topic PROC CORR for nominal values in Statistical Procedures

PROC CORR for nominal values

issac — Mon, 06 Aug 2012 13:17:43 GMT

Hi everyone;

I want to perform correlation analysis with 4 variables that are measured in nominal scale. I would like to know which method (Pearson, Spearman, Kendall, ...) is best for that purpose? Any comments would be appreciative!

Thanks;

Issac

Re: PROC CORR for nominal values

art297 — Mon, 06 Aug 2012 14:26:02 GMT

Since none of our statisticians have responded as yet, I'll provide a non-statistician's comments which, hopefully, will get them to correct me.

If you only have nominal variables, unless they are all 0,1 dichotomies, I would think that you want to look at proc freq (i.e., chi-square) rather than proc corr.

Art

Re: PROC CORR for nominal values

Rick_SAS — Mon, 06 Aug 2012 15:29:39 GMT

Thanks, Art. For truly nominal values (Red, Green, Blue,...), PROC FREQ and chi-square is a good answer.

If the variables are ordinal, there are more options. In PROC FREQ you can use tetrachoric or polychoric correlations (use PLCORR options on TABLES stmt) to study the correlation between discrete categories that can be ordered.

Rick

Re: PROC CORR for nominal values

issac — Mon, 06 Aug 2012 16:09:38 GMT

Thanks Arthur and Rick;

These are purely nominal, I think. For example, whether the patient is Veteran or not, where is the POW location, Patient Eligibility, Means Test, etc. So I should for PROC FREQ rather than CORR, correct?

Re: PROC CORR for nominal values

Rick_SAS — Mon, 06 Aug 2012 17:32:27 GMT

Yes, based on what you've said. You can use PROC FREQ to test for association between groups or uniformity across groups. for example, to see if POW_LOCATION is uniformly distributed in your data, you can say

tables POW_LOCATION / chisq;

To see if there is an association between gender and veteran status, use

tables SEX*Veteran / chisq;

The FREQ documentation has several examples that you can look at.