Fitting Joint Models in R Using Packages JM and JMbayes

• Activity Number: 394
• Type: Invited
• Date/Time: Tuesday, August 11, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Section for Statistical Programmers and Analysts
• Author(s): Dimitris Rizopoulos*
• Companies: Erasmus Medical Center
• Keywords: Survival Analysis ; Longitudinal Data Analysis ; Random Effects ; Software ; Predictions

Abstract

Joint models for longitudinal and time-to-event data constitute a very active research field in Statistics and Biomedical sciences in general. 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-dependents covariates measured with error (e.g., biomarkers), and second, when focus is on the longitudinal outcome and we wish to correct for non-random dropout. In this talk we will illustrate how these models can be fitted in R using packages JM and JMbayes. Particular attention will be given in joint models with categorical longitudinal responses, different options for the functional form of the association structure between the two outcomes, and how to calculate dynamic predictions. For the last feature we will also illustrate a shiny application in R that greatly facilitates the use of the package in practice.