About the course | Intended audience | Prerequisites | Content details
About the course
An introductory course on Bayesian inference for researchers with no previous experience of Bayesian statistics.
This course introduces the core ideas behind Bayesian inference and demonstrates how Bayesian methods can be applied to real datasets using R and the STAN framework. The emphasis is on developing practical understanding and interpretation skills rather than mathematical derivation.
Participants will learn the language and concepts of Bayesian statistics, how Bayesian approaches compare with classical statistical methods, and how to fit and interpret simple Bayesian models.
Topics include prior and posterior distributions, likelihoods, uncertainty, credible intervals, model interpretation, and practical Bayesian modelling using STAN.
By the end of the course, participants should be able to:
- understand the key concepts and terminology used in Bayesian inference
- explain how Bayesian methods differ from classical statistical approaches
- interpret posterior distributions and credible intervals
- fit and run simple Bayesian models using STAN
- critically assess outputs from Bayesian analyses
The course combines short lectures with practical examples and hands-on exercises.
Back to top Intended audience
This course is suitable for:
- researchers and postgraduate students interested in learning Bayesian approaches to data analysis
- participants with experience using standard statistical methods who want to understand Bayesian alternatives
- researchers who want a practical introduction to Bayesian modelling in R and STAN
- participants looking to build confidence interpreting Bayesian outputs in research papers and analyses
No previous experience with Bayesian statistics is required.
Prerequisites
Participants should have coding skills broadly equivalent to an introductory course in R.
A working knowledge of classical statistical concepts equivalent to a core statistics course is also required. In particular, participants should already be familiar with ideas such as hypothesis testing, regression, statistical models, and uncertainty.
This course is designed as an introduction to Bayesian inference itself and does not assume prior Bayesian knowledge.
Content details
The course is delivered over two half-day sessions:
- Session 1 — The language and key ideas of Bayesian inference
Introduces the conceptual foundations of Bayesian statistics, including probability as uncertainty, prior distributions, likelihoods, posterior distributions, and Bayesian updating. Participants learn the key terminology used in Bayesian analysis and how Bayesian approaches differ conceptually from classical statistical inference. The session also explores how uncertainty is represented and interpreted in Bayesian models, including the meaning of credible intervals and posterior probabilities.
- Session 2 — Using STAN to perform Bayesian inference
Introduces practical Bayesian modelling using STAN within R. Participants learn how to specify and run simple Bayesian models, inspect posterior outputs, interpret parameter estimates, and assess model behaviour. The emphasis is on understanding the practical workflow involved in Bayesian data analysis and developing confidence interpreting Bayesian model outputs in applied research contexts.
The course also discusses the strengths and limitations of Bayesian approaches, common interpretation mistakes, and situations where Bayesian methods may provide advantages over classical statistical techniques.