Date of Award

6-9-2025

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Mathematics and Statistics

First Advisor

Wei Zhang

Abstract

Propensity score weighting (PSW) plays a key role in minimizing confounding in observational research, especially when estimating treatment effects for time-to-event outcomes. However, its integration into survey data with complex design – particularly data with multiple stage sampling and censoring – remains underexplored. One significant challenge in such settings is the presence of nonresponse, which can introduce additional bias and complicate the use of standard weight adjustments. Moreover, there has been limited study on how PS weights can be effectively combined with nonresponse weighting adjustments in complex survey data that include survival outcomes. This dissertation aims to extend current methodologies by evaluating how PS weights can be effectively combined with nonresponse weighting methods to improve treatment effectiveness estimation under complex survey conditions. Using simulations, we compare estimation performance under both Missing Completely at Random (MCAR) and Missing at Random (MAR) mechanisms, with consideration of scenarios involving weak overlap in propensity scores and varying censoring levels. The study evaluates absolute and relative treatment effects and compares the effectiveness of two adjustments strategies – cell-based adjustment and logistic regression-based adjustment – in addressing nonresponse bias. Our research results suggest that incorporating PS weights with nonresponse adjustments yields more accurate and reliable estimates of treatment effect, especially under MAR and limited overlap conditions. Among the two nonresponse adjustments, logistic regression weighting outperforms cell weighting in addressing bias values under these conditions.

Download

Included in

Biostatistics Commons

Share

COinS