proc Genmod with repeated option(GEE estimates) and post hoc test to compare 3 groups.

[eunyo75]

Hi SAS users!! 

I am a beginner of SAS.   I am hoping someone here can help me with.

Currently I am trying to used GEE model using proc genmod for the panel data. 

I want to divide data into three groups. I was able to calculate estimates, SEs, p values. but I want to to compare these groups results. (post hoc test, bonferroni ) because I found the articles to compare between groups. 

I think I can use 'lsmeans'  and 'adjust'  however it doesn't works with repeated measures option.  

How should I solve this? 

[StatDave · Accepted solution]

Yes, it works with the REPEATED statement. For example, the following uses the GEE example in the Getting Started section of the GENMOD documentation.

proc genmod data=six;
class case city age;
model wheeze = city age smoke / dist=bin;
repeated subject=case / type=exch;
lsmeans age / diff adjust=bon;
run;