报告人:杨玥含（中央财经大学）

日  期:2019年5月10日

时  间:20:00

地  点:理科楼 LD202

摘  要:Regression adjustments are often considered by investigators to improve the estimation efficiency of causa effect in randomized experiments when there exist many pre-experiment covariates. In this paper, we provide conditions that guarantee the penalized regression including the Ridge, Elastic Net and Adapive Lasso adjusted causal effect estimators are asymptotic normal and we show that their asymptotic variances are no greater than that of the simple difference-in-means estimator, as long as the penalized estimators are risk consistent. We also provide conservative estimators for the asymptotic variance which can be used to construct asymptotically conservative confidence intervals for the average causal effect (ACE). Our results are obtained under the Neyman-Rubin potential outcomes model of randomized experiment when the number of covariates is large. Simulation study shows the advantages of the penalized regression adjusted ACE estimators over the difference-in-means estimator.

报告人简介：杨玥含，理学博士，就职于中央财经大学。2014年博士毕业于北京大学数学科学学院。主要研究高维线性模型、图模型、多变量模型的复杂数据建模及算法。

公司联系人:杨 虎

欢迎广大师生积极参与！