Online Program Home
  My Program

Abstract Details

Activity Number: 595 - Dynamic Methods for Functional Data with Application to Clinical Data Analysis
Type: Invited
Date/Time: Thursday, August 3, 2017 : 8:30 AM to 10:20 AM
Sponsor: ENAR
Abstract #322387 View Presentation
Title: Dynamic Prediction with Joint Models and Landmarking
Author(s): Jonathan Gellar*
Companies: Mathematica Policy Research

Dynamic prediction of mortality is the prediction of future survival based on data (such as a biomarker) recorded up to a particular time point. Currently, there are two competing approaches in the literature for performing dynamic prediction: joint modeling of longitudinal and survival data, and landmarking. In this talk, we show how the fundamental ideas behind each approach are not mutually exclusive, and that joint modeling and landmarking can be used in concert with one another. We present a model that combines the features of joint modeling and landmarking, leveraging the advantages of each approach while avoiding key limitations. Methods are motivated and applied to a study of mortality in the intensive care unit.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

Copyright © American Statistical Association