A0458
Title: The Cox proportional hazards cure model in application of disease screening
Authors: Lisha Guo - South-Central University for Nationalities (China) [presenting]
Xiaoqiong Joan Hu - Simon Fraser University (Canada)
Yanyan Liu - Wuhan University (China)
Abstract: Motivated by a tuberculosis (TB) study, we consider likelihood-based estimation under the Cox proportional hazards cure model using right-censored times together some covariate entries missing not at random. We demonstrate the existence of the pseudo semiparametric maximum likelihood estimator of the model parameters, and establish the consistency and weak convergence of the estimator. Finite sample performance of the proposed estimation procedure is examined and compared with two conventional approaches. An analysis of the tuberculosis (TB) study data is used to illustrate the application of the statistical approach in disease screening.