Principal speaker
Associate Professor Sama Low-Choy
Logistic regression provides a great introduction to generalized linear models (GLMs); it is in fact a GLM with a binomial sampling model, so is sometimes referred to as binomial regression. We will explore both traditional (Frequentist) as well as Bayesian approaches to modelling how a binary response (also referred to as a dependent variable or an outcome) may relate to several explanatory variables (also known as independent variables or predictors).
Probing Predictions: We examine how you can alternatively use logistic regression in a data analytics (machine learning) kind of way that focuses on predictions.
Format: These 'Stat-a-along' sessions are designed so that you can replay the session slowly, whilst following similar steps with your own data.
Intended audience: Those with no experience in regression, wishing to understand the model from the outset. Those with some practical experience running these models, wishing to go to the next level, and understand the meaning of estimates.