How do you include random effects in GENMOD?  I don't see how you could do this, unless you are referring to the REPEATED statement used to create GEE models.   To implement my idea of looking at the information criteria, I think you will have to switch to GLIMMIX where you can specify random effects in a RANDOM statement.  At this point, greater detail on the design used to collect the data, models considered, and the questions that the data are supposed to address would be in order to provide additional help.   SteveDenham ... View more

So I tried to use "the restrict" that you talked about proc reg data=data; model a= int b c d; restrict int=intercept; run;   but that doesn't solve the problem, because I can't do the restrcition if int is not in the model. Thus I have 4 variables int, b, c and d and an intercept that is equal to int ... View more

It might help that Proc Reg is one of the procedures that will let you have multiple model statements. The label, text with :, is the help reading the output to identify which model is shown. proc reg data=data; a_b_c_d: model a = b c d; a_b: model a = b; a_c: model a = c; a_d: model a = d; run; quit; ... View more

See this example https://documentation.sas.com/?cdcId=pgmsascdc&cdcVersion=9.4_3.4&docsetId=statug&docsetTarget=statug_reg_gettingstarted01.htm&locale=en   You look at the ANOVA table, and if Pr>F is <0.05, then the model is significant at the 5% level. If the Pr>F is <0.01, then the model is significant at the 1% level. ... View more

You take the p-value for the coefficient of B, and you double it. ... View more