Interpreting proc genmode output

[ChuksManuel]

Hello guys,

I will be glad to know how i can interpret proc genmod output. Materials online have not helped one bit!

Its a clinical trial data and my model is as below:

proc genmod data = newdata descending;
class ID dose time;
model status=dose time dose*time/dist=bin link=logit;
repeated subject=ID/type=un corrw covb modelse within=time;
run;

Status is my outcome variable and is coded (1 vs 0). How do i interprete dose and the interaction term (dose*time)? Please any imput needed.

[SteveDenham]

Interpretation of the GEE parameters follows the same general principles outlined by @PaigeMiller in your post "Interpreting proc mixed output" in the Statistical Procedures community.  Note that the reference category for dose and time is the last level and is set to zero for the non-full model GLM parameterization.  interpretation of the Type 3 tests is usually the way to look for main effect and interaction differences, so make sure you have added the Type3 option to your MODEL statement.

SteveDenham

[ChuksManuel]

Thanks. It's clear