Does proc glmselect support random effects

[RobertF]

I'm building a predictive model that predicts future hospital length of stay. The dataset is episode level, including multiple episodes for many of the members. I'd like to use a penalized GLM (such as a lasso) while at the same time including a member-level random effect.

I know proc glmselect does not have a "random" statement. Is there a feature I'm missing or a workaround that allows random effects to be included in a predictive model?

[Ksharp · Accepted solution]

Answer is no.

But you could use interact term to simulate RANDOM effect.

model y=x1 x2 x1*x2  x1*x1 x2*x2 ;

[RobertF]

Thank you Ksharp - I could treat the Member ID # as a fixed effect and model it's interactions, but wouldn't that mean having thousands of Member ID # dummy variables (and using up lots of degrees of freedom)?