R - Create a Matrix of Variables with the frequency of same values

Question

I face a Problem in R which I can't handle myself.

I have a data frame that looks like this with more variables und cases:

ID      Var1   Var2   Var3   Var4
1          1      0      1      1
2          0      0      0      0
3          1      1      1      1
4          1      1      0      1
5          1      0      1      0

I like to have — similar to a correlation matrix — a matrix that shows the frequency that a pair of variables have the same value — for example the value "1". The resulting matrix for the df above should then be like.

           Var1   Var2   Var3   Var4
Var1                2      3      3
Var2                       1      2
Var3                              2
Var4                              

Perhaps you can help. Thank you in advance.

Answer 1

First create a evaluation data matrix that tests for your value, here 1.

e <- d[-1] == 1  ## value to test

Then use outer to compare the columns crosswise with a FUNction that sums how often there are two TRUEs summing up to 2. From the result you apparently want to remove the lower.tri including the diagonal.

FUN <- Vectorize(function(i, j) sum(e[,i] + e[,j] == 2))
(res <- t(outer(1:ncol(e), 1:ncol(e), FUN)))
res[lower.tri(res, diag=1)] <- NA
res
#      [,1] [,2] [,3] [,4]
# [1,]   NA    2    3    3
# [2,]   NA   NA    1    2
# [3,]   NA   NA   NA    2
# [4,]   NA   NA   NA   NA