Bayesian Data Analysis With OpenBUGS, BRugs, and JAGS

Software download:

• WinBUGS
• OpenBUGS website (Information)
• JAGS (Installation instructions / Example)
• R package: BRugs
• R package: MCMCpack
• R package: rJAGS
• BRugs package includes OpenBUGS.

Recommended Textbooks

Must-haves

• Bayesian Data Analysis, 2nd Edition. Gelman, Carlin, Stern, and Rubin (2004) go to CRP press to order. One of the best sellers. Cheap.
• WinBUGS manual and examples (Vol 1, 2, and 3). free download from winbugs homepage.
• OpenBUGS manual free download from openbugs homepage.
• Bayesian Approaches to Clinical Trials and Health-Care Evaluation. Spiegelhalter, Abrams, and Myles (2004). Frank's favorite.

Online Courses

• http://users.soe.ucsc.edu/~draper/eBay-Google-2013.html Bayesian Modeling, Inference, Prediction and Decision-Making by David Draper

A list of good textbooks:*

• Computational statistics. Givens and Hoeting (2005). expensive. A general overview of statsistical computing including EM algorithm, optimization algorithm, numerical integration, MCMC, Bootstrapping, and smoothing.
• Markov Chain Monte Carlo in Practice. Gilks, Richardson, and Spiegelhalter (1996). expensive For theroetical and further readings of MCMC.
• Bayes and Empirical Bayes Methods for Data Analysis, 2nd Edition. Carlin and Louis (1996). Cheap. Best seller.
• Bayesian Analysis. Box and Tiao. (classic version)
• See also http://www.indiana.edu/~kruschke

Notes, Slides, Codes and Data sets

• IBC Plan 1/17/2006
• Latex template of slides
• Latex template of notes: main program, hierarchicalNormalNormal.tex, intro.tex

• BUGS language, Hierarchical normal / normal model, Yi He, Feb. 13, 2006
  • BUGS code with data
  • Data for R, R program
  • notes
  • Slides
• Meta Analysis, logistic regression, Chuan Zhou, March 9, 2006
  • BUGSintro_0306.pdf: meta-JAGS Slides
  • The lecture slide, data, R and BUGS code are attached. Use tar -xzvf to unpack the file, and read the README file carefully.
  • JAGS code with data

The first presentation will include:

1. Overview of our IBC project: members, organization, plan, goal, etc.*
2. A short handout of the presentation;
3. Very brief overiew of Bayesian techniques, in particular, how to understand Bayesian MCMC samples vs. frequentist analysis; common MCMC samplers;
4. Software download and install;
5. A concrete hierarchical example with data and BUGS code. Run the code during the presentation and explain some Bayesian concepts in this example;