Longitudinal analysis
Analysing repeated measurements collected over time — quantifying change in a response and the factors that drive it, with a focus on mixed-effects models.
What this course covers
Register interest
This course explores repeated measurements collected over time for study subjects. Participants learn to quantify changes in a response variable and identify the factors influencing those changes, with an emphasis on mixed-effects modelling and practical applications in medical research.
Lectures run in the morning and a computer practical in the afternoon. The primary software is Stata (version 14+), with full R solutions provided.
Full course title: Longitudinal analysis: An introduction to concepts, methods & software
At a glance
What you'll learn
Describing longitudinal data
Basic concepts, notation, and approaches for describing longitudinal data, with a review of linear regression.
Linear mixed-effects models
Random-intercept and random-intercept-slope models, and strategies for building them.
Predictions
Post-estimation and model-based predictions — both population-level and subject-specific.
Audience & prerequisites
Who it's for
Epidemiologists, statisticians, physicians, public health specialists or anyone with an interest in methods for studying longitudinal data.
Prerequisites
Basic knowledge of the fundamentals of epidemiology and biostatistics, and comfort fitting and interpreting statistical models in epidemiology (e.g. linear, logistic, Poisson, or Cox regression). Prior basic knowledge of Stata is assumed.