R工作室分层抽样

Question

我必须计算按分类变量分层的连续变量的平均值。
我想通过结果计算年龄的平均值

我把结果变成了分类变量

#make outcome variable continuous into categorical
rhc2$Outcome<-cut(rhc2$t3d30, c(0,29,30))

summary(rhc2$Outcome)

我有 4631 个关于年龄和结果的观察值

View(rhc2$Outcome)   
summary(rhc2$Outcome)   
 (0,29] (29,30]     
   1333    3298 

age
70.25098
78.17896
75.33197
86.07794
54.96799
43.63898
18.04199
48.42398
34.44199
68.34796

Answer 1

因为你没有发布任何示例数据，这是你的第一篇文章，所以我冒昧地创建了虚假数据来解决你的问题。

library(tidyverse)

set.seed(41)
# since you did not provide data I made up Age
Age <- sample(seq(from = 0, to = 100, by = 1),
                    size =  4631,replace = TRUE)

# and I made up the Outcome variable
Outcome <- sample(seq(from = 0, to = 1, by = 1),
                   size = 4631,
                   replace = TRUE,
                   prob = c(0.3, 0.7))

# Create the data frame
df <- data.frame(Age,Outcome)

然后你可以使用 dplyr 包的组 function 然后是总结 function

# First group the data frame by the Outcome variable
# Then calculate the mean for every outcome variable

df %>% group_by(Outcome) %>% summarize(Mean = mean(Age))

结果：

# A tibble: 2 x 2
  Outcome  Mean
    <dbl> <dbl>
1       0  48.9
2       1  49.6