我有这些数据集:
df
作为主要数据框(但让我们将它们想象为非常大的数据集)。
df = data.frame(x = seq(1,20,2),
y = c('a','a','b','c','a','a','b','c','a','a'),
z = c('d','e','e','d','f','e','e','d','e','f') )
stage1 = data.frame(xx = c(2,3,4,5,7,8,9) )
stage2 = data.frame(xx = c(3,5,7,8,9) )
stage3 = data.frame(xx = c(2,3,6,8) )
stage4 = data.frame(xx = c(1,3,6) )
然后创建计数表如下:
library(dplyr)
library(purrr)
map(lst(stage1 , stage2 ,stage3 ,stage4 ),
~ inner_join(df, .x, by = c("x" = "xx")) %>%
count(y, name = 'Count'))
我希望应用卡方检验来研究每两个连续表之间的差异是否显着。
library(dplyr)
library(purrr)
df = data.frame(x = seq(1, 20, 2),
y = c('a', 'a', 'b', 'c', 'a', 'a', 'b', 'c', 'a', 'a'),
z = c('d', 'e', 'e', 'd', 'f', 'e', 'e', 'd', 'e', 'f') )
stage1 = data.frame(xx = c(2, 3, 4, 5, 7, 8, 9) )
stage2 = data.frame(xx = c(3, 5, 7, 8, 9) )
stage3 = data.frame(xx = c(2, 3, 6, 8))
stage4 = data.frame(xx = c(1, 3, 6))
tbls <- map(lst(stage1 , stage2 ,stage3 ,stage4 ),
~ inner_join(df, .x, by = c("x" = "xx")) %>%
count(y, name = 'Count'))
results <- cbind(seq(1, length(tbls), by = 2),
seq(2, length(tbls), by = 2)) |>
apply(1, function(x) {
result <- list(test_result = NA,
table_idx = NA)
result$table_idx <- c(x[ 1 ], x[ 2 ])
test_result <- chisq.test(tbls[[ x[ 1 ] ]]$Count,
tbls[[ x[ 2 ] ]]$Count,
correct = FALSE) |>
try()
if ('try-error' %in% class(test_result)) {
return(result)
}
result$test_result <- test_result
return(result)
})
print(results)
我为您的最终列表输出指定了对象名称 (l)。然后我分成两个子列表并应用函数“map2”。这会将您请求的测试应用于两个列表中的元素对(即原始列表中的两个连续元素):
l <- map(lst(stage1 , stage2 ,stage3 ,stage4 ),
~ inner_join(df, .x, by = c("x" = "xx")) %>%
count(y, name = 'Count'))
将每两个连续元素拆分为两个子列表
is.odd <- rep(c(TRUE, FALSE), length = length(l))
l1<-l[is.odd]
l2<-l[!is.odd]
然后连接元素对并根据 l 重命名新元素:
l12<-map2(l1,l2, ~ left_join(.x,.y, by='y'))
names(l12)<-paste(names(l1),names(l2),sep = ' vs ')
对配对列表的每个元素执行卡方检验(每个元素包含来自“l”的两个连续表:
x.test<-map(l12, ~ chisq.test(.[-1]))
这是输出:
x.测试
$
stage1 vs stage2
Pearson's Chi-squared test
data: X-squared = 0, df = 2, p-value = 1
$
stage3 vs stage4
Chi-squared test for given probabilities
X-squared = 0.33333, df = 1, p-value = 0.5637