Blanks in polychoric matrix

[jose nogueira]

Hi, does any one know the reason why the polychoric matrix often include blank values? Why is the the system unable to calculate correlation between those variables?

[William Lisowski]

Welcome to Statalist.

I'll start by rewording your sparse description of your problem to reflect my understanding.

You are using the polychoric command, a user-written Stata command available from SSC, to compute the polychoric correlation matrix for a set of discrete variables. You find there are blank values in the matrix of polychoric correlations it displays. Why is that?

When I've used the polychoric command, I've seen that it follows the same conventions as the correlate command and only displays the main diagonal (which of course is all 1's) and the correlations below the diagonal. This is because all correlation matrices are symmetric, so the correlation of x1 and x2 is the same as the correlation of x2 and x1.

I have never seen blank entries below the main diagonal in a correlation matrix produced by either polychoric or correlate.

Perhaps I've misunderstood your problem. If so, you might add further detail to your question, having first taken a few moments to look over the Statalist FAQ linked to from the top of the page, as well as from the Advice on Posting link on the page you used to create your post. Note especially sections 9-12 on how to best pose your question.

The more you help others understand your problem, the more likely others are to be able to help you solve your problem.