STAT638: Applied Bayesian Methods

Author

Shao-Ting Chiu (stchiu@email.tamu.edu)

Published

December 1, 2022

Preface

This is the lecture notes for STAT638 Applied Bayesian Methods by Dr. Matthias Katzfuss.

Course details

Course Number: STAT 638
Course Title: Introduction to Applied Bayesian Methods
Time: TuTh 2:20 - 3:35 (Central time)
Location: Blocker 411
Textbook: Hoff, (Links to an external site.)A First Course in Bayesian Statistical Methods (Links to an external site.) (electronic version available through TAMU library)
Prerequisite: STAT 630 or STAT 650. (Also, familiarity with R or other statistical software, training in vector/matrix algebra, and some exposure to linear regression will be very helpful.)

Schedule

Introduction (Week 1)
Conditional distributions and Bayes rule (Weeks 1-2)
One-parameter models (Weeks 3-4)
Monte Carlo approximation (Weeks 5-6)
The normal model (Weeks 6-8)
Gibbs sampling (Weeks 8-9)
The multivariate normal model (Weeks 9-11)
Group comparisons and hierarchical modeling (Weeks 11-12)
Linear regression (Weeks 12-13)
Markov chain Monte Carlo (Weeks 13-14)
Mixed effects models (Week 14)

Programming

Majorly use R
Homework will be R
Using Python is acceptable

Exam

Exam 1: October 18th
Exam 2: December 1st

Homework

No late homework is acceptable

Solution manual

https://github.com/jayelm/hoff-bayesian-statistics

Resources

Notes and solutions of Hoff book. [Github]

# Preface {.unnumbered}

This is the lecture notes for STAT638 Applied Bayesian Methods by [Dr. Matthias Katzfuss](https://scholars.library.tamu.edu/vivo/display/ne2600027/Persons/View%20All).


## Course details

- Course Number: STAT 638
- Course Title: Introduction to Applied Bayesian Methods
- Time: TuTh 2:20 - 3:35 (Central time)
- Location:  Blocker 411
- Textbook: Hoff,  (Links to an external site.)A First Course in Bayesian Statistical Methods (Links to an external site.) (electronic version available through TAMU library)
- Prerequisite: STAT 630 or STAT 650. (Also, familiarity with R or other statistical software, training in vector/matrix algebra, and some exposure to linear regression will be very helpful.)



## Schedule

1. Introduction (Week 1)
1. Conditional distributions and Bayes rule (Weeks 1-2)
1. One-parameter models (Weeks 3-4)
1. Monte Carlo approximation (Weeks 5-6)
1. The normal model (Weeks 6-8)
1. Gibbs sampling (Weeks 8-9)
1. The multivariate normal model (Weeks 9-11)
1. Group comparisons and hierarchical modeling (Weeks 11-12)
1. Linear regression (Weeks 12-13)
1. Markov chain Monte Carlo (Weeks 13-14)
1. Mixed effects models (Week 14)


## Programming

1. Majorly use R
2. Homework will be R
3. Using Python is acceptable


## Exam

1. Exam 1: October 18th
2. Exam 2: December 1st


## Homework

- *No late homework is acceptable*

## Solution manual

- [https://github.com/jayelm/hoff-bayesian-statistics](https://github.com/jayelm/hoff-bayesian-statistics)


## Resources

- Notes and solutions of Hoff book. [[Github]](https://github.com/jayelm/hoff-bayesian-statistics)