I am having a hard time figuring out how to get an adjusted
percentages for drug rates at each of our hospitials.

I have the observed percentage of our yes no variable by using proc
freq by hosp*drug(y/n).

I thought I had found a solution, with the lsmeans hosp/ilink
statement.  Upon further examination, it appears that statment
actually gives me the predicted probabilities.  Does anyone know of a
way to get what I am looking for?  Similar to an adjusted mean of a
continuous variable in the lsmeans statment in GLM?  Thanks in advance
for your help.

Meg

proc GLIMMIX  data=hospdata;
title "";
class hosp RACE;
model drug(desc)= RACE age male  hosp/dist=binary link=logit solution
OR ddfm=bw ;

lsmeans hosp/ cl ilink;

run;