Introduction to Generalised Linear Models using R (COURSE FULL)

Session 5 – 01:30:00 – Poisson Regression I
Introduction to Poisson regression for count data; interpreting log link coefficients.

Session 6 – 01:30:00 – Poisson Regression II
Practical applications: offsets, exposure variables, prediction and visualisation of count model outputs.

Session 7 – 01:30:00 – Residuals and Diagnostics
Checking model fit using residuals (including DHARMa); identifying patterns, influence, and outliers in GLMs.

Session 8 – 01:30:00 – Model Selection and Evaluation
Model comparison using AIC, BIC, likelihood ratio tests, and cross-validation. Principles of simplification vs. overfitting; assessing predictive performance.

Session 9 – 01:30:00 – Binary Logistic Regression I
The logit link and binary outcomes; fitting and interpreting logistic regression models.

Session 10 – 01:30:00 – Binary Logistic Regression II
Predicted probabilities, odds ratios, visualising predictions.

Session 11 – 01:30:00 – Grouped Binomial Models
Modelling grouped binary/proportion data; weights; comparing logit, probit, and cloglog links.

Session 12 – 01:30:00 – Multinomial Logistic Regression
Theory and practice of modelling unordered categorical outcomes; interpreting and visualising category probabilities.

Session 13 – 01:30:00 – Ordinal Logistic Regression
Ordered categorical outcomes; cumulative logit models; assumptions (e.g., proportional odds).

Session 14 – 01:30:00 – Gamma GLMs
Modelling skewed, strictly non-negative responses; log vs. identity links; comparing Gamma and log-normal approaches.

Session 15 – 01:30:00 – Overdispersion in GLMs
Identifying and diagnosing overdispersion in Poisson and binomial models; quasi-likelihood approaches; negative binomial extensions.

Session 16 – 01:30:00 – Full-Length Case Study
End-to-end application of GLMs: data preparation, model fitting, diagnostics, interpretation, and presentation.

Session 17 – 01:30:00 – Introduction to Bayesian GLMs
Bayesian inference in the GLM framework: priors, posteriors, uncertainty, and interpretation.

Session 18 – 01:30:00 – Bayesian GLMs in Practice
Fitting Bayesian GLMs in R (e.g., brms); posterior predictive checks; comparison with frequentist GLMs.

Session 19 – 01:30:00 – Mixed Effects GLMs (Intro to GLMMs)
Why random effects are useful; fitting random intercepts with lme4::glmer(); interpreting group-level effects.

Session 20 – 01:30:00 – Extensions and Wrap-Up
Random slopes, challenges with convergence and overfitting; best practices and pitfalls.