Term of Award
Doctor of Public Health in Biostatistics (Dr.P.H.)
Document Type and Release Option
Dissertation (restricted to Georgia Southern)
Copyright Statement / License for Reuse
This work is licensed under a Creative Commons Attribution 4.0 License.
Department of Biostatistics, Epidemiology, and Environmental Health Sciences
Committee Member 1
Committee Member 2
The mixture cure model is a developed statistical survival model. It assumes that the studied population is a mixture of susceptible patients who may experience the event of interest, and non-susceptible patients who will never experience the event of interest even at the end of follow-up. This mixture cure model is composed of two parts: one is the incidence part, which is the probability of being uncured, and the other is the latency part, which describes the distribution of the survival time of uncured patients. In this dissertation, we evaluate the performance of three statistical methods: proportional hazards regression model (Cox PH), restricted mean survival time (RMST), and mixture cure model on simulated data. The results indicated that when the data satisfied the proportional hazards assumption, the Cox PH model was always the best method to estimate the parameters. When the data did not satisfy the proportional hazards assumption, most of time RMST was the best model. When the data was cure rate data, the mixture cure model was always the best method. Moreover, the three methods were applied to real cancer data to compare the results.
Liu, Manyun, "Analysis Of Overall Survival Data Using Mixture Cure Model" (2022). Electronic Theses and Dissertations. 2460.
Research Data and Supplementary Material
Available for download on Thursday, June 24, 2027