I have a categorical variable with 4 categories as dependent variable, and 4 categorical independent variables with 2 categories each variable and one continuous independent variable. I want to know which independent contribute the most to the variance of dependent variable.
Could anybody tell me which procedure I should use to do this kind of analysis?
Variance of a categorical variable ? How dow you compute that ?
If likelihood can be used in your question instead of variance, I would give PROC LOGISTIC a try : the type 3 tests would tell which independent variable best contributes to model likelihood.
Do you think Proc Discrim can work in this case? I want to know which variables contribute the most to predict group difference. I tried with this procedure but it seemed like the procedure wouldn't work when there were categorical independent variables.