STATS 331: Introductory Bayesian Data Analysis:

Second Semester 2010

Taught by Dr. Wayne S. Stewart

STATS 331 is a paper offered in the second semester 2010.

 

The title is "Introductory Bayesian Data Analysis".

 

The paper starts with a brief history of Statistics, and demonstrates that the  Bayesian paradigm was basically how Statistics was originally done and how it went out of favour, to be largely replaced by the frequentist paradigm (which we call classical and is what you have been taught up till now)  only to flourish again in the last 30 or so years due to the advancement of the computer and the mathematics of MCMC (Monte Carlo Markov Chains),  the combination of which has meant that Bayesian statistics is doable and is capable of answering questions that the classical methods cannot.

 

The course will give an introduction to some of the principles that are foundational to the Bayesian paradigm (like the Likelihood principle), along with a number of philosophical issues like the conditionality priniciple and Stopping rule principle. 

 

 The Bayesian approach will be introduced through discrete distributions using "Bayes Box". The parameter is treated as a Random Variable with a probability density function. The prior reflects prior knowledge, which is updated with the likelihood to form the latest understanding of the parameter called the posterior.

 

The course will show methods of summarizing the posterior, including Highest density intervals and Bayesian credible regions and give details on how to practically carry out a fully Bayesian analysis.

 

Basics of Bayesian simulation will be taught with rejection sampling and MCMC as a black box. Only the absolute mathematical necessities will be taught with most emphasis given to the practical implementation and interpretation.

 

WinBUGS will be the main software used to do the simulations and construct and run the models. Time will be given to learn and understand how to use this software. Indeed the two software packages used in the course will be R and WinBUGS.  Interestingly, WinBUGS can be run from within R and this will be covered also.

 

Model checking will be taught using Bayes factors,  predictive distributions and DIC.

 

A major part of the course will be to re-run analyses and methods you are already familiar with and compare results and interpretations with the Bayesian conclusions.

 

ANOVA, regression, one, two sample t-tests, Hierarchical methods and time series will be given a Bayesian treatment.

 

This course will be an EYE -opener -- you will be shocked at some of the comparisons we make with classical methods.

 

We will look at the probability of the posterior NULL hypothesis and compare this with the classical P-Value for a number of problems.

 

Many new insights into statistics will be demonstrated.

 

For more information contact

Dr. Wayne Stewart

Office 303.294

Ph. 373 7599 X83763