GENMOD and repeated measurement

[SHINAR]

I have a repeated-measurement data including 1.8 million observations, and each individual contains more than one recording. I wonder to explore the relationship between outcome and exposure using PROC GLIMMIX, like this: proc glimmix data=mydata; class id stage; model outcome=exposure confoundings / solution cl; random int / subject=id(stage); run; But, SAS log specified an error that is "Model is too large to be fit by PROC GLIMMIX in a reasonable amount of time on this system. Consider changing your model." I want to know if could I use PROC GENMOD+REPEATED instead to fit my model. proc genmod data=mydata; class id source; model outcome=exposure confoundings ; repeated subject=id /within=stage; run;

[DannyModlin]

Greetings.

When using linear mixed models, it is possible to generate the same marginal model from use of the RANDOM statement or the REPEATED statement. You would just have to check the V matrix created by both structures. However, when you leave normality(Generalized linear mixed models) you will not yield the same marginal model.

Hope this helps.

[StatDave]

Yes, you could try fitting a GEE model, but use PROC GEE, not PROC GENMOD. There is no guarantee though that the time and memory needed will be feasible. Be sure to specify your response distribution in the DIST= option in the MODEL statement. And the WITHIN= variable should also be in the CLASS statement.