Dissertation/Thesis Abstract

Shared-Parameter Joint Models of Fatigue and Time Until Death of Non-Resectable Lung Cancer Patients
by Phillips, David, M.S., The University of Arizona, 2018, 31; 10815456
Abstract (Summary)

With researchers showing greater interest in the relationship between longitudinal and survival outcomes, joint models are being used with greater frequency. Joint models of longitudinal and time to event outcomes offer distinct advantages. First, joint models can reduce bias in estimates of the relationship between surrogate markers and survival endpoints. Second, this class of model can provide sensitivity analysis of longitudinal estimates in the presence of potential missing data when the longitudinal outcome and survival outcome are related. The aim of this paper is to demonstrate the usefulness of this methodology when dealing with potentially related outcomes. Using a data set from a clinical trial aimed at reducing fatigue with physical activity amongst non-resectable lung cancer patients, several joint models and conventional models such as a linear mixed model and Cox proportional hazards model were generated. Both the longitudinal and survival estimates from these models were compared to demonstrate the utility of joint models. Furthermore, the implementation of joint models is discussed as a result of the analysis.

Indexing (document details)
Advisor: Bell, Melanie
Commitee: Hsu, Chiu-Hsieh (Paul), Hu, Chengcheng
School: The University of Arizona
Department: Biostatistics
School Location: United States -- Arizona
Source: MAI 57/06M(E), Masters Abstracts International
Subjects: Biostatistics, Statistics, Oncology
Keywords: Joint models, Longitudinal outcomes, Lung cancer, Survival outcomes
Publication Number: 10815456
ISBN: 978-0-355-94290-3
Copyright © 2020 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy