Five-Day Intensive Online Course
Marine-mammal research increasingly relies on advanced statistical tools to analyse complex ecological data: spatial surveys, detection-non-detection datasets, telemetry tracks, abundance estimates, behavioural data, and multi-level hierarchical structures. Bayesian Modelling using R-INLA (BMIN03) provides a comprehensive, practical introduction to modern Bayesian methods that are directly applicable to these challenges.
This five-day live-online course is designed for ecologists and conservation scientists who want to apply efficient Bayesian modelling to their data, using the R-INLA framework.
Spatial and spatio-temporal modelling are central to marine-mammal ecology; INLA excels at these models due to its efficient latent Gaussian approach.
Large datasets from aerial surveys, eDNA transects, passive acoustic monitoring, or satellite telemetry can be modelled more efficiently than with traditional MCMC.
INLA supports complex hierarchical structures, allowing you to combine environmental covariates, survey design effects, behavioural information, and individual variation within a unified Bayesian framework.
The core ideas behind Bayesian inference and how INLA provides fast, accurate approximations ideal for large ecological datasets.
How to build and fit generalised linear, mixed-effects, spatial, and spatio-temporal models commonly used in marine-mammal population analysis.
How to incorporate latent effects, custom priors, random fields, and structured dependencies — useful for modelling habitat use, movement, distribution, and abundance.
How to analyse line-transect and distance-sampling-style data, telemetry data, occupancy models, and hierarchical datasets with individual- or site-level effects.
How to interpret posterior outputs, generate predictions, map spatial distributions, assess uncertainty, and communicate Bayesian results effectively.
Five days, 7 hours per day, combining theory, practical coding exercises, and guided model-building.
Live online sessions with full recordings provided.
Full access to teaching materials plus 30 days of post-course support.
Marine-mammal ecologists, conservation biologists, environmental statisticians and analysts who work in R.
Researchers involved in abundance estimation, density surface modelling, telemetry studies, habitat modelling, impact assessment, or long-term monitoring.
Scientists familiar with basic statistical modelling (e.g., GLMs, mixed models) but who want to move into Bayesian approaches.
Next course date: 23–27 February 2026 (live online)
Course fee: £500
Advance your ability to model complex ecological systems and produce defensible, transparent, and uncertainty-aware analyses.
Learn more or register: https://prstats.org/course/bayesian-modelling-using-r-inla-bmin03/