如何交叉表观察具有多个类别的成员资格？

Question

我有一个数据集，其中包含混合了互斥和非互斥类别的观察结果。例如，假设不存在混血种族而存在多重国籍，那么数据集看起来像这样：

 id white hispanic asian usa canada uk
 1     0        1     0   1      0  1
 2     1        0     0   0      1  0
 3     0        0     1   1      0  1
 4     1        0     0   1      1  0
 5     0        1     0   0      0  1
 6     0        0     1   0      0  1

如您所见，任何人 person/observation 只有一个种族，但可以拥有多个国籍。我希望通过公民身份来分解种族并产生这样的东西：

         usa       canada    uk        total
white     1 (33%)   2 (66%)   0         3  
hispanic  1 (33%)   0         2 (66%)   3  
asian     1 (33%)   0         2 (66%)   3  
total     3         2         3

我如何编写一个循环来汇总所有类别，以便我可以在种族和公民身份之间进行交叉表（可以重复计算）？

任何关于此类数据可视化的 advice/suggestion 将不胜感激。非常感谢您的帮助！

Answer 1

根据我的理解，您可以将您的数据突变为整洁的格式，然后使用 janitor 获得交叉 table:

数据：

df <- data.frame(id = seq(1,6),
                 white = c(0,1,0,1,0,0),
                 hispanic = c(1,0,0,0,1,0),
                 asian = c(0,0,1,0,0,1),
                 usa = c(1,0,1,1,0,0),
                 canada = c(0,1,0,1,0,0),
                 uk = c(1,0,1,0,1,1))

代码：

library(tidyverse)
library(janitor)

df %>% 
  pivot_longer(cols = 2:4,names_to = "Origin") %>% 
  filter(value == 1) %>% 
  select(-value) %>% 
  pivot_longer(cols = 2:4, names_to = "ethnicity") %>% 
  filter(value == 1) %>% 
  select(-value) %>% 
  tabyl(Origin, ethnicity) %>% 
  adorn_totals(where = c("row","col")) %>% 
  adorn_percentages(denominator = "col") %>% 
  adorn_pct_formatting(digits = 0) %>% 
  adorn_ns(position = "front")

输出：

   Origin   canada       uk      usa    Total
    asian 0   (0%) 2  (50%) 1  (33%) 3  (33%)
 hispanic 0   (0%) 2  (50%) 1  (33%) 3  (33%)
    white 2 (100%) 0   (0%) 1  (33%) 3  (33%)
    Total 2 (100%) 4 (100%) 3 (100%) 9 (100%)

如何交叉表观察具有多个类别的成员资格？

How do I crosstab observations with membership in multiple categories?

r

crosstab

categorical-data