my model assesses the relative risk of positive_reaction (1/0) associated with therapy hours. proc genmod data=mydata; class id; model positive_reaction = num_hours +other_vars /dist=poisson link=log; output out=try predicted=p reschi=r resraw=resraw; repeated subject=id /type=unstr; quit; proc sgplot data=try; scatter x=p y=r; scatter x=p y=resraw; run; i would like to create a diagnostic plot in the genmod procedure to see if this linearity relationship works, or i need to use cubic splines. i did the scatter plot of predicted and raw residual (resraw), it shows two straight lines if i do the scatter plot of the predicted and pearson residual (reschi), it shows two distinct curved line but i expect to see random dots which scattered the XY plain i might have not done the correct residual plots. what should i suppose to do? thanks so much.
... View more