Hi,
I wonder if it is possible to retain the original identification (Here: unikdyr) from the dataset in the solution output from the random statement in PROC MIXED.
SAS code:
ods output solutionR=sol;
ods trace on;
PROC MIXED data=b covtest ratio;
id unikdyr;
model ekm = dimund60 dimov60 / s ddfm=bw outp=predicted;
random dimund60 dimov60 int / type=un subject=unikdyr solution;
run;
odc trace off;
In the Solution output (sol) each individual now got a subject number, but I would like to be able to link that subjectnumber to an animalnumber (=unikdyr) because I want to use the random estimates in another model.
Any good ideas??
Thanks - Bodil
Add a CLASS statement (I changed the ID statement to a CLASS statement, but you may need both for your outp= option statement):
PROC MIXED data=b covtest ratio;
class unikdyr;
model ekm = dimund60 dimov60 / s ddfm=bw outp=predicted;
random dimund60 dimov60 int / type=un subject=unikdyr solution;
run;
The dataset sol should have what you are looking for.
Steve Denham
Add a CLASS statement (I changed the ID statement to a CLASS statement, but you may need both for your outp= option statement):
PROC MIXED data=b covtest ratio;
class unikdyr;
model ekm = dimund60 dimov60 / s ddfm=bw outp=predicted;
random dimund60 dimov60 int / type=un subject=unikdyr solution;
run;
The dataset sol should have what you are looking for.
Steve Denham
Thanks Steve!
How simple... Sometimes I tend to complicate things... ;o)
Available on demand!
Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.