Chi-square p value matrix in r

Question

Is there any way to find the chi-square p-value matrix in 'R' (a matrix with the p-values between the attributes)?

As an example, consider the the iris data set. I am looking for a matrix as follows:

|                | Sepal length | Sepal width | Petal length | Petal width | Species |
|----------------|--------------|-------------|--------------|-------------|---------| 
| Sepal length   |              |             |              |             |         |
| Sepal width    |              |             |              |             |         |
| Petal length   |              |             |              |             |         |
| Petal width    |              |             |              |             |         |
| Species        |              |             |              |             |         |

The elements of the matrix would be the chi square values for the (i,j) variables of the iris data set.

Sepal length Sepal width Petal length Petal width Species Sepal length Sepal width Petal length Petal width Species — sindhu chowdary, Sep 23 '15 at 06:44
p values should be between the attributes, rows and cols are attributes names — sindhu chowdary, Sep 23 '15 at 06:45
it would be clearer if you edited your question with those informations and formatted this output as a matrix — scoa, Sep 23 '15 at 06:49
They are all continuous variables and how can you do chi squared test? You can do a matrix of correlation p values. — Veera, Sep 23 '15 at 06:52
See [this thread](http://stackoverflow.com/questions/10680658/how-can-i-create-a-correlation-matrix-in-r) (2nd Google hit for 'correlation matrix in r') — Hip Hop Physician, Sep 23 '15 at 16:50

score 8 · Answer 1 · answered Sep 23 '15 at 19:36

8

If that is what you want considering only one of those columns is a categorical variable, Try this:

chisqmatrix <- function(x) {
  names = colnames(x);  num = length(names)
  m = matrix(nrow=num,ncol=num,dimnames=list(names,names))
  for (i in 1:(num-1)) {
    for (j in (i+1):num) {
      m[i,j] = chisq.test(x[,i],x[,j],)$p.value
    }
  }
  return (m)
}
mat = chisqmatrix(iris)

answered Sep 23 '15 at 19:36

pcantalupo

2,212
17
27

If the data is a tibble, use `chisq.test(pull(x, i), pull(x, j))$p.value` – Bart Jul 07 '23 at 19:19

Chi-square p value matrix in r

1 Answers1

Linked