BTRY 4940/6940 Spring 2009

"Likelihood and Bayesian Statistical Methods"

Instructor: Jim Booth, Biological Statistics and Computational Biology
Office: 1178 Comstock

Time: TR 8:40-9:55am, 106B Comstock

Prerequisites: BTRY 4070/6070 or BTRY 4080

Note: This course can be used as an advanced elective for the Biometry
and Statistics major.

Credit hours: 3

Grade: s/u or letter

Grading: Homework 70%, Prelim 30%

Brief Description:

This course focuses on the application of the likelihood-based,
empirical Bayes and fully Bayesian approaches to statistical modeling
and inference. Basic concepts are introduced using simple,
single-parameter models. More advanced models covered include
multinomial, hierarchical, regression and mixture models. Applications
from a variety of areas are considered including sociology, medicine,
biology and genetics. Computational methods for model fitting and
inference, such as the EM algorithm and Monte Carlo simulation, are
discussed and implemented using the R and BUGS statistical packages.

Text: Gelman, Carlin, Stern and Rubin (2004), "Bayesian Data Analysis"
2nd Edition. Chapman and Hall/CRC. ISBN: 1-58488-388-X.

Software:

R (2008), A Language and Environment for Statistical Computing. R
Development Core Team. R Foundation for Statistical Computing, Vienna,
Austria. ISBN: 3-900051-07-0, http://www.R-project.org.

BUGS (Bayesian inference Using Gibbs Sampling)
http://www.mrc-bsu.cam.ac.uk/bugs/

OpenBugs http://mathstat.helsinki.fi/openbugs/Home.html