STAT41070 Bayesian Data Analysis

Academic Year 2023/2024

This module will equip students with the knowledge required to practically use standard statistical data analysis tools within a Bayesian framework. The module will focus on data analysis examples, using modern Bayesian statistical computing tools, e.g. R, Nimble, or Stan.

Students will learn how to implement standard statistical models such as linear regression, Poisson regression, logistic regression and Gaussian processes in a Bayesian framework. Application of these methods to high-dimensional, complex data will be considered, e.g. shrinkage priors in the context of regression or handling of missing data.

Students will use modern computational tools such as the Gibbs sampler and the Metropolis- Hastings algorithm. Through implementing these models, aspects such as convergence diagnostics, model checking and posterior predictive checks will be considered. Throughout, real data analysis examples will be used to motivate and illustrate the methods and theory of practical Bayesian data analysis.

Show/hide contentOpenClose All

Curricular information is subject to change

Learning Outcomes:

On completion of this module students will be equipped with the knowledge of how to apply standard statistical analysis methods in a Bayesian framework using modern statistical computational tools.

Indicative Module Content:

Draft syllabus:
1. Recap of Bayesian analysis
2. Bayesian regression analysis
a. linear regression
b. hierarchical linear models
c. generalized linear models
3. Computational tools
4. Nonparametric models
5. Handling missing data

Student Effort Hours: 
Student Effort Type Hours
Lectures

24
Computer Aided Lab

11
Specified Learning Activities

32
Autonomous Student Learning

48
Total

115
Approaches to Teaching and Learning:
Lectures, tutorials, enquiry and problem-based learning.
 
Requirements, Exclusions and Recommendations
Learning Requirements:

Students must have knowledge equivalent to that achieved through successfully completing STAT20180 Bayesian Analysis, STAT20100 Statistical Inference, STAT20240 Predictive Analytics and STAT30250 Advanced Predictive Analytics.


Module Requisites and Incompatibles
Incompatibles:
STAT40950 - Adv Bayesian Analysis (online)


 
Assessment Strategy  
Description Timing Open Book Exam Component Scale Must Pass Component % of Final Grade
Examination: Written exam. 2 hour End of Trimester Exam No Alternative linear conversion grade scale 40% No

60
Assignment: Assessment assigned and submitted during the trimester. Will assess theory and practical knowledge. Throughout the Trimester n/a Alternative linear conversion grade scale 40% No

40

Carry forward of passed components
No
 
Resit In Terminal Exam
Spring Yes - 2 Hour
Please see Student Jargon Buster for more information about remediation types and timing. 
Feedback Strategy/Strategies

• Feedback individually to students, post-assessment

How will my Feedback be Delivered?

Not yet recorded.

Bayesian Data Analysis, by Andrew Gelman, John Carlin, Hal Stern, David Dunson, Aki Vehtari, and Donald Rubin.

Bayes Rules! An Introduction to Applied Bayesian Modeling, by Alicia A. Johnson, Miles Q. Ott, Mine Dogucu.

An Introduction to Bayesian Inference, Methods and Computation, by Nick Heard.
Timetabling information is displayed only for guidance purposes, relates to the current Academic Year only and is subject to change.
 
Autumn
      
Lecture Offering 1 Week(s) - Autumn: All Weeks Mon 14:00 - 14:50
Laboratory Offering 1 Week(s) - 3, 4, 5, 6, 7, 8, 9, 10, 11, 12 Tues 11:00 - 11:50
Lecture Offering 1 Week(s) - Autumn: All Weeks Wed 14:00 - 14:50
Laboratory Offering 1 Week(s) - 2 Tues 11:00 - 11:50
Autumn