Longitudinal Data Analysis is a very popular statistical method in a range of fields including medicine, natural resource management, business and economics.

As well as allowing a researcher to elicit the changes in a subject (person, business, etc) over time, longitudinal data is also exceedingly powerful as it allows the within-subject and between-subject variance to be estimated independently (generally allowing the parameters in the statistical model to be estimated with a much tighter accuracy than traditional models).

This course provides an overview of Longitudinal Data Analysis. As well as the statistical theory, an overview of the many applications and capabilities of LDA is given. The course is not particularly mathematical, but instead places emphasis on the fundamental concepts of LDA and how it is used by applied researchers.

The workshop will focus on linear mixed effects models, however we will also go through generalized linear mixed effects models and any new material a participant will need to understand in order to successfully use generalized LME’s. There will be exercises using both types of models.

The computer exercises for this workshop will be conducted in Stata. Stata has been chosen as it provides both basic and advanced functionality for conducting longitudinal data analyses. A full set of exercises and solutions in Stata will be provided in this workshop, where they include the Stata syntax required to perform each individual exercise. In addition the workshop presenter will demonstrate how to use Stata for the first exercise in each session prior to workshop participants individually working though the exercises for that session.

General aims of the course are for students to develop a readiness for using LDA software and to develop the requisite knowledge for applying LDA methods and models in an intelligent way. Note that participants may be invited to briefly present their own research on the last day of class. This exercise, along with the formal lecture material, might help participants to chart a direction forward in their study and application of LDA.

Day 1

• Revision of linear, logistic and Poisson regression

Day 2 and Day 3

• Mixed effects models

• Fixed and random effects

• Random intercept and random slope

• Goodness of fit measures (including Likelihood and AIC)

• Model choice

• Having more than one clustering level

• Generalized Estimating Equations

Day 4

• Survival or time-to-event analysis

• Kaplan-Meier curves

• Survival and hazard functions

• Missing Data

• Multiple Imputation

• Heckmann Selection models

Day 5

• Regression Diagnostics

• Linear

• Normality

• Constant Variance

• Outliers

• Collinearity

Approximately half of the time during this course will be spent in PowerPoint presentations, and half of the time in computer demonstrations and self-paced computer exercises (conducted in Stata).

It would be beneficial if students have had some previous exposure to regression, though the topic of regression will be taught at the start of the workshop, assuming that students are seeing regression for the first time.

Participants do not need to be familiar with Stata. The workshop presenter will demonstrate how to use Stata for the first exercise in each session, prior to workshop participants individually working though the exercises for that session.