(p_value_w1w2 = t.test(unlist(wave1), unlist(wave2), paired = TRUE)$p.value,
p_value_w1w3 = t.test(unlist(wave1), unlist(wave3), paired = TRUE)$p.value) %>%
select(variable, matches("(p_value)"))
variable p_value_w1w2 p_value_w1w3
<chr> <dbl> <dbl>
1 testA 0.664 0.921
2 testB 0.146 0.418
但是，我希望看到不同/更优雅的解决方案，它们给出相似的结果。我主要是在寻找dplyr/ tidyverse解决方案，但是如果有一种完全不同的方法来实现它，那么我并不反对。
样本数据：
set.seed(123)
df <- data.frame(ID = 1:20,
testA_wave1 = round(rnorm(20, 5, 3), 0),
testA_wave2 = round(rnorm(20, 5, 3), 0),
testA_wave3 = round(rnorm(20, 5, 3), 0),
testB_wave1 = round(rnorm(20, 5, 3), 0),
testB_wave2 = round(rnorm(20, 5, 3), 0),
testB_wave3 = round(rnorm(20, 5, 3), 0))
Ron*_*hah 10
从dplyr0.8.0开始，我们可以group_split用来将数据帧拆分为数据帧列表。
我们gather将数据框转换为长格式，然后separate将列的名称（key）转换为不同的列（test和wave）。然后group_split，我们用于将数据框基于test列拆分为列表。对于列表中的每个数据帧，我们将spread其转换为宽格式，然后计算t.test值，然后使用将其重新绑定到一个数据帧中map_dfr。
library(tidyverse)
df %>%
gather(key, value, -ID) %>%
separate(key, c("test", "wave")) %>%
group_split(test) %>% #Previously we had to do split(.$test) here
map_dfr(. %>%
spread(wave, value) %>%
summarise(test = first(test),
p_value_w1w2 = t.test(wave1, wave2, paired = TRUE)$p.value,
p_value_w1w3 = t.test(wave1, wave3, paired = TRUE)$p.value))
# A tibble: 2 x 3
# test p_value_w1w2 p_value_w1w3
# <chr> <dbl> <dbl>
#1 testA 0.664 0.921
#2 testB 0.146 0.418
由于只有2个值需要计算，因此我们手动执行了t检验。如果wave...列数更多，那么这将变得很麻烦。在这种情况下，我们可以
df %>%
gather(key, value, -ID) %>%
separate(key, c("test", "wave")) %>%
group_split(test) %>%
map_dfr(function(data)
data %>%
spread(wave, value) %>%
summarise_at(vars(setdiff(unique(data$wave), "wave1")),
function(x) t.test(.$wave1, x, paired = TRUE)$p.value) %>%
mutate(test = first(data$test)))
# wave2 wave3 test
# <dbl> <dbl> <chr>
#1 0.664 0.921 testA
#2 0.146 0.418 testB
在这里，它将对每个带有“ wave1”列的“ wave ..”列执行t检验。
由于您也愿意接受其他解决方案，因此请尝试使用纯基础R解决方案
sapply(split.default(df[-1], sub("_.*", "", names(df[-1]))), function(x)
c(p_value_w1w2 = t.test(x[[1]], x[[2]],paired = TRUE)$p.value,
p_value_w1w3 = t.test(x[[1]], x[[3]],paired = TRUE)$p.value))
# testA testB
#p_value_w1w2 0.6642769 0.1456059
#p_value_w1w3 0.9209554 0.4184603
我们根据划分列，test*并创建数据框列表，然后t.test为每个数据框应用不同的列组合。
这是一种做到这一点的方法，需要花费purrr很多时间。
library("tidyverse")
set.seed(123)
df <- tibble(
ID = 1:20,
testA_wave1 = round(rnorm(20, 5, 3), 0),
testA_wave2 = round(rnorm(20, 5, 3), 0),
testA_wave3 = round(rnorm(20, 5, 3), 0),
testB_wave1 = round(rnorm(20, 5, 3), 0),
testB_wave2 = round(rnorm(20, 5, 3), 0),
testB_wave3 = round(rnorm(20, 5, 3), 0)
)
pvalues <- df %>%
# From wide tibble to long tibble
gather(test, value, -ID) %>%
separate(test, c("test", "wave")) %>%
# Not stricly necessary; will order the waves alphabetically instead
mutate(wave = parse_number(wave)) %>%
inner_join(., ., by = c("ID", "test")) %>%
# If there are two waves w1 and w2,
# we end up with pairs (w1, w1), (w1, w2), (w2, w1) and (w2, w2),
# so filter out to keep the pairing (w1, w2) only
filter(wave.x == 1, wave.x < wave.y) %>%
nest(ID, value.x, value.y) %>%
mutate(pvalue = data %>%
# Perform the test
map(~t.test(.$value.x, .$value.y, paired = TRUE)) %>%
map(broom::tidy) %>%
# Also not strictly necessary; you might want to keep all
# information about the test: estimate, statistic, etc.
map_dbl(pluck, "p.value"))
pvalues
#> # A tibble: 4 x 5
#> test wave.x wave.y data pvalue
#> <chr> <dbl> <dbl> <list> <dbl>
#> 1 testA 1 2 <tibble [20 x 3]> 0.664
#> 2 testA 1 3 <tibble [20 x 3]> 0.921
#> 3 testB 1 2 <tibble [20 x 3]> 0.146
#> 4 testB 1 3 <tibble [20 x 3]> 0.418
pvalues %>%
# Drop the data in order to pivot the table
select(- data) %>%
unite("waves", wave.x, wave.y, sep = ":") %>%
spread(waves, pvalue)
#> # A tibble: 2 x 3
#> test `1:2` `1:3`
#> <chr> <dbl> <dbl>
#> 1 testA 0.664 0.921
#> 2 testB 0.146 0.418
由reprex软件包（v0.2.1）创建于2019-03-08