Online self-study course 5: Introduction to GAM and GAMM.

£ 450.00


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
The course starts with a short revision of data exploration and multiple linear regression models. A non-technical introduction of generalised additive models (GAM) is provided. GAM will be used to estimate non-linear covariate effects using the mgcv package. We also provide a short revision to linear mixed-effects models generalised linear models (GLM).

Generalised additive mixed-effects models (GAMM) are applied to count data, absence-presence data, proportional data, and continuous data. We also discuss 2-dimensional smoothers (including the soap-film smoother for study areas with barriers; e.g. an island in the sea). to analyse hierarchical data (e.g. short time series from the same core or site).

GAMMs are applied on continuous, binary, proportional and count time series data using the Gaussian, Poisson, negative binomial, Bernoulli, binomial, beta, gamma and Tweedie distributions.

Detailed outline:

Module 1

  • General introduction.
  • Revision exercise on multiple linear regression.
  • Introduction to matrix notation.
  • Theory presentation on GAM.
  • Two introductory GAM exercises.

Module 2

  • GAM exercise discussing model selection and smoother interactions.
  • Short theory presentation on linear-mixed effects models.
  • One exercise using linear mixed-effects models.
  • One exercise on Gaussian additive mixed-effects models (GAM with random effects).

Module 3

  • Exercise using hierarchical GAMs (the GAM equivalent of random slope models).
  • Revision of Poisson, negative binomial and Bernoulli GLMs.
  • Two revision exercises on Poisson and negative binomial GLMs.
  • Introduction to DHARMa.
  • One exercise on negative binomial GAM.

Module 4

  • Five exercises on Poisson, negative binomial, Bernoulli and binomial GAMM.

Module 5

  • Three exercises using beta, gamma and Tweedie GAMs and GAMMs.
  • One exercise showing how to apply a GAM with 2-dimensional smoothers to capture spatial dependency.
  • We will also use the so-called soap-film smoother to deal with barriers in the study area (e.g. an island in the sea).

For a more detailed description, see:

Pre-required kmowledge
Working knowledge of R and linear regression. This is a non-technical course.