Programming the statistical procedures from SAS

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

Accepted Solution Solved
Reply
Occasional Contributor
Posts: 17
Accepted Solution

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

[ Edited ]

Hi all, 

I am trying to do logistic regression with random effiect for binary data by GLIMMIX.

However, I get warinig message as follows;

 

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

 

Anyone know how I can overcome this problem?

Thanks,

 

--------------------------------------------------------------------------------

proc glimmix data=logitbank method=quad;
class fid;
model ydat2(event='1') = D1013 fid*D1013
/dist = binary link=logit ddfm=none solution;
random intercept/ subject=fid;
output out =glmout pred =xbeta pred(ilink) =predprob;
covtest;
run;

---------------------------------------------------------------------------------

 


Accepted Solutions
Solution
‎05-20-2017 07:05 AM
Super User
Posts: 10,784

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

Posted in reply to Tissue5454
Or try PARAM statement . and I quoted here.
"The PARMS statement specifies initial values for the covariance or scale parameters, or it requests a grid search over several values of these parameters in generalized linear mixed models."

View solution in original post


All Replies
Super User
Posts: 10,784

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

Posted in reply to Tissue5454

Why you include subject term in the independent variables ?

Try option type=chol.

 

random intercept/ subject=fid type=chol ;

Occasional Contributor
Posts: 17

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

Hi Ksharp!

 

Thank you for reply!

 

>Why you include subject term in the independent variables ?

 

Because I want to include not only random intercept but also random slope.

 

>Try option type=chol.

 

I received same warning message: WARNING: Obtaining minimum variance quadratic unbiased estimates as starting values for the covariance parameters failed...

Tissue5454

 

 

Solution
‎05-20-2017 07:05 AM
Super User
Posts: 10,784

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

Posted in reply to Tissue5454
Or try PARAM statement . and I quoted here.
"The PARMS statement specifies initial values for the covariance or scale parameters, or it requests a grid search over several values of these parameters in generalized linear mixed models."

Occasional Contributor
Posts: 17

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

Hi Ksharp!

 

Thank you for reply!

 

I tried PARAM statement and succeed in getting result!

I think the warning message;

"WARNING: Obtaining minimum variance quadratic unbiased estimates as starting values for the covariance parameters failed" tend to come up when the model is too complicated.

In my case, independent variable "D1013" is nonsignificant .

 

Thank you again,

 

tissue5454

 

Super User
Posts: 10,784

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

Posted in reply to Tissue5454

I am glad that worked and pround of your effort .

Regular Learner
Posts: 1

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

Posted in reply to Tissue5454

Hey there, tissue5454

 

Do you mind sharing the syntax of your PARAM fix. I am having a similar code and error log, and would like to know how/where the PARAM fix was inserted. 

 

Many thanks, in advance.

 

-R

Occasional Contributor
Posts: 17

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

Sorry... I could not find the above file.

 

tissue5454

 

PROC Star
PROC Star
Posts: 404

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

Lots of good information in this recent SGF paper by Kathleen Kiernan (2018) of SAS, including possible solutions to the warning message that you are getting

 

Insights into Using the GLIMMIX Procedure to Model Categorical Outcomes with Random Effects

 

This older paper by Kiernan, Tao, and Gibbs (2012) is good, too

 

Tips and Strategies for Mixed Modeling with SAS/STAT® Procedures

Occasional Contributor
Posts: 17

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

Thank you sld !


Your information is valuable for me and rplum64.

These papers containe some examples which use "PARMS" statement.

 

Thank you again for your help.

☑ This topic is solved.

Need further help from the community? Please ask a new question.

Discussion stats
  • 9 replies
  • 1280 views
  • 6 likes
  • 4 in conversation