BookmarkSubscribeRSS Feed
halladje
Fluorite | Level 6

I would like to run Full Information Maximum Likelihood estimation in my multilevel logistic model (under PROC GLIMMIX). The only documentation I have found for FIML is in PROC CALIS which only appears to allow linear modeling. Does anyone know how to do FIML in GLIMMIX? 

 

Also, my code currently isn't running for my GLIMMIX procedure and I'm not sure why! I'm very new to SAS, so it may be an obvious mistake. 

 

Proc glimmix data=work.smhse method=rspl noclprint;

class x_idschool x_classid x_studentid male prob need;

model intent= male age int ext prob need assets familyincome schoolsize/CL dist=binary link-logit solution oddsratio cl corrb covb;

reference=first event=last;

lsmeans adjust=bon;

random intercept/subject=x_idschool s cl type=vc;

random intercept/subject=s_classid(x_idschool) S CL type=vc;

covtest/wald;

run; 

 

Any advice is greatly appreciated!

1 REPLY 1
Haris
Lapis Lazuli | Level 10
It's been two years since this inquiry. SAS: any progress to report?

Ready to join fellow brilliant minds for the SAS Hackathon?

Build your skills. Make connections. Enjoy creative freedom. Maybe change the world. Registration is now open through August 30th. Visit the SAS Hackathon homepage.

Register today!
What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 1 reply
  • 1434 views
  • 0 likes
  • 2 in conversation