励新卓越论坛

——澳门沙金在线平台建校70周年系列学术活动

报告题目：Efficient Estimation for the Accelerated Failure Time Model with Auxiliary Aggregate Information

报告人：马慧娟 副教授（华东师范大学）

报告摘要：With the rapidly increasing availability of aggregate data in the public domain, there has been a growing interest in synthesizing information from individual-level data and aggregate data. This article proposes a novel one-step estimator to improve the estimation of the accelerated failure time model by incorporating the auxiliary aggregate information from external sources. We construct a new expectationmaximization (EM) algorithm that is computationally convenient and produces a semi-parametrically efficient maximum conditional likelihood estimator without combining any auxiliary information as an initial estimator. The proposed framework stems from the maximum full likelihood estimator and allows for population heterogeneity. We establish the consistency and asymptotic normality of the proposed estimator and show that it is more efficient than the maximum conditional likelihood estimator. The asymptotic variance of the proposed estimator has a closed form and its variance estimator is easily obtained by plug-in rule. Simulation studies show that the proposed estimator yields an efficiency gain over existing approaches. The proposed methodology is illustrated with an analysis of a chemotherapy study for Stage III colon cancer.

个人简介：马慧娟，华东师范大学统计学院与统计交叉科学研究院副教授。2015年在中国科学技术大学获得统计学博士学位，2015-2018年在美国埃默里大学生物统计与生物信息系做博士后，2018年加入华东师范大学。主要研究方向包括生存分析，分位数回归，半参数模型等。在统计学期刊 Biometrika, Biometrics, Journal of Business & Economic Statistics, Statistica Sinica等期刊发表论文二十余篇。曾主持完成国家自然科学基金青年项目和上海市浦江人才项目。 现以项目骨干身份参与国家自然科学基金重点项目和科技部重大专项。

报告时间：2023年11月10日（周五）下午15：00-16：00

报告地点：教二楼701

联系人：胡涛