topic I am trying to obtain variance covariance matrix from proc glm. I know in R we have vcov funtio in Statistical Procedures

I am trying to obtain variance covariance matrix from proc glm. I know in R we have vcov funtio

ndang3188 — Tue, 05 Mar 2024 22:00:58 GMT

proc glm data=outmi;

by _imputation_;

class TRT02PN;

model W24CHG=TRT02PN/solution;

means TRT02PN /hovtest=leven(type=abs);

ods output ParameterEstimates=coeff;

run;

I am trying to obtain variance covariance matrix of the Estimates and don't know what line of code I should you.

Re: I am trying to obtain variance covariance matrix from proc glm. I know in R we have vcov funtio

sbxkoenk — Tue, 05 Mar 2024 23:26:14 GMT

Home > Analytics > Stat Procs > Covariance of Coefficients
https://communities.sas.com/t5/Statistical-Procedures/Covariance-of-Coefficients/td-p/409714

Koen

Re: I am trying to obtain variance covariance matrix from proc glm. I know in R we have vcov funtio

SteveDenham — Tue, 19 Mar 2024 18:31:04 GMT

What do you see when you add the inverse option to the model statement:

proc glm data=outmi;
   by _imputation_;
  class TRT02PN;
  model W24CHG=TRT02PN/solution inverse;
  means TRT02PN /hovtest=leven(type=abs);
  ods output ParameterEstimates=coeff;
run;

And sometimes it is easier to step away from GLM and try something like this:

proc glimmix data=outmi;
   by _imputation_;
  class TRT02PN;
  model W24CHG=TRT02PN/solution covb;
    ods output ParameterEstimates=coeff covb=covb;
run;

This is solely to get the covariance matrix for the fixed effects, and not to combine the imputations.

SteveDenham

Re: I am trying to obtain variance covariance matrix from proc glm. I know in R we have vcov funtio

TomHsiung — Thu, 07 Nov 2024 14:30:23 GMT

Thanks for sharing. I wonder how do we get the variance-covariance matrix of regression coefficients? Thanks.

Re: I am trying to obtain variance covariance matrix from proc glm. I know in R we have vcov funtio

Ksharp — Fri, 08 Nov 2024 01:18:09 GMT

You could try COVB option:

proc glimmix data=sashelp.heart ;
class sex;
model status=weight height sex/dist=binary corrb covb;
run;