Level: Professional (P)
 

This intensive 2-day course provides a comprehensive introduction to modern Bayesian statistical methods with a strong emphasis on practical workflow and computational implementation. Moving beyond traditional theory-focused instruction, this course teaches participants how to build, fit, check, and improve statistical models estimated with Stan through brms, a modelling interface for the statistical programming language R.
 
The course bridges the gap between Bayesian theory and practice, guiding participants through the complete modelling cycle – from initial model specification through computational fitting, diagnostic checking, model comparison, and refinement. This will be achieved by working through a number of real-world case studies spanning diverse applications such as clinical trials, ecology, education, and time-series analysis, participants will develop practical skills for applying Bayesian methods to their own research problems.
 

Learning Outcomes

By the end of this course, participants will be able to:

• Understand the principles of Bayesian inference and how they translate into practical statistical workflow
• Build mixed-effects/hierarchical statistical models appropriate for complex data structures
• Implement Bayesian models using modern computational tools
• Diagnose computational problems and apply appropriate solutions
• Validate models through posterior predictive checking
• Compare competing models using cross-validation and other principled methods
• Make predictions and causal inferences from fitted models
• Apply iterative model development strategies to real problems

 

Topics Covered

 

• Introduction to Bayesian theory: Priors, likelihood, and posterior
• Visualising, choosing and specifying priors
• Choosing the right likelihood
• Visualizing and checking fitted models
• Visualising and analysing posteriors
• Statistical inference
• Diagnosing and fixing model problems

 

Target Audience
 

Anyone with some statistics training who is aware of the advantages of Bayesian modelling could benefit from attending. Fields where this may be most popular are: insurance, political pollsters, finance, marketing, healthcare, education research, psychology, econometrics.
 

Assumed Knowledge

Attendees should be comfortable with using R and should be able to estimate regression models in R. They should understand probability distributions and basic regression models, though this can be intuitive and doesn’t have to be mathematically rigorous. Knowledge of the tidyverse is beneficial, but not necessary (see: https://r4ds.hadley.nz/). Attendees do not have to have used brms or Stan before (but they should come with it loaded on a laptop, and should check it is working properly – see mc-stan.org)

Henrik Singmann

Henrik Singmann is associate professor of mathematical and quantitative psychology and the director of the UCL Centre for Behavioural Data Science (https://www.ucl.ac.uk/brain-sciences/pals/research/behavioural-data-science). He has a long history of teaching statistics to student and researchers at various levels with excellent teaching evaluations. He is also the developer of a number of well-known R packages such as afex and bridgesampling.

Fees		Registration before  15 August 2026	Registration on/after 15 August 2026
Non Member  RSS Fellow  RSS CStat/Gradstat/Data Analyst  also MIS & FIS		£795.00 +VAT  £675.00 +VAT £635.00 +VAT	£835.00 +VAT £710.00 +VAT £665.00 +VAT
Group discounts are also available*: 3-5 people 6-8 people 9+ people *Discount only applies to non-member price		10% discount 15% discount 20% discount