Hi, I want to test whether my gender variable effects my categorical variable, with levels say 1, 2 and 3, in any way. I've done tested the assumption for normality, it does not hold. What PROC statement should I use to test independence between my variables now rather than the PROC TTEST?
From your description, you have only categorical variables and so test of normality and t-tests are meaningless and also irrelevant.
It sounds like you want a chi-squared test from a simple contingency table using PROC FREQ.
From your description, you have only categorical variables and so test of normality and t-tests are meaningless and also irrelevant.
It sounds like you want a chi-squared test from a simple contingency table using PROC FREQ.
My categorical variable, levels 1 2 & 3, is transformed from raw data using if statements.
Normally, I advise against this.
So if I worked with the raw data I had to test normality and equality of variance for both genders, and if those assumptions held, then test independence.
Not sure what "independence" means in this context. But since you mentioned t-tests, normality and equality of variance are necessary, but the Satterthwaite t-test handles the case where the variances are different. If you have large amounts of data, then the central limit theorem takes care of normality, and makes the standard t-test reasonable. (And if you don't have a lot of data, there are bootstrap tests and also non-parametric tests available in SAS)
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.