Cost and booking

This is a paid course costing £300. Please register your interest via EventBrite, and we will be in touch with details of how to book, and bursaries for PhD students.

Overview

Longitudinal data are essential in a number of research fields as they enable analysts to understand individual-level change in time and the occurrence of events, and help improve our causal understanding of the world.

Led by Dr Alexandru Cernat, we will cover three fundamental frameworks for analysing longitudinal data:

• multilevel modelling,
• structural equation modelling (SEM),
• event history analysis.

We will consider how to:

• clean and visualize longitudinal data in an efficient way using R
• use the main statistical models to analyse data.

By the end of the course you will be able to choose a design, a plausible model and an appropriate method of analysis for a range of research questions.

Prerequisites

• Good knowledge of regression modelling
• Basic knowledge of R, or good programming experience with a different statistical software

Course timetable

Monday 21 June

• Morning: Data cleaning using R
• Afternoon: Visualization using R

Tuesday 22 June

• Morning: Intro to SEM and auto-regressive models
• Afternoon: Cross-lagged models

Wednesday 23 June

• Morning: Intro to multilevel model for change
• Afternoon: Advanced multilevel model for change

Thursday 24 June

• Morning: Intro to latent growth models
• Afternoon: Advanced latent growth model

Friday 25 June

• Morning: Survival analysis
• Afternoon: Cox regression

Recommended reading

Singer, J., & Willett, J. (2003). Applied longitudinal data analysis: modelling change and event occurrence. Oxford University Press. (available online)

Long, J. D. (2011). Longitudinal Data Analysis for the Behavioral Sciences Using R. SAGE.

Newsom, J. T. (2015). Longitudinal Structural Equation Modeling: A Comprehensive Introduction. Routledge.