Hi,   I'm not quite sure from your question what your goal is.  If you are looking for a multivariate response, would something like the following help?   I've also included time as a numeric variable in case you were looking to leverage the linear (or non-linear) structure of change over time, but I haven't worked that into the model yet.   Ryan   data clp4y ;    set clp4 ;    logy = logp24 ;    var = 'logp24' ;    time = 24 ;    output ;    logy = logp48 ;    var = 'logp48' ;    time = 48 ;    output ;    logy = logp72 ;    var = 'logp72' ;    time = 72 ;    output ;    logy = logp96 ;    var = 'logp96' ;    time = 96 ;    output ; run ; proc mixed data=CLP4y ;       class var diet hormone;       model logy = var diet hormone diet*hormone/ ddfm=KR;       repeated var / r ;       lsmeans diet hormone diet*hormone / pdiff=all ;       *repeated time 4 (24 48 72 96) polynomial/summary printe;       *lsmeans diet hormone diet*hormone/pdiff lines; run; ... View more

Hi,   without some sample data, it is difficult to tell for sure if the variables should be dropping out, however I did notice one thing in the code that I wanted to ask about.   In the "strata" statement you have the following:      Strata Year Hight_sensitive EPA Emissions_trading;   but in the class and model statements you have:      class High_sensitive ...   is it possible that a simple typo of "Hight_sensitive" rather than "High_sensitive" may be the source of your issues?   best of luck!   Ryan     ... View more