统计学系系列讲座之365期

时　间：2019年12月23日（星期一）16:00-17:00

地　点：史带楼302室

主持人：张新生  教授 复旦大学管理学院统计学系

主　题：Instrumental variable methods in regularized regression with covariate measurement error

主讲人：Professor Liqun Wang　Department of Statistics, University of Manitoba

简　介：Dr. Liqun Wang is professor in statistics in Department of Statistics at University of Manitoba. He is an elected member of the International Statistical Institute (ISI).He has served as associate editor of the Canadian Journal of Statistics. He also served as Chair of the Research Committee of the Statistical Society of Canada.

His research areas include estimation in nonlinear models with measurement error, high-dimensional variable selection and data assimilation, boundary crossing probability for diffusion processes, and Monte Carlo simulation methods in statistical computation and optimization. He is also interested in biostatistics and econometrics.

摘　要：

Regularization methods are widely used in high-dimensional regression models and most methods are developed for the situation where all variables are correctly and precisely measured. However, in real data analysis measurement error is common. We study the variable selection and estimation problems in linear and generalized linear models when some of the predictors are measured with error. We demonstrate how measurement error impacts the selection results and propose regularized instrumental variable methods to correct for the measurement error effects. The proposed methods are consistent in selection and estimation and we derive their asymptotic distributions under general conditions. We also investigate the performances of the methods through Monte Carlo simulations and compare them with the naive method that ignores measurement error. Finally, the proposed method is applied to a real dataset. This is a joint work with Lin Xue.

 统计学系 

2019-12-16