How to create dummy variables - Categorical Variables

[Reeza]

If you're doing some analysis with categorical data and you're using a proc that does not support the CLASS statement then you may need to create dummy variables.

I won't go into what dummy variables are, but how to create them using GLMMOD.

Problem: Create dummy variables for sex and age from sashelp.class dataset.

Solution:

/*Run model within PROC GLMMOD for it to create design matrix
Include all variables that might be in the model*/
proc glmmod data=sashelp.class outdesign=want outparm=p;
class sex age;
model weight = sex age height;
run;

/*Create rename statement automatically
THIS WILL NOT WORK IF YOUR VARIABLE NAMES WILL END UP OVER 32 CHARS*/
data p;
set p;
if _n_=1 and effname='Intercept' then var='Col1=Intercept';
else var= catt("Col", _colnum_, "=", catx("_", effname, vvaluex(effname)));
run;

proc sql;
select var into :rename_list separated by " "
from p;
quit;


/*Rename variables*/
proc datasets library=work nodetails nolist;
modify want;
rename &rename_list;
run;quit;


proc print data=want;
run;

The WANT dataset can now be used to model with the dummy variables present.

[Rick_SAS]

Here are some articles about how to create dummy variables in SAS. They contain discussion and examples:

• Create dummy variables in SAS
• Four ways to create a design matrix in SAS
• Dummy variables in SAS/IML

A design matrix is a numeric matrix that representes all variables (continuous and categorical) in a regression model.