我不能保证 prop.table 是否比 binom.test 更好,你应该阅读更多关于这两个的内容。
library(dplyr)
# just for this example, you have your survey here
df <- data.frame(Intervention=sample(x = c(TRUE,FALSE), size = 20, replace = TRUE),
Q1d=sample(x = 0:1, size = 20, replace = TRUE),
Q2d=sample(x = 0:1, size = 20, replace = TRUE),
Q3d=sample(x = 0:1, size = 20, replace = TRUE),
Q4d=sample(x = 0:1, size = 20, replace = TRUE),
Q5d=sample(x = 0:1, size = 20, replace = TRUE),
Q6d=sample(x = 0:1, size = 20, replace = TRUE),
Q7d=sample(x = 0:1, size = 20, replace = TRUE))
# vector with the sum of FALSE and the sum of TRUE
count_Intervention <- c(length(which(!df$Intervention)),length(which(df$Intervention)))
# group by TRUE/FALSE and sum(count) the 1's
df_sum <- df %>%
group_by(Intervention) %>%
summarize(across((colnames(df)[-1]),list(sum)))
# for new info. I added the pvalue, that might be important
new_df <- data.frame(Question=as.character(), LowerConfInt=as.numeric(), UpperConfInt=as.numeric(), Pvalue = as.numeric())
#loop
for (Q_d in colnames(df_sum)[-1]) {
lower <- prop.test(as.vector(t(df_sum[,Q_d])), count_Intervention)$conf.int[1]
upper <- prop.test(as.vector(t(df_sum[,Q_d])), count_Intervention)$conf.int[2]
pvalue <- prop.test(as.vector(t(df_sum[,Q_d])), count_Intervention)$p.value
new_df <- rbind(new_df, data.frame(Q_d, lower, upper, pvalue))
}
new_df
Q_d lower upper pvalue
1 Q1d_1 -0.2067593 0.8661000 0.34844258
2 Q2d_1 -0.9193444 -0.1575787 0.05528499
3 Q3d_1 -0.4558861 0.5218202 1.00000000
4 Q4d_1 -0.4558861 0.5218202 1.00000000
5 Q5d_1 -0.7487377 0.3751114 0.74153726
6 Q6d_1 -0.2067593 0.8661000 0.34844258
7 Q7d_1 -0.4558861 0.5218202 1.00000000