暨南大学经济学院建院40周年系列活动之学术讲座第37期
经济学院统计学系列 Seminar 第73期
主题: Comparison of Two Frameworks for Analyzing Longitudinal Data
主讲人: 周洁（首都师范大学）
主持人：王国长
会议工具：腾讯会议 （ID： 302 256 639 ）
会议时间：2020年11月10日上午10:00-11:00
摘要
Longitudinal data has two designs according to observation times: the fixed design and the random design, which have regular and irregular observation times respectively. Under the random design, there are two frameworks for analyzing longitudinal data. One is the clustered data framework and the other is counting process framework. In this paper, we give a thorough comparison of these two frameworks in terms of data structure, model assumption and estimation procedures. We find that modeling the observation times in the counting process framework will not gain any efficiency when the observation times are independent of the longitudinal response given covariates. Some simulation studies are conducted to confirm these results in finite sample behaviors, and a real data analysis of the alzheimer's disease study is implemented for further comparison.
主讲人简介
周洁，现任首都师范大学数学科学学院副教授，主要从事生存分析、复发事件与纵向数据的研究，在JASA，Biometrics, Statistica Sinica等国内外重要统计学杂志上发表SCI论文20余篇，主持2项国家自然科学基金项目及多项北京市科研项目。
