computer code
exercises
data
labs

## Bayesian Statistical Methods

Lectures MWF, 9:30-10:20, EEB 054
Lab Th, 12:30-1:20, Communications B027
Instructor
• Peter Hoff
• Office Hours: Tue 9:30-10:30, Wed 10:30-11:30 or by appointment.
• pdhoff at uw dot edu
Teaching Assistant
• Alex Volfovsky
• Office Hour: TBA
• volf at uw dot edu
Please include "564" (without quotes) in any emails to allow for appropriate filtering.
Texts

Assignments
• Week 10: Read Chapter 10 and do the final homework.
• Week 9: Read Chapter 9 and do exercises 9.2(a) and all of 9.3, to be turned in Friday June 3.
• Week 8: Read Chapter 8 and do exercises 8.1 and 8.3, to be turned in Friday May 27.
• Week 7: Read Chapter 7 and do exercises 7.4 and 7.6. For 7.4 part d, only do d.iii to be turned in Friday May 20.
• Week 6: Read Chapter 6 and do these exercises to be turned in Friday May 13.
• Week 5: Read Chapter 5 and do exercises 4.8 and 5.1 and 5.2 to be turned in Friday May 6.
• Week 4: Read Chapter 4 and do exercises 3.3 part (a), 4.1 and 4.2, to be turned in Wednesday April 27. For 4.2 (b) use n0 values between 1 and 10. For 4.2 (c2) you only have to repeat part 4.2 (a) using the predictive distribution.
• Week 3: Read Chapter 3 and and do exercises 3.2, 3.7 and 3.9, to be turned in Wednesday April 20.
• Week 2:
• Week 1: Read Chapter 1 and start Chapter 2 of the text.

Evaluation
• Eight or nine homework assignments
• Two or three in-class quizzes, which will be announced in advance
Each quiz will be given the same weight as a homework. There will be the opportu nity to correct quiz mistakes for partial credit.

Course Outline

1. Concepts of randomness and probability
2. Review of probability calculus
3. Inference for binomial, Poisson and normal distributions
4. Hierarchical models
5. Multivariate normal distribution
6. Linear regression models
7. Generalized linear models
8. Generalized linear mixed-effects models
Additionally, we will cover the basics of Monte-Carlo integration and Markov chain Monte Carlo (Gibbs sampling and the Metropolis-Hastings algorithm). This material will be covered concurrently with the material listed above.

Late policy
Each turned in item receives an initial grade of x, then the actual grade is y=x exp(-d/8), where d is the number of days (including weekends) after the due date I receive the work. Everyone receives one grace day to be applied to one homework for the entire quarter.