Hello,
I am using SAS 9.4 to run a model using PROC GEE with a multinomial outcome (3-levels), binary and continous independent variables, and repeated measures. I have a significant interaction term between two categorical variables.
Typically I would use the estimate or lsmeans statement to calculate the odds ratios for the possible combinations, however these options are not available with PROC GEE.
How can I generate the standard errors/confidence limits for each of the combinations of the interaction term? Is there another way to code my interaction term?
PROC GEE data=dataset descending;
class var1 var2 var3 ID/Ref=first;
model outcome= time var1 var2 var3 var2*var3 / dist=multinomial link=glogit;
repeated subject=ID /Type=ind;
run;
LSMEANS are available in my version of PROC GEE (SAS/STAT14.1), so the most hopeful thing I can think of is to upgrade your installation.
Steve Denham
Don't miss out on SAS Innovate - Register now for the FREE Livestream!
Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.