学术报告
Variable selection via penalized GEE for a marginal survival model——牛一 副教授（大连理工大学）
“2020首师大青年统计论坛”系列报告
题目：Variable selection via penalized GEE for a marginal survival model
报告人：牛一 副教授（大连理工大学）
时间：2020年11月26日（周四）下午19:00-20:00
地点：线上腾讯会议（会议号：766 943 031）
Abstract :Clustered and multivariate survival times, such as times to recurrent events, often arise in biomedical and health research, and marginal survival models are often used to model such data. When there are a large number of predictors available, variable selection is always an important issue when modeling such data with a marginal survival model. We consider a marginal Cox's proportional hazards model in this paper. Under the sparsity assumption, we propose a penalized generalized estimating equations approach to select important variables and to estimate regression coefficients simultaneously in the marginal model. The proposed method explicitly models the correlation structure within clusters or correlated variables by using a prespecified working correlation matrix. The asymptotic properties of the estimators from the penalized generalized estimating equations are established and the number of candidate covariates is allowed to increase in the same order as the number of clusters does. We evaluate the performance of the proposed method through a simulation study and demonstrate its application using two real datasets.
报告人简介：牛一，大连理工大学77779193永利官网副教授，主要从事生存分析、统计计算以及与公共健康相关的交叉学科研究。主持并参加了多项国家自然科学基金和省部级项目。在Statistics in Medicine，Journal of the National Cancer Institute，Statistical Methods in Medical Research，Biometrical Journal，Computational Statistics and Data Analysis，Journal of Multivariate Analysis，Computer Methods and Programs in Biomedicine等学术期刊发表多篇科研论文。
联系人：周洁、胡涛
举办单位：77779193永利官网统计系、北京应用统计学会、交叉科学研究院
