
ONLINE COURSE – Introduction to Bayesian modelling with INLA (BMIN02) This course will be delivered live
22 May 2023 - 26 May 2023
£500.00
Event Date
Monday, May 22nd, 2023
Course Format
This is a ‘LIVE COURSE’ – the instructor will be delivering lectures and coaching attendees through the accompanying computer practical’s via video link, a good internet connection is essential.
Course Program
TIME ZONE – UTC+2 – however all sessions will be recorded and made available allowing attendees from different time zones to follow a day behind with an additional 1/2 days support after the official course finish date (please email oliverhooker@prstatistics.com for full details or to discuss how we can accommodate you).
Course Details
The aim of the course is to introduce you to Bayesian inference using the integrated nested Laplace approximation (INLA) method and its associated R-INLA package. This course will cover the basics on the INLA methodology as well as practical modelling of different types of data.
By the end of the course participants should:
- Understand the basics of Bayesian inference.
- Understand how the INLA method works and its main differences with MCMC methods.
- Be able to fit models with the R-INLA package.
- Know how to interpret the output from model fitting.
- Be confident with the use of INLA for data analysis.
- Understand the different models that can be fit with INLA.
- Know how to define the different parts of a model with INLA.
- Be able to develop new latent effects not implemented in the R-INLA package.
- Know how to define new priors not included in the R-INLA package.
- Have the confidence to use INLA for their own projects.
Intended Audiences
Academics and post-graduate students working on projects related to data analysis and modelling and who want to add the INLA methodology for Bayesian inference to their toolbox.
Applied researchers and analysts in public, private or third-sector organizations who need the reproducibility, speed and flexibility of a command-line language such as R.
The course is designed for intermediate-to-advanced R users interested in data analysis and modelling. Ideally, they should have some background on probability, statistics and data analysis.
Venue
Venue – Delivered remotely
Course Information
Time zone – Central European Standard Time (CEST)
Availability – 20 places
Duration – 5 days
Contact hours – Approx. 35 hours
ECT’s – Equal to 3 ECT’s
Language – English
PLEASE READ – CANCELLATION POLICY: Cancellations are accepted up to 28 days before the course start date subject to a 25% cancellation fee. Cancellations later than this may be considered, contact oliverhooker@prstatistics.com. Failure to attend will result in the full cost of the course being charged. In the unfortunate event that a course is cancelled due to unforeseen circumstances a full refund of the course fees will be credited.
Teaching Format
he course will be a mixture of theoretical and practical sessions. Each concept will be first described and explained, and next there will be a time to exercise the topics using provided data sets. Participants are also very welcome to bring their own data.
Assumed quantitative knowledge
The course is designed for intermediate-to-advanced R users interested in Bayesian inference for data analysis and R beginners who have prior experience with Bayesian inference.
Assumed computer background
Attendees should already have experience with R and be familiar with data from different formats (csv, tab, etc.), create simple plots, and manipulate data frames. Furthermore, knowledge of how to fit generalized linear (mixed) models using typical R functions (such as glm and lme4) will be useful.
Equipment and software requirements
A laptop/personal computer with any operating system (Linux, Windows, MacOS) and with recent versions of R (https://cran.r-project.org) and RStudio (https://www.rstudio.com) installed; both are freely available as open-source software. You will be sent a list of packages prior to the course. It is essential that you come with all necessary software and packages already installed.
https://cran.r-project.org/
UNSURE ABOUT SUITABLILITY THEN PLEASE ASK oliverhooker@prstatistics.com
Assumed quantitative knowledge
Coming soon..
Assumed computer background
Coming soon..
Equipment and software requirements
Attendees will need to install/update R/RStudio and various additional R packages.
This can be done on Macs, Windows, and Linux.
R – https://cran.r-project.org/
RStudio – https://www.rstudio.com/products/rstudio/download/
PLEASE READ – CANCELLATION POLICY
Cancellations are accepted up to 28 days before the course start date subject to a 25% cancellation fee. Cancellations later than this may be considered, contact oliverhooker@prstatistics.com. Failure to attend will result in the full cost of the course being charged. In the unfortunate event that a course is cancelled due to unforeseen circumstances a full refund of the course fees will be credited.
Monday 22nd
Classes from 14:00 to 21:00
Introduction to the course
Key concepts related to Bayesian inference
Models with conjugate priors
Introduction to Bayesian hierarchical models
Computational methods for Bayesian inference
Introduction to the INLA methodology
Fitting generalized linear models with INLA and the R-INLA package
Understanding and manipulating the output from model fitting with R-INLA
Tuesday 23rd
Classes from 10:00 – 17:00
Fitting generalized linear mixed models with R-INLA
Types of latent effects in R-INLA
Models with i.i.d. latent effects
Fitting multilevel models with R-INLA
Models with correlated latent effects
Fitting time series models with R-INLA
Wednesday 24th
Classes from 14:00 – 21:00
Priors in R-INLA
Setting priors in R-INLA
Introduction to Penalized Complexity priors (PC-priors)
Defining new priors in R-INLA
Spatially correlated random effects
Fitting spatial models with R-INLA
Visualizing the output from spatial models and mapping
Thursday 25th
Classes from 14:00 – 21:00
Advanced features in R-INLA
Computing linear combinations of the latent effects
Fitting models with several likelihoods
Models with shared terms
Adding linear constraints to the latent effects
Implementing new latent models in R-INLA
Imputation and missing covariates in R-INLA
Friday 26th
Classes from 14:00 to 21:00
Case studies and own data.
Course Instructor

Dr Virgillio Gomez Rubio
Works at: Universdad de Castilla~La Mancha