Instructor: Fang Chen (SAS Institute Inc)

AUGUST 18, 1:30—5 PM

ROOM: LInC 268

The MCMC procedure is a general purpose Markov chain Monte Carlo simulation tool designed to fit a wide range of Bayesian models, including linear or nonlinear models, multi-level hierarchical models, models with nonstandard likelihood function or prior distributions, and missing data problems. This tutorial starts with an in-depth introduction to PROC MCMC and moves on to demonstrate its use with a series of applications. An optional and brief introduction to Bayesian and MCMC methods is included if the audience prefers an overview on the paradigm.

Course Outline

Part I – Introduction to Bayesian statistics (optional)

1. Concepts in Bayesian Methods
2. Computational Methods
3. Convergence Diagnostics

Part II – Introduction to PROC MCMC

Part III – Models and Applications

1. Linear/GLM/Nonlinear Regression Models
2. Classification Variables
3. Models with Nonstandard Distributions
4. Incorporation of Historical Data
5. Random-Effects Models
   1. Generalized Linear
   2. Multivariate
   3. Nested and nonnested models
   4. Repeated Measurements
   5. Connection to other SAS mixed modeling procedures
6. Model Selection
7. Missing Data Analysis

About Fang Chen

Fang Chen is a Senior Manager of Bayesian Statistical Modeling in Advanced Analytics Division at SAS Institute Inc. Among his responsibilities are development of Bayesian analysis software and MCMC procedure. Prior to joining SAS Institute, he received his graduate degree in statistics from Carnegie Mellon University in 2004.