Kaz's SAS, HLM, and Rasch Model
Kaz's macros for SAS PROC MIXED
Home
Large National Data Sets
Kaz Library
SAS manuals
What is "error"?
Rasch Model
HLM
SAS PROC NLMIXED and GLIMMIX
Factor Analysis
Reading output via SAS
Excel functions for Statistical Analysis
Essays on learning statistics
Statistics in Japanese
My profile
My SAS questions and SAS's responses
My work tool box
Homemade Macros for SAS PROC MIXED
MACRO 1: varcut.txt
 
SAS PROC MIXED's output has a cosmetic defect.  Just look at this mess when you put many variables on a CLASS statement (to make it explicit that these should be treated as categorical variables).
 
 
My macro will fix it in this way.

This is the result of using this macro. 

Now to achieve this result:

PROC MIXED..
<here model statement, etc>
ods output solutionF=_soln;
run;

%let soln=_soln;
%include "C:\temp\varcut.txt";

The PROC MIXED syntax should include an ODS statement as in the example.  "_soln" is the name I arbitrarily chose here, but any name can be used.  If I use _soln, I will get _soln2 as a result data set.  Its content will be printed out automatically, so you will be able to read a more concise coefficient table.

This is an example of how I used it.  I used it with MACRO GLIMMIX, though.

This macro can be used also after MACRO GLIMMIX that uses PROC MIXED to run itself.  I wrote this macro actually to go with MACRO GLIMMIX, which is why I have _soln as a data name.  MACRO GLIMMIX produces _soln to host coefficients from the model.  (But note that from version 9 macro galimmix became a procedure PROC GLMMIX)

I think you can also use this macro for PROC GLM and PROG LOGISTICS to fix the messes.  I have not tried them.

MACRO 2: FIXED EFFECT summarizer
Put coefficients into a table whose columns correspond to models.

Enter supporting content here

Copyright 2005 KU
For information inquiry (AT) estat.us