Good morning,
How can I store effects from the "missmodel" of the proc gee to be able to use them in proc mianalyze?
Briefly, I have imputed M=10 (works fine) then I have run:
proc gee data=d;
by _imputation_;
class output t_class id;
model output = t v1 v2 v3 / dist=bin; /* These effects seem to be stored */
repeated subject=id / within=t_class corr=un ecovb;
missmodel t v1 v2 v3 prev / type=obslevel; /* These effects I would like to store, too */
ods output GEEEmpPEst=gmparms_mi_1 parminfo=gmpinfo_mi_1
modelinfo=modelinfo_mi_1 GEERCov=gmcovb_mi_1;
run;
Now when I run proc mianalyze I get an error "The effect prev is not in the PARMINFO= data set."
Could you kindly help?
Thanks in advance,
Piotr Lewczuk
The table name for the missingness model parameter estimates is MissModelPEst, they are not included in the response model parameter estimates table (the GEEEmpPEst table).
Note you can always use the ODS TRACE statement to request a record of each output object that's produced. That information will be written to the SAS log and it will include the table name. Also at the end of the details section for SAS/STAT procedures there will be a section on ODS Table Names that will summarize the table names and the statement/option that requests the table. Here is that section for PROC GEE.
The table name for the missingness model parameter estimates is MissModelPEst, they are not included in the response model parameter estimates table (the GEEEmpPEst table).
Note you can always use the ODS TRACE statement to request a record of each output object that's produced. That information will be written to the SAS log and it will include the table name. Also at the end of the details section for SAS/STAT procedures there will be a section on ODS Table Names that will summarize the table names and the statement/option that requests the table. Here is that section for PROC GEE.
Thank you very much! This is very helpful.
Piotr
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 16. Read more here about why you should contribute and what is in it for you!
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.