Abstract
AbstractBerry and Berry proposed a hierarchical model for the analysis of frequency counts of adverse events with one active treatment and one control group. For parameter estimation, a simulation-based Bayesian approach has been suggested. SAS® offers in version 9.2 for the first time a procedure that is able to fit models of any complexity using Bayesian simulation. This procedure – called Proc MCMC – is shipped as experimental version and offers all features to implement the Berry–Berry model in SAS. Proc MCMC allows various ways to code the problem. A successful implementation requires some understanding of the functioning of Proc MCMC as will be demonstrated.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have