PROC BGLIMM provides Bayesian inference for generalized linear mixed models. Bayesian analysis is different from the classical (or frequentist) approach in the sense that the Bayesian paradigm treats all parameters (including fixed effects and random effects) as random variables, and the objective is to derive inference from the joint posterior distribution of all parameters. PROC BGLIMM uses syntax similar to that of the MIXED and GLIMMIX procedures (the CLASS, MODEL, RANDOM, REPEATED, and ESTIMATE statements) to specify a GLMM, and it uses Markov chain Monte Carlo methods to draw samples from the joint posterior distribution. You can use PROC BGLIMM to fit multilevel nested and non-nested random-effects models and to handle repeated measures data and missing data problems.