You could fit a conditional logistic model by stratifying on the sites by using the STRATA statement. Doing this will remove the need to estimate the separate parameters for the sites. See the conditional logistic example in the PROC LOGISTIC documentation. If you need to estimate the site parameters, you could try using the penalized likelihood method by adding the FIRTH option. Another possibility is exact estimation, but this is very resource intensive and might not be feasible. ... View more

Got it from SAS Programming in the Pharmaceutical Industry book. Also, this code does not have drug class in it. It would just get n % for cmdecod and active, placebo, and total columns so it doesn't match exactly what you're trying to do.   However, I have made a lot of TLFs for clinical trials if you or @sbxkoenk knows anyone in need of another SAS Programmer. Also, check out my poster at SESUG this fall. ... View more