Advisor(s)

Stacey Cofield

Committee Member(s)

InmacUlada Aban
J Wells
Justin Leach
Nengjun Yi

Document Type

Dissertation

Date of Award

1-27-2026

Degree Name

Doctor of Public Health (DrPH)

School

School of Public Health

Department

Public Health

Abstract

Chronic Obstructive Pulmonary Disease (COPD) remains a major global health concern and one of the leading causes of death in the United States, affecting approximately 4.6% of adults and reaching a prevalence of 9.4% in Alabama according to 2024 National Health Interview Survey. The disease imposes a substantial burden on quality of life and healthcare costs and contributes to increased disability-adjusted life years and years of life lost, as highlighted by the 2022 Lancet Commission report. Despite its im-pact, COPD is frequently diagnosed only after irreversible lung damage has occurred, largely due to under-recognized symptoms and limited diagnostic tools. Early detection and effective intervention depend on the quality and completeness of longitudinal data. However, missing data, commonly occur in longitudinal studies and randomized con-trolled trials (RCTs), presents a significant methodological and public health challenge, as improper handling can bias estimates of disease progression, misrepresent treatment effects, and misguide policy. This dissertation aims at improving the handling of missing data in COPD re-search. The first paper presents a literature review and evaluates statistical methods used to address missing data in COPD studies, assessing their underlying assumptions, performance, and limitations. The second paper identifies patterns and likely mechanisms of missing data within the Prospective Repository for coupling EVEnts to Novel paThways in COPD and Asthma (PREVENT) research registry using diagnostic tools and statistical modeling. The final paper investigates the impact of weight loss on physical function in obese patients with COPD, comparing results from multiple imputation (MI) and complete case analysis (CCA) to evaluate how different imputation and analysis strategies influence model inference and prediction when both predictors and outcomes are missing. Together, the research presented in this dissertation highlights that addressing missing data is not merely a statistical concern but a crucial factor in advancing COPD symptom management, improving methodological rigor, and strengthening the reliability of clinical and public health research.

Keywords

COPD;missing data;missing pattern;multiple imputation

ProQuest Publication Number

32284342

ISBN

9798273349766

Download

Share

COinS