Back to search

McMaster University

Statistical Methods for Analyzing EQ-5D Data in Clinical Trials

Abstract

dc:description.abstract

Patient-reported outcomes (PROs) are increasingly recognized as important outcomes in clinical trials. Among preference-weighted PRO measures for assessing health-related quality of life (HRQoL), the EQ-5D is one of the most widely used instruments and is routinely collected in randomized clinical trials (RCTs). The EQ-5D data, if analyzed properly, can produce important evidence for two purposes: estimating the treatment effect between arms and deriving health state utilities (HSUs) to support economic modeling. Although there is a guidance book for reporting and analyzing EQ-5D data, it primarily focuses on cross-sectional analyses. In contrast, EQ-5D data collected alongside RCTs are typically longitudinal in nature, requiring statistical methods that appropriately address key analytical challenges, including non-normal distributions, within-subject correlation over time, and missing data. However, methodological guidance on analyzing EQ-5D data in trials remains limited. This thesis aims to generate empirical evidence by comparing commonly used statistical models for estimating treatment effects and deriving HSUs using EQ-5D data from RCTs. The PhD project began with a systematic review of statistical methods used to analyze EQ-5D data in RCTs. Based on the findings, we conducted empirical comparisons of the most commonly used and recommended methods using individual-level data from multiple RCTs across different disease areas, focusing on treatment-effect estimation, missing data imputation, as well as HSU estimation. We further evaluated the implications of statistical model selection on both clinical and economic decision-making by examining its impact on statistical significance and clinical relevance of treatment-effect estimates, as well as on economic model outputs and cost-effectiveness conclusions. Across analyses, the empirical evidence supports linear mixed-effects models (LMMs) as a reasonable and pragmatic approach for analyzing EQ-5D data in RCTs, providing evidence-based methodological recommendations that may inform future guidance and improve the quality of EQ-5D analysis and reporting.

Degree

thesis:*
Department dc:contributor.department
Health Research Methodology
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Yan, Jiajun
Advisor dc:contributor.advisor
  • Xie`, Feng

Subjects

dc:subject × 5

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
McMaster University
Base URL
macsphere.mcmaster.ca/server/oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Yan, Jiajun. Statistical Methods for Analyzing EQ-5D Data in Clinical Trials. 2026. https://hdl.handle.net/11375/33572