STAT 491: Intro to Bayesian Stats
Course Resources:
Course Schedule:
Week | Content |
Week 1: Jan 11 |
Thurs. Course Overview, Quiz 1, Bayesian Thought Experiment. (PDF) (R Markdown) |
Week 2: Jan 16 Week 2: Jan 18 |
Tues. Ch.2: Credibility, Models, and Parameters (PDF) (R Markdown) Thurs. HW1 due (HTML) (R Markdown), Quiz 2 Ch.4: Probability (PDF) (R Markdown) |
Week 3: Jan 23 Week 3: Jan 25 |
Tues. Ch. 4: Probability Thurs. Quiz 3 Ch. 4: Probability |
Week 4: Jan 30 Week 4: Feb 1 |
Tues. HW2 due (HTML) (R Markdown), Ch. 4: Probability, Part 2 (PDF) (R Markdown) Thurs. Quiz 4, Lab 1 due (HTML) (R Markdown) Ch. 4: Probability |
Week 5: Feb 6
Week 5: Feb 8 |
Tues. HW3 due (HTML) (R Markdown), Lab 2 due (HTML) (R Markdown) Ch. 5: Bayes Rule (PDF) (R Markdown) Thurs. Quiz 5 Ch. 5: Bayes Rule |
Week 6: Feb 13
Week 6: Feb 15 |
Tues. Quiz 6 Ch. 6: Binomial Probability (PDF) (R Markdown) (Occupancy Model Framework) Thurs. HW4 due (HTML) (R Markdown), Lab 3 due (HTML) (R Markdown) Ch. 6: Binomial Probability |
Week 7: Feb 20
Week 7: Feb 22 |
Tues. Quiz 7 Ch. 7: MCMC (PDF) (R Markdown) Thurs. HW5 due (HTML) (R Markdown), Lab 4 due (HTML) (R Markdown) Ch. 7: MCMC/JAGS Project Overview (PDF) |
Week 8: Feb 27
Week 8: Mar 1 |
Tues. Quiz 8 Ch. 16 Normal Distribution (PDF) (R Markdown) Thurs. Lab 5 due (HTML) (R Markdown) Ch. 16 Normal Distribution with JAGS |
Week 9: Mar 6
Week 9: Mar 8 |
Tues. HW6 due (HTML) (R Markdown), Lab 6 due (HTML) (R Markdown) (KEY) Exam 1 Thurs. No Class: Take Home Exam Due Saturday March 10 (PDF) (R Markdown) |
Week 10: Mar 13 Week 10: Mar 15 |
Tues. No Class - Spring Break Thurs. No Class - Spring Break |
Week 11: Mar 20
Week 11: Mar 22 |
Tues. Project Proposal due Two sampling testing (Ch. 16.3, Ch.11, Ch.12) (PDF) (R Markdown) Thurs. Two sampling testing (Ch. 16.3, Ch.11, Ch.12) |
Week 12: Mar 27 Week 12: Mar 29 |
Tues. Two sampling testing (Ch. 16.3, Ch.11, Ch.12) / Ch. 9: Hierarchical Models Thurs. HW 7 due (HTML) (R Markdown), Lab 7 due (HTML) (R Markdown) Ch. 9: Hierarchical Models (PDF) (R Markdown) |
Week 13: April 3 Week 13: April 5 |
Tues. Bayesian Regression (Ch: 15, 17) (PDF) (R Markdown) Thurs. Lab 8 due (HTML) (R Markdown) Bayesian Regression (Ch: 15, 17) |
Week 14: April 10 Week 14: April 12 |
Tues. Quiz 8 (online D2L), HW 8 due (HTML) (R Markdown) Bayesian Regression (Ch: 18, 19) (PDF) (R Markdown) Thurs. Intermediate Project Summary due Bayesian Regression (Ch: 18, 19) |
Week 15: April 17 Week 15: April 19 |
Tues. HW 9 due (HTML) (R Markdown), Lab 9 due (HTML) (R Markdown) Ch. 21: Binary Regression (PDF) (R Markdown) Thurs. Quiz 9 (online D2L), Ch. 24: Count Regression |
Week 16: April 24 Week 15: April 26 |
Tues. HW 10 due (HTML) (R Markdown), Lab 10 due (HTML) (R Markdown) Take Home Exam Assigned Thurs. Exam 2 (in class) Take home exam (PDF) (R Markdown) due Sunday April 29 at 8 AM |
Finals Week: April 30 |
Mon. 2:00 - 3:50 Project Presentations Wed. 8 AM Written Summary Due |
Course Overview:
- Meeting Time: Tuesday and Thursday - 9:25 - 10:40
- Classroom: Barnard Hall 126
- Office Hours: Tues/Thurs 11 - 12
Course Description
This course will introduce the basic ideas of Bayesian statistics and provide a contrast with techniques for classical inference. The course focuses on both the philosophical foundations and practical implementation of Bayesian methods.
Prerequisites
MATH 172 (Calculus II) or equivalent and STAT 217 or STAT 411. While not required experience with R will be useful.
Learning Outcomes
At the completion of this course, students will be able to:
- Describe fundamental differences between Bayesian and classical inference,
- Select priors, write likelihoods, derive posterior distributions, and verify model and prior assumptions,
- Use computer code, including R and JAGS, to sample from posterior distributions, and
- Make inferences from posterior distributions.
Textbook:
- Doing Bayesian Data Analysis, Second Edition , by John Kruschke.
Course Evaluation:
-
Quizzes: 10% of final grade:
-
There is no formal attendance policy, but there will be periodic quizzes.
-
-
Homework: 20% of final grade:
- Homework problems will be assigned every week. Students are allowed and encouraged to work with classmates on homework assignments, but each student is required to complete their own homework.
-
Labs: 10% of final grade:
- The course will periodically have labs, which will be organized group activities to be completed in class.
-
Exam 1 & Exam 2, 15% (each) of final grade
- The exams will be largely conceptual including some short mathematical derivations. The take home portions will focus on data analysis and implementation of Bayesian methods.
-
Project 30% of final grade
- The final project will focus on the complete data analysis cycle using relevant data: prior and model specification, posterior computation, model checking, and inference in a Bayesian context. There will be preliminary deadlines as the course progresses.