This course is a continuation of AMS-206. The course will have an emphasis on statistical modeling from a Bayesian perspective. Some of the topics that will be covered include: hierarchical modeling, linear models (regression and analysis of variance), multivariate regression models and mixture models. Computational simulation-based methods such as MCMC will be studied and used for parameter estimation and prediction. The prerequisite for this class is AMS-206 (former ENGR-206). If you are taking this class you should be familiar with R and/or with any other programming language (C, C++, F77, F95, Matlab or similar) at a level that allows you to write relatively complex code to fit models with multiple parameters.
The course webpage is www.soe.ucsc.edu/classes/ams207/Spring06/ You can find a detailed schedule here (please check this site at least once per week as it will be constantly updated!)
TEXTBOOK
The required textbook is: Bayesian Data Analysis, Second Edition. A. Gelman, J.B. Carlin, H.S. Stern and D.B. Rubin. Chapman and Hall/CRC. Here is a list of other recommended books (not required):
- Markov Chain Monte Carlo, Dani Gamerman, Chapman and Hall/CRC
HOMEWORK, QUIZZES AND EXAM
The course work will be weighted as follows: Quiz (20%), Final Exam (30%) and Homework (50%).
There will be regular homework assignments. The homework will be collected and graded (or at least a sub-set of the homework problems will be graded).