Hello, I am working with a small dataset of pregnant cannabis users.   I am using PROC GEE to examine the effect of preconception cannabis use (prepg_can_new, categorical 1-3) on current cannabis use (Candays, count data 0-30) across the prenatal period. Candays is a repeated measure, asked at each trimester (categorical 1-3). I am using link=log and a negative binomial distribution.   GOAL: I would like to exponentiate point estimates and 95% CLs so they are meaningful during interpretation (IRR).   When using GEE, it seems like I need to run a separate data step to do this. When I run the code below, it exponentiates betas but NOT CLs. How could I adjust this code to get exponentiated CLs?? Potential issue highlighted in red below.   PROC GEE DATA=RQ1_NEW; CLASS BL_MARCH_ID TRIMESTER PREPG_CAN_NEW (ref='1'); MODEL CANDAYS = PREPG_CAN_NEW trimester PREPG_CAN_NEW*TRIMESTER /Dist=negbin LINK=log; REPEATED SUBJECT=BL_MARCH_ID/WITHIN=TRIMESTER TYPE=EXCH; STORE P1; RUN;   ODS OUTPUT PARAMETERESTIMATES = EST; PROC PLM SOURCE = P1; SHOW PARAMETERS; RUN;   data EST_EXP;     set EST;     if upcase(parameter) not in ('INTERCEPT') then do;         IRR = exp(estimate);          IRR_LCL = exp(lclm);          IRR_UCL = exp(uclm);     end; run;   PROC PRINT DATA = EST_EXP; RUN; ... View more