BookmarkSubscribeRSS Feed
mbakare
Calcite | Level 5

Hi Everyone,

proc mixed returned the statement  "Covariance Parameter Values At Last Iteration"  which is an indication that I don't have convergence solution even though some covariance parameter estimates are displayed. Unfortunately, It could not give me "Fit statistics" from where I would extract "-2 Res Log Likelihood"  to carry out likelihood ratio test. Please how do I improve efficient of my proc mixed procedure to have convergence so as NOT to display "Covariance Parameter Values At Last Iteration"

Meanwhile the result from other traits seem to be good.

See my script below

 

ods output Fitstatistics = &dsn._dm_fitstat(where=(descr="-2 Res Log Likelihood") rename=(value=full_loglik));
ods output Dimensions = &dsn._dm_dim(rename=(Descr=Descr1 value=full_dim)where=(Descr1="Covariance Parameters"));

proc mixed data = &dsn noitprint noclprint update;
by trait;
class trial rep gen;
model y = trial gen gen*trial/ddfm = satterth;
random rep(trial);
repeated /group = trial;
where trait in("dm");
run;
quit;

 

 

 

1 REPLY 1
unison
Lapis Lazuli | Level 10

One route might be adjusting the default tolerance up so that you get convergence (convf, convg or convh options)?

https://support.sas.com/documentation/cdl/en/statug/63347/HTML/default/viewer.htm#statug_mixed_sect0...

 

-unison 

-unison

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!
How to Concatenate Values

Learn how use the CAT functions in SAS to join values from multiple variables into a single value.

Find more tutorials on the SAS Users YouTube channel.

Click image to register for webinarClick image to register for webinar

Classroom Training Available!

Select SAS Training centers are offering in-person courses. View upcoming courses for:

View all other training opportunities.

Discussion stats
  • 1 reply
  • 422 views
  • 2 likes
  • 2 in conversation