Thanks for the example. I am thinking that the time-varying predictor...in this case would need to be in the Random Statement.    Maybe something like this...   proc mixed data = work noclprint covtest; class id trtprogram (ref='0'); model cd4 = time time2 trtprogram/ ddfm=bw solution cl; random intercept time time2 mcm_dico /subject = id type = un; run;   Thoughts? Am I still able to say the change in CD4 cell counts based on Treat Program from this analysis?  ... View more