topic Proc MIXED random intercept model sp(pow) in Statistical Procedures

Proc MIXED random intercept model sp(pow)

____1 — Tue, 11 Sep 2018 11:05:58 GMT

Hi,

I'm trying to fit a random intercept mixed model with a sp(pow) covariance structure (time is continuous) to quality of life data. When I try to run the code below SAS gives me the following error:

"Warning: Stopped because of too many likelihood evaluations."

proc mixed data=data cl;

class person_id treatment_group;

model QOL = QOL_baseline treatment_group time treatment_group*time

/ solution cl htype=1;

repeated / type=sp(pow)(time) subject=person_id r rcorr;

random intercept / subject=person_id;

run;

Can anyone help?

Re: Proc MIXED random intercept model sp(pow)

sld — Tue, 11 Sep 2018 18:34:37 GMT

As noted in Tips and Strategies for Mixed Modeling with SAS/STAT® Procedures by Kiernan et al., this warning could be due to an overspecified model. Try omitting

random intercept / subject=person_id;

This paper by Littell et al. describes the difference between an AR(1)+RE structure and an AR(1) structure.

The Kiernan et al. paper lists other potential solutions to this problem.

I'd also add the <repeated-effect> to the REPEATED statement; it may not be necessary for your data but it's a programming safeguard. See the documentation.

I hope this helps.