Applied Bayesian Analysis
Biostatistics 234
Instructor: Robert Weiss
Fall 2007
Information

Instructor Robert Weiss
Phone 310-206-69626
email robweiss at you-know-where d0t edu

Event Time Day Room
Lecture 1 11:00 - 11:50 Tuesday 51-279 CHS
Lecture 2 11:00 - 12:50 Thursday 51-279 CHS
Computer Lab 12:00 - 12:50 Tue A1-241 CHS
Office Hours 1:00 - 1:30 or more Tue, Thu 51-269
There is no discussion section

2007F Course Business Information (updated 20070925)
Text and references.
Homework Schedule.

The Benefits of Bayes. Bottom line: More Tools.
WinBugs home page. Click on WinBUGS download version 1.4, and get the update to 1.4.3 and the key.
Proof that Bayesians do indeed have more fun. (or not)
Bayesian songbook

Course pages. Password protected. For registered students.

  1. This course is aimed at second year Biostatistics masters students and Biostatistics doctoral students. Graduate (usually doctoral) students with a strong quantitative background from other departments are encouraged to enroll. A necessary prerequisite is a good background in linear regression. For Fall 2007, concurrent enrollment in Biostat 200A is fine.
  2. Grading is based on homework and data analysis projects.
  3. Course topics will include an overview of Bayesian philosophy, computation, data analysis, modeling and estimation. Emphasis will be on data modeling.
  4. Registration info is here, page down to Biostat 234.
  5. Computing labs are an integral part of the course. Lecture examples are illustrated in the labs, and sample programs are presented for most of the computing discussed in class.
  6. Computing is done in WinBugs. Go get WinBugs now! WinBugs is Free. Upgrade to version 1.4.3. You will need to register (its free) to get the key to upgrade to a full-featured version. Since WinBugs does Bayesian calculations well, but not necessarily all calculations nor graphics particularly well, you will want another stat package to make nice pictures and to do additional calculations.
  7. In previous years, students from Biostatistics, Economics, Business, Education, Statistics and Epidemiology have successfully completed the course. Comfort with statistical tools such as likelihood and exposure to statistical computing will be helpful preparation for the course. A previous regression course will be extremely helpful, and at a minimum, should be concurrently registered for. Like many stat courses, the more statistics you already know, the more useful this course will be. In particular, exposure to logistic regression and random effects models will be helpful, but won't be necessary.
  8. The lectures are based on notes which will be made available on the web. The notes will be the primary reading material.
  9. A good backup textbook is Bayesian Data Analysis by Gelman, Carlin, Stern and Rubin, 2nd edition.

-- Rob Weiss

Robert Weiss                       http://rem.ph.ucla.edu/~rob/
Department of Biostatistics         e-mail: robweiss at you-cnow-la d0t edu
UCLA School of Public Health                FAX: (310) 267-2113
Los Angeles, CA 90095-1772 USA            Phone: (310) 206-9626
HOME
My links