base

使用summary()直接获取相应的结果

  1. df <- mtcars[,c("mpg", "cyl","disp", "am")]
  2. summary(df)
  3. # out
  4.       mpg             cyl             disp             am        
  5.  Min.   :10.40   Min.   :4.000   Min.   : 71.1   Min.   :0.0000  
  6.  1st Qu.:15.43   1st Qu.:4.000   1st Qu.:120.8   1st Qu.:0.0000  
  7.  Median :19.20   Median :6.000   Median :196.3   Median :0.0000  
  8.  Mean   :20.09   Mean   :6.188   Mean   :230.7   Mean   :0.4062  
  9.  3rd Qu.:22.80   3rd Qu.:8.000   3rd Qu.:326.0   3rd Qu.:1.0000  
  10.  Max.   :33.90   Max.   :8.000   Max.   :472.0   Max.   :1.000

数据结果中并没有偏度和峰度的结果

偏度：度量随机变量概率分布的不对称性 image.png 当偏度<0时，概率分布图左偏。 当偏度=0时，表示数据相对均匀的分布在平均值两侧，不一定是绝对的对称分布。 当偏度>0时，概率分布图右偏 峰度：度量随机变量概率分布的陡峭程度 image.png 完全服从正态分布的数据的峰度值为 3，峰度值越大，概率分布图越高尖，峰度值越小，越扁

自己写一下

  1. # 偏度
  2. sapply(df, function(x) {
  3.   sum(((x - mean(x))/sd(x))^3)/length(x)
  4. })
  5. # out
  6. # mpg        cyl       disp         am 
  7. #  0.6106550 -0.1746119  0.3816570  0.3640159 
  9. # 峰度
  10. sapply(df, function(x) {
  11.   (sum(((x - mean(x))/sd(x))^4)/length(x)) -3
  12. })
  13. # out
  14. #       mpg       cyl      disp        am 
  15. # -0.372766 -1.762120 -1.207212 -1.924741

psych

使用describeBy()或者describe()获取描述性统计分析结果

  1. describe(df)
  2. describeBy(df, group = "am")

分组描述

aggregate

func只能接受单返回值

  1. # by 可以存在多个分组变量
  2. aggregate(df, by = list(gr = df$am), FUN = mean)
  4. # out
  5. #   gr      mpg      cyl     disp am
  6. # 1  0 17.14737 6.947368 290.3789  0
  7. # 2  1 24.39231 5.076923 143.5308  1

group_by与summarize

  1. df %>% group_by(am) %>% summarise(
  2.   count = n(),
  3.   dist.mean = mean(disp, na.rm = TRUE),
  4.   dist.sd = sd(disp, na.rm = TRUE),
  5.   mpg.mean = mean(mpg, na.rm = TRUE),
  6.   mpg.sd = sd(mpg, na.rm = TRUE),
  7. )
  8. # out
  9. # A tibble: 2 x 6
  10. #     am count dist.mean dist.sd mpg.mean mpg.sd
  11. #  <dbl> <int>     <dbl>   <dbl>    <dbl>  <dbl>
  12. #1     0    19      290.   110.      17.1   3.83
  13. #2     1    13      144.    87.2     24.4   6.17