Course format:
- Self-study course.
- On-demand access to all video content online within a 12-month period.
- Daily interaction on the Discussion Board for detailed questions.
- Live chat for quick queries.
- Course fee includes a 1-hour video chat with instructors for personalized questions and data assistance.
Course content
This course provides a practical introduction to Generalised Additive Models (GAMs) and Generalised Additive Mixed Models (GAMMs) in R using the mgcv package. We start with a short revision of data exploration, multiple linear regression, and linear mixed-effects models before moving on to modelling non-linear relationships using smoothers. Participants work through a wide range of applied ecological examples, including whale acoustics, lizard abundance, fisheries CPUE, elephant poaching, barn owl behaviour, and grassland biodiversity.
The course covers Gaussian, Poisson, negative binomial, Bernoulli/binomial, beta, gamma, and Tweedie GAMs and GAMMs, as well as hierarchical mixed-effects structures, hierarchical GAMs, and random effects. Participants will learn how to fit, interpret, visualise, and validate models using tools such as DHARMa, and how to deal with count, binary, proportional, and continuous data. We also discuss the important distinction between conditional, empirical marginal, and population marginal fitted values in mixed-effects GAMMs.
The course is highly applied in nature and focuses on practical modelling skills rather than mathematical derivations. All analyses are conducted in R using real datasets, with a strong emphasis on interpretation, model validation, smoother behaviour, and ecological interpretation of model output.
For a more detailed description, see our course website:
https://www.courses.highstat.com/index.php/8-introduction-to-gam-and-gamm-using-frequentist-tools
Pre-required kmowledge
This course assumes familiarity with R, regression models, GLMs, and common distributions such as the binomial, Poisson, negative binomial, gamma, beta, and Tweedie distributions. Participants without this background are strongly encouraged to first attend our introductory course: Data Exploration, Regression, GLM and GAM.