PROC GENMOD w/ REPEATED is changing estimates!

ashlicole — Thu, 07 Sep 2017 17:48:55 GMT

Hi Friends, I'm hoping you can help with a modeling conundrum.

I'm modeling some cost data using generalized linear models (PROC GENMOD). I have multiple observations per person, so I've included the REPEATED statement to account for the correlation between values for the same patient. However, I'm a little confused by the results. As I understand it, including a repeated statement shouldn't change the model estimates, just the CIs/SEs. But I noticed that changing the covariance structure from compund symmetric to autoregressive DOES change the estimates (and by a non-negligible amount!). This is making me wonder if I'm doing something wrong in my code... I've pasted my code below. Aany insight into why I might be getting unexpected changes in the model estimate as a result of changing the covariance structure??

proc genmod data=forreg ;
class id bg year / param=ref ref=first;
model pay = bg year bg*year/ link=log dist=gamma;
repeated subject=id /type=cs ;
run;

Re: PROC GENMOD w/ REPEATED is changing estimates!

SAS_Rob — Thu, 07 Sep 2017 18:55:36 GMT

The GEE algorithm is an iterative algorithm that solves for both the parameter estimates and the covariance matrix so you should expect to see differences in both the parameters and the standard errors.

There will be more specific details here

http://support.sas.com/documentation/cdl/en/statug/68162/HTML/default/viewer.htm#statug_genmod_details29.htm

topic PROC GENMOD w/ REPEATED is changing estimates! in Statistical Procedures

PROC GENMOD w/ REPEATED is changing estimates!

Re: PROC GENMOD w/ REPEATED is changing estimates!