如何计算描述性统计[关闭]

2 回答

• 1

  函数 summarise() 来自包 dplyr 将是一个很好的解决方案：

  library('dplyr')
  df %>% 
    na.omit %>%
    group_by(gender) %>% 
    summarise(Freq = n(), #unshure, maybe n()/NROW(df)
              Mean = mean(height),
              Median = median(height),
              Mode = moda(height),
              Std.Dev = sd(height),
              min = min(height),
              max = max(height))
  

  其中 moda(x) 是来自连续变量的样本的estimatin模式的函数：

  moda <- function(x, na.omit = TRUE){
    if (na.omit) x <- na.omit(x)
    d <- density(x)
    return(d$x[which.max(d$y)])
  }
  

  回复于 2024-05-13T21:06:13+08:00
• 0

  尝试使用这个

  # assuming df is your data.frame and gender, height are column names
  tapply(df$height, df$gender, function(grp) c( Freq = length(grp), mean = mean(grp),mode = mode(grp),SD =  sd(grp),min =  min(grp),max = max(grp)))
  

  回复于 2024-05-13T21:06:13+08:00