BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
claudiajc
Obsidian | Level 7

Hi,

 

I am currently running the model below  It runs fine and I obtain the output data sets I want.  However, it shows "WARNING: Class levels for USUBJID are not printed because of excessive size".  There are a few hundred of subjects in this data set, and there are several records per subjects.

 

a) Why am I getting this warning?

b) Is this 'warning' unavoidable?

c) Does it affect the statistical analysis? 

d) What would you recommend I do to avoid this warning being shown?

 

Many thanks,

 

Claudia

 

ods listing close;
proc glimmix data=one order=data;
 nloptions tech=nrridg;
 class                  trt01pn day period usubjid;
 model avalc(event='Y')=trt01pn day trt01pn*day period base/link=logit dist=binary s ddfm=kr;
 random intercept day period/type=vc subject=usubjid;
 lsmeans trt01pn*day trt01pn/ilink diff obsmargins cl oddsratio; 
ods output 
           ConvergenceStatus=status
           LSmeans=lsmeans
           Diffs=diffs
           tests3=Tests3;
 run;
quit;
ods listing;
1 ACCEPTED SOLUTION

Accepted Solutions
PaigeMiller
Diamond | Level 26

a) Why am I getting this warning?

 

I think that's pretty clear, you have too many levels of USUBJID

 

b) Is this 'warning' unavoidable?

 

Probably, in this case with hundreds of subjects.

 

c) Does it affect the statistical analysis? 

 

No, I don't think so. The WARNING message would have told you the model fit is suspect, or words like that.

 

d) What would you recommend I do to avoid this warning being shown?

 

I don't know, if you really have to model hundreds of subjects, you're probably going to get this message.

 

 

--
Paige Miller

View solution in original post

2 REPLIES 2
PaigeMiller
Diamond | Level 26

a) Why am I getting this warning?

 

I think that's pretty clear, you have too many levels of USUBJID

 

b) Is this 'warning' unavoidable?

 

Probably, in this case with hundreds of subjects.

 

c) Does it affect the statistical analysis? 

 

No, I don't think so. The WARNING message would have told you the model fit is suspect, or words like that.

 

d) What would you recommend I do to avoid this warning being shown?

 

I don't know, if you really have to model hundreds of subjects, you're probably going to get this message.

 

 

--
Paige Miller

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
  • 2 replies
  • 1473 views
  • 1 like
  • 2 in conversation