通知公告

6月14日:吴远山 | Double Bias Corrections for High-Dimensional Sparse Additive Hazards Regression with Covariate Measurement Error

时间:2019年6月14日(周五)下午15:00-16:00

地点:闵行校区法商南楼135室

题目:Double Bias Corrections for High-Dimensional Sparse Additive Hazards Regression with Covariate Measurement Error  

报告人:吴远山 教授  中南财经政法大学

摘要:This article proposes an inferential procedure for additive hazards regression for censored high-dimensional survival data, wherein the covariate is prone to be measured with error. We develop an estimating function for regression parameter to firstly correct the bias arising from measurement error in covariate. Adopting the convex relaxation technique, a regularized lasso estimator for regression parameter is obtained by elaborately designing a feasible loss based on the estimating function. Utilizing the recent debiasing method, we propose an asymptotically unbiased estimator by secondly correcting the bias caused by the convex relaxation and regularization. We build the $\ell_1$- and $\ell_2$-bounds of the proposed estimator and further establish the asymptotic normality for the low-dimensional parameter estimator and the liner combination thereof, accompanying with consistent estimators for their finite-dimensional covariance matrices. Extensive numerical experiments are carried out on both simulated and real datasets to demonstrate the promising performance of the proposed double bias correction method.

报告人简介:吴远山,中南财经政法大学统计与数学学院教授,博士,博士生导师,曾于2010.9-2011.9在香港大学统计与精算系进行博士后研究。主要研究方向为:高维数据分析、生物统计、大数据分析与分布式计算,主持多项国家级和省部级科研项目,在国际重要统计学期刊上发表SCI学术论文20多篇,其中多篇论文发表在国际顶级统计学杂志:Journal of the American Statistical Association、Biometrika、Biometrics上。


发布者:王璐瑶发布时间:2019-06-10浏览次数:190