Tabulating multiple response questions

apply, r

Solution

dat.t <- data.frame(table(dat))    
dat.t$combn <- apply(dat.t[,1:4] == 1, 1, function(x) paste(names(dat)[x], collapse=' + '))

> dat.t
   A B C D Freq         combn
1  0 0 0 0    2              
2  1 0 0 0    2             A
3  0 1 0 0    0             B
4  1 1 0 0    1         A + B
5  0 0 1 0    1             C
6  1 0 1 0    3         A + C
7  0 1 1 0    0         B + C
8  1 1 1 0    2     A + B + C
9  0 0 0 1    0             D
10 1 0 0 1    2         A + D
11 0 1 0 1    1         B + D
12 1 1 0 1    1     A + B + D
13 0 0 1 1    2         C + D
14 1 0 1 1    0     A + C + D
15 0 1 1 1    3     B + C + D
16 1 1 1 1    0 A + B + C + D
>

Problem

Imagine that I have a question for which there are four options, and a respondent can select zero or any combination of the four. The variables are named `A`, `B`, `C`, and `D` and the responses are stored in a data.frame as below. ``` set.seed(1) dat = data.frame(A = sample(c(0, 1), 20, replace=TRUE), B = sample(c(0, 1), 20, replace=TRUE), C = sample(c(0, 1), 20, replace=TRUE), D = sample(c(0, 1), 20, replace=TRUE)) ``` I can tabulate the combination of responses (for example, how many responded with `A` alone, or `A`+`B`, or `C`+`D`, and so on) by doing the following: ``` data.frame(table(dat)) # A B C D Freq # 1 0 0 0 0 2 # 2 1 0 0 0 2 # 3 0 1 0 0 0 # 4 1 1 0 0 1 # 5 0 0 1 0 1 # 6 1 0 1 0 3 # 7 0 1 1 0 0 # 8 1 1 1 0 2 # 9 0 0 0 1 0 # 10 1 0 0 1 2 # 11 0 1 0 1 1 # 12 1 1 0 1 1 # 13 0 0 1 1 2 # 14 1 0 1 1 0 # 15 0 1 1 1 3 # 16 1 1 1 1 0 ``` I would like to now create a new column that shows the letter combination that is being represented by this output. For example, row 4 represents the count of `A`+`B` responses, and row 14 represents the count of `A`+`C`+`D` responses. I think that one of the `apply` functions would be useful here, but I'm not sure how to proceed.

Original source