Speaker: Yingwei Peng (Queen's University)

Time: 9:00-10:00 a.m., October 12, 2023, GMT+8

Venue: Zoom Meeting ID: 959 7114 8691 Password: 123456

Abstract:

Nonparametric estimation methods for the cure rate and the distribution of the failure time of uncured subjects with covariates for right-censored survival data have attracted much attention in the last few years. To model the effects of covariates on the latency distribution of the failure time of uncured subjects, existing works assume that the cure rate is either constant or depends on the same covariate as the covariate in the latency distribution of uncured subjects. In this talk, I will review the nonparametric estimation methods for the mixture cure model and present a new nonparametric method to model covariate effects on the latency distribution of uncured subjects. The estimation method is based on the EM algorithm, which is readily available for mixture cure models, and it relaxes the assumption used in the existing works. The finite sample and asymptotic properties of the proposed estimator are discussed. Finally, the nonparametric estimation methods are employedto model the effects of some covariates on the time to bankruptcy amongcommercial banks insured by the FDIC during the first quarter of 2006.

Source: Biostatistics Seminar Series