PS931-15 Bayesian Approaches in Behavioural Science
Introductory description
Bayesian approaches have made important contributions to Behavioural Science, both as statistical models for empirical data, and as cognitive models of how people perform tasks. As statistical models, Bayesian methods are particularly important for establishing the absence of an effect, which is difficult for standard statistical methods to do. As cognitive models, Bayesian methods prescribe what an agent should do in a task, as as such provide important benchmarks against which to compare human behaviour. In both domains, approximations play an important role: allowing the practical use of complex statistical models, and providing a route to explain deviations of human and animal behaviour from the Bayesian ideal.
Module aims
The purpose of the module is to introduce Bayesian approaches to statistics and modelling of behaviour, and the approximations that make them work in practice.
Outline syllabus
This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.
The module will introduce Bayesian statistics and Bayesian models of behaviour. In the lectures on Bayesian statistics, topics such as mixed models, estimation vs. testing, approximation, and choosing priors will be covered. In the lectures on Bayesian models of behaviour, topics such as the evidence for and against these models, the role of approximations, evolution and animal behaviour will be covered.
Learning outcomes
By the end of the module, students should be able to:
- Apply common Bayesian statistical methods to analyse empirical data in behavioural science.
- Gain familiarity with Bayesian approaches to modelling cognition and behaviour.
- Understand the evidence against Bayesian approaches to modelling cognition and behaviour, and the extent to which approximations can account for this evidence.
- Understand the logic of Bayesian statistics and the necessity of approximation methods.
Indicative reading list
View reading list on Talis Aspire
Interdisciplinary
Incorporates elements of Psychology, Economics, Business, and Statistics
Subject specific skills
Understand the logic of Bayesian statistics and the necessity of approximation methods.
Apply common Bayesian statistical methods to analyse empirical data in behavioural science.
Transferable skills
Understand the logic of Bayesian statistics and the necessity of approximation methods.
Applying common Bayesian statistical methods to analyse empirical data generally.
Study time
| Type | Required |
|---|---|
| Lectures | 9 sessions of 2 hours (20%) |
| Seminars | 4 sessions of 2 hours (9%) |
| Private study | 62 hours (70%) |
| Total | 88 hours |
Private study description
Reviewing of lecture materials and reading of background literature
Costs
No further costs have been identified for this module.
You do not need to pass all assessment components to pass the module.
Assessment group A1
| Weighting | Study time | Eligible for self-certification | |
|---|---|---|---|
| Bayesian data analysis assignment | 42% | 25 hours | Yes (extension) |
|
Using provided data, students will perform Bayesian data analysis and write up the results |
|||
| Essay on a choice of questions about Bayesian models of cognition | 42% | 25 hours | Yes (extension) |
|
Students will answer one question from a set of questions on Bayesian models of cognition and behaviour |
|||
| Weekly MCQs | 16% | 12 hours | No |
|
Weekly multiple-choice questions to assess the student learning |
|||
Feedback on assessment
Individual written feedback will be provided during the term for the Bayesian data analysis assignment, and individual written feedback will be provided after the term for the Essay. Students will be told the correct answers to the MCQs after each quiz closes, and the quiz answers will be discussed during the lectures.
Courses
This module is Core optional for:
- Year 1 of TPSS-C803 Postgraduate Taught Behavioural and Data Science
- Year 1 of TPSS-C8P7 Postgraduate Taught Behavioural and Economic Science (Science Track)
This module is Optional for:
- Year 1 of TPSS-C8P7 Postgraduate Taught Behavioural and Economic Science (Science Track)
- Year 1 of TECS-C8P8 Postgraduate Taught Behavioural and Economics Science (Economics Track)
- Year 1 of TECA-L1P6 Postgraduate Taught Economics
- Year 1 of TMAA-G1PF Postgraduate Taught Mathematics of Systems
This module is Core option list A for:
- Year 1 of TPSS-C803 Postgraduate Taught Behavioural and Data Science