27–31 October 2025

This four-day online workshop offers an applied and accessible introduction to Bayesian modelling using R-INLA. Participants will start with an intuitive overview of Bayesian inference and how it contrasts with classical approaches, setting the stage for understanding the INLA methodology and its advantages over traditional Markov Chain Monte Carlo (MCMC) methods.

We will explore the theory and application of Integrated Nested Laplace Approximation (INLA) for latent Gaussian models, progressing from linear models to GLMs, GAMs, and GLMMs. Throughout, hands-on exercises will reinforce key concepts, with a strong focus on how to effectively work with the inla model object — including extracting, summarising, and visualising posterior distributions.

This course is ideal for students, researchers, data scientists, and applied statisticians who are new to INLA — or who have used it before but seek a stronger conceptual foundation — the course guides participants through the core ideas, methods, and tools needed to build and interpret a wide range of models using Integrated Nested Laplace Approximation (INLA). No prior experience with Bayesian statistics is assumed, and the workshop is designed to be welcoming to participants from a wide range of applied backgrounds.

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

• Understand the foundations of Bayesian inference and INLA’s core principles

• Use inla() to fit linear models, GLMs, GAMs, and GLMMs

• Choose appropriate priors and interpret their effects

• Extract, summarise, and visualise posterior distributions using the INLA model object

• Apply INLA to real-world datasets and compare competing models

• Extend their skills to structured models with smooth or random effects

Daily on-line sessions,  14:00-18:00 CET; offline communication through Slack.

Day 1 – Foundations: Bayesian Inference & Introduction to INLA

• Basics of Bayesian Inference

• Theoretical overview of INLA

• Introduction to R-INLA

• Hands-on:

  • Fitting simple linear models (lm style)

  • Modifying formulas and priors

  • Using summary(), plot(), and marginal plots

Day 2 – Generalised Linear Models (GLMs) and Model Objects

• Building GLMs in INLA (logistic, Poisson, etc.)

• Working with the inla model object

• Visualising and interpreting model outputs

• Hands-on:

  • Fit and interpret GLMs

  • Transform and interpret parameters

Day 3 – GAMs and Structured Models

• Introduction to Generalised Additive Models (GAMs)

• Smoothers and structured components

• Advanced posterior summaries

• Hands-on:

  • Fit GAMs using different priors and smoothers

  • Simulate and model structured data

Day 4 – GLMMs, Model Comparison, and Extensions

• Hierarchical models and random effects

• Fitting GLMMs using INLA

• Comparing models and understanding extensions

• Final practical session:

  • Build and interpret full structured models

  • Model selection and diagnostics

  • Discussion on use cases, limitations, and resources