Change in R-square for Hierarhical logistic regression

[CGA]

I am conducting hierarchical logistic regression (entering variables in blocks) and wondering if there is a way to calculate whether the change in the R-square between each block is significant? In SPSS this is possible because it considers each block as part of the same command...but in SAS each model is run separately. Basically, is it possible to get the p value for the change in R2 between model 1 and model 2, model 2 and model 3.

[Ksharp]

I am not sure. Do you want COV matrix between each subject ?

Check PROC GLIMMIX for mixed model for logistic.

Or your are using STRATA statement of PROC LOGISTIC ?