Tutorial: Bayesian Statistics and Marketing

presented by Peter Rossi

Bayesian methods have become increasingly popular in marketing applications. The purpose of this tutorial is twofold: 1) to provide a brief introduction to Bayesian inference and to models appropriate for marketing applications and 2) to demonstrate how our R package, bayesm, can be used to analyze both survey and marketplace data collected for marketing applications.

We will cover the following topics:

• Bayesian Essentials
• MCMC methods
• Hierarchical Models
• Multinomial Logit/Probit Models
• Bayesian analysis of conjoint survey data
• Bayesian analysis of consumer purchase panel data

All discussion will be illustrated by examples that employ bayesm.

Background:

• Elementary knowledge of R
• Basic knowledge of statistics including distribution theory.
• Chapters 2, 3 and appendix A (particularly sections 2.0-2.4, 2.8 and 3.1-3.4) of Bayesian Statistics and Marketing by Rossi et al (Wiley 2005) will be helpful.

Back to Tutorials