Nonparametric Sieve Maximum Likelihood Estimation for Semi-competing Risks Data

题目： NonparametricSieve Maximum Likelihood Estimation for Semi-competing Risks Data

时间：11月6日（周二）下午3:00―5:00

地点：工商楼2楼报告厅（200-9）

报告人：Professor Xu, J. F.（The University of Hong Kong）

摘要：Inclinical trials comparing therapeutic interventions, a subject may experiencedistinct types of events. We consider the problem of estimating the transition functionsfor a semi-competing risks model under illness-death model framework. Wepropose to estimate the intensity functions by maximizing a B-spline basedsieve likelihood. The method yields smooth estimates without parametricassumptions. This approach also permits direct computation of the variance ofparameters using the inverse of the Hessian matrix. Under some mild conditions,the estimators are shown to be strongly consistent; the convergence rate of theestimator for transition function is obtained and the estimator for the unknownparameter is shown to be asymptotically normally distributed. Simulationstudies are conducted to examine the small-sample properties of the proposedestimates and a real data set is used to illustrate our approach.

欢迎大家参加！

联系人：张荣茂（rmzhang@zju.edu.cn)