hmmm
REG does not use the CLASS statement. So using dummy vars is an alternative. GLM does use the CLASS statement and does support more than one class variable. The OUTPUT statement is used to write out the individual estimates. Past that I am not sure of the question (or the model). Consider the following to see if it can start the discussion.
[pre]proc glm data=sashelp.class;
class age sex;
model weight = age|sex height;
output out=stat p=pred cookd=cooksd;
run;
[/pre]
... View more
