Course 2

Course 2
An introduction to the joint modelling of longitudinal and survival data

Presenter: Dimitris Rizopoulos                Room: Oak Bay 1&2
(Sunday, 10 July 2016 from 9:00 am – 5:00 pm)

Click here to download course materials.

Summary: In follow-up studies different types of outcomes are typically collected for each subject. These include longitudinally measured responses (e.g., biomarkers), and the time until an event of interest occurs (e.g., death, dropout). Often these outcomes are separately analyzed, but in many occasions it is of scientific interest to study their association. This type of research questions has given rise to the class of joint models for longitudinal and time-to-event data. These models constitute an attractive paradigm for the analysis of follow-up data that is mainly applicable in two settings: First, when focus is on a survival outcome and we wish to account for the effect of endogenous time-varying covariates measured with error, and second, when focus is on the longitudinal outcome and we wish to correct for non-random dropout.

This full-day course is aimed at applied researchers and graduate students, and will provide a comprehensive introduction into this modeling framework. Emphasis is given on applications, with detailed examples on how to fit the these models in R and how to interpret the results.

The aims of the course are to:

  1. introduce the framework of joint models for longitudinal and survival data;
  2. explain the key features behind them, and
  3. illustrate how these models can be fitted in R.

At the end of the day, participants should:

  1. know which type of research questions require the separate and which the joint analysis of outcomes;
  2. know the basics of joint models and their key attributes;
  3. be able to define a joint model based on the data and questions at hand;
  4. be able to fit the joint model using R, and
  5. know how to interpret the results.

Topics covered

brief review of mixed models; brief review of relative risk model; the basic joint model; extensions of joint models; dynamic predictions.

Learning strategy

Topics will be introduced by a presentation, followed by hands‐on application using publicly available R packages.

Preparation

Participants are expected to bring a laptop with the latest versions of R and Rstudio installed, as well as the recent versions of packages JM and JMbayes. Participants will be asked to download course material about two weeks prior to the course.

Pre‐requisites

This course assumes knowledge of basic statistical concepts, such as standard statistical inference using maximum likelihood, and regression models. In addition, basic knowledge of R would be beneficial but is not required.

About the instructor

Dimitris Rizopoulos is an Associate Professor of Biostatics at the Erasmus Medical Center, Rotterdam, the Netherlands. He has published a series of methodological and applied papers in the field of joint models, he is the author of the first book on this topic, and the author of two publicly available R packages to fit them.