Skip to main content

Module

MAS8405 : Bayesian Data Analysis

  • Offered for Year: 2022/23
  • Module Leader(s): Professor Chris Oates
  • Owning School: Mathematics, Statistics and Physics
  • Teaching Location: Newcastle City Campus
Semesters
Semester 2 Credit Value: 10
ECTS Credits: 5.0

Aims

Bayesian analysis provides an ideal approach for synthesizing information from different sources in a coherent way. In recent years, Bayesian principles have been adopted across a wide variety of areas within science, industry, machine learning, and AI. This has been made possible by the development of powerful algorithms for computing posterior distributions, including for sophisticated statistical models. This module starts with an introduction to the principles of Bayesian analysis before moving on to more complex models and computational algorithms relevant to practical data analysis.

Specifically, the module aims to equip students with the following knowledge and skills:
-       To gain an understanding of the principles and the practical applications of the Bayesian approach to data analysis.
-       To gain knowledge of modern computational methods for Bayesian analysis and their application to industrial problems.

Outline Of Syllabus

-       Principles of Bayesian inference
-       Conjugate priors
-       Computational methods, such as Markov chain Monte Carlo (MCMC)
-       Applications, such as: linear models, generalized linear models, mixture models, hidden Markov models, dynamic linear models, Gaussian process regression

Teaching Methods

Teaching Activities
Category Activity Number Length Student Hours Comment
Structured Guided LearningLecture materials61:309:00Non-synchronous online pre-recorded lectures and set reading
Guided Independent StudyAssessment preparation and completion214:0028:00Formative and summative reports
Scheduled Learning And Teaching ActivitiesPractical62:0012:00Present in person structured synchronous practical
Guided Independent StudyProject work129:3029:30Main project
Scheduled Learning And Teaching ActivitiesDrop-in/surgery42:008:00Present in person drop-in
Guided Independent StudyIndependent study91:3013:30Lecture follow-up/background reading
Total100:00
Teaching Rationale And Relationship

Pre-recorded lectures and set reading are used for the delivery of theory and explanation of methods, illustrated with examples. Practicals are used both for solution of problems and to give insight into the ideas/methods studied. There are two present-in-person practical sessions per week to ensure rapid feedback on understanding. Scheduled present-in-person drop-ins provides opportunity to ask questions and receive immediate feedback. Students unable to attend PiP will be able to complete the practical work at home and will be able to receive immediate feedback through joining the drop-ins virtually.

Alternatives as described will be offered to students unable to be present-in-person due to the prevailing C-19 circumstances.

Student’s should consult their individual timetable for up-to-date delivery information.

Assessment Methods

The format of resits will be determined by the Board of Examiners

Other Assessment
Description Semester When Set Percentage Comment
Report2M100A compulsory report allowing students to demonstrate skills and knowledge gained during the course.
Formative Assessments
Description Semester When Set Comment
Practical/lab report2MA compulsory report allowing students to develop problem solving techniques & to practise the methods learnt and to assess progress
Assessment Rationale And Relationship

A compulsory formative practical report allows the students to develop their problem-solving techniques, to practise the methods learnt in the module, to assess their progress and to receive feedback, before the summative assessments.

The oral presentation encourages students to focus on interpretation of statistical results, builds their skills in the presentation of statistical concepts, and provides opportunity for feedback.

In a foundational subject like the Mathematical Sciences, there is research evidence to suggest that continual consolidation of learning is essential and the fewer pieces of assessment there are, the more difficult it is to facilitate this. On this module, it is particularly important that the material on the earlier summative assessment is fully consolidated, before the later assessment is attempted.

Reading Lists

Timetable