topic Re: PROC GLM, obsorb vs. class statement: Results are different in SAS Procedures

PROC GLM, obsorb vs. class statement: Results are different

Saraja — Tue, 19 Jun 2018 02:44:31 GMT

I am running PROC GLM for the fixed effects regression of variable &depVar. over independent variables &indVar., while controlling for fixed effects for the geographic variation HRR_x_Year. Both ways, the results must be equivalent; however, in first case it complains about a singularity and R-square jumps to 0.84, where as in later case the R-square due to HRR_x_Year only changes about 0.06.Is the implementation different intrinsically.

PROC GLM DATA=WORK.MODEL2;
absorb HRR_x_Year;
model &depVar.= &indVar. / SS3 SOLUTION ;
run;

"Note: The X'X matrix has been found to be singular, and a generalized inverse was used to solve the normal equations. Terms whose estimates are followed by the letter 'B' are not uniquely estimable."

PROC GLM DATA=WORK.MODEL2;
Class HRR_x_Year;
model &depVar.= &indVar. HRR_x_Year / SS3 SOLUTION ;
run;

Re: PROC GLM, obsorb vs. class statement: Results are different

Rick_SAS — Mon, 02 Jul 2018 19:55:23 GMT

Is it possible that you have reversed the order of the two procedure calls?

The message

Note:

The X'X matrix has been found to be singular...

is displayed when you use CLASS variables and you use the SOLUTION option to request the parameter estimates. The NOTE reminds you that the GLM parameterization of classification effects is a singular parameterization and therefore the last level of the classification variable will be set to zero.

Re: PROC GLM, obsorb vs. class statement: Results are different

S4uc3 — Sun, 23 Jul 2023 15:25:06 GMT

Hi I know this is an old thread but I seem to be having the same problem, were you able to find a solution? If so do you mind sharing?

Re: PROC GLM, obsorb vs. class statement: Results are different

PaigeMiller — Sun, 23 Jul 2023 15:35:29 GMT

Please show us the different results.

Re: PROC GLM, obsorb vs. class statement: Results are different

S4uc3 — Sun, 23 Jul 2023 16:27:58 GMT

Thanks for the response. I found a thread you had replied to which suggested theissue was that the absorb statement does not work with two way Fixed Effects. Thanks