ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Joint Models for Time-to-Event and Categorical Longitudinal Outcomes

Doms, Hortense
(2020)

Files

Doms_63521800_2020.pdf
  • Open access
  • Adobe PDF
  • 1.08 MB
Download

Details

Supervisors
Legrand, Catherine
Faculty
Faculté des sciences
Degree label
Master [120] en statistique, orientation biostatistiques
Abstract
In clinical research, subjects are generally observed over a period of time during which longitudinal and time-to-event outcomes are recorded. The main interest is to assess potential associations between these two outcomes by fitting joint models. In this thesis, we present the joint modelling framework motivated by the time-to-event point of view and we propose an approach for continuous and categorical longitudinal outcomes. We present methods for estimating joint models from the frequentist and Bayesian perspectives. The methodology is then applied to the intensive care unit (ICU) database. Patients admitted to ICUs are likely to develop delirium. We use joint models to study the association between longitudinal measurements of hypotension episodes and the hazard of developing delirium. We also present and use different association structures between the two outcomes.