BookmarkSubscribeRSS Feed
Val40106
Calcite | Level 5

Help!

PROC GLIMMIX IS NOT CONVERGING! I get an error message

WARNING: Obtaining minimum variance quadratic unbiased estimates as starting values for the

         covariance parameters failed. I first tried d=b link=clogit. My prof suggested deleting the d=b. My outcome is ordinal (1-4)

*****************ANALYSES*******************************;

PROC glimmix DATA=one order=data;

  CLASS v6;

  MODEL encourage= /SOLUTION link=clogit;

  RANDOM intercept/SUBJECT=v6;

  NLOPTIONS TECHNIQUE=NRRIDG;

  weight v8;

  TITLE 'STEP 1: RANDOM EFFECTS ANOVA';

run;

1 REPLY 1
SteveDenham
Jade | Level 19

Well, the obvious first step would be to apply a multinomial distribution (dist=mult, or d=mult, with link=clogit).

This worked for me in translating the example in the PROC GENMOD documentation (Example 43.4 Ordinal Model for Multinomial Data) to a GLIMMIX framework.

Steve Denham

sas-innovate-2026-white.png



April 27 – 30 | Gaylord Texan | Grapevine, Texas

Registration is open

Walk in ready to learn. Walk out ready to deliver. This is the data and AI conference you can't afford to miss.
Register now and lock in 2025 pricing—just $495!

Register now

What is Bayesian Analysis?

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.

SAS Training: Just a Click Away

 Ready to level-up your skills? Choose your own adventure.

Browse our catalog!

Discussion stats
  • 1 reply
  • 2144 views
  • 0 likes
  • 2 in conversation