学术报告
报告题目：Envelopes: Methods for Efficient Estimation inMultivariate Statistics
报告人: Professor Dennis R. Cook
Dennis Cook教授现任美国明尼苏达大学统计系主任，当代国际统计顶尖学者，“Cook-距离”的提出者，2005年COPSS的Fisher Lecturer获奖者（统计学最高终身荣誉，相当于数学界的沃尔夫奖），是ASA、IMS和ISI会士，是现代统计诊断和数据降维领域的开创者之一。他是两本著名统计教课书《An Introduction to Regression Graphics》和《Applied Regression Including Computing and Graphics》的作者，曾三次获得应用统计学领域最高荣誉《Technometrics》的Jack Youden Prizefor Best Expository Paper。
时间：2014.05.16 (周五) 14:00-15:00
地点：数学院第一报告厅
摘要：An envelopes is a nascent construct for increasing efficiency in multivariatestatistics without altering the traditional goals. We will begin with a mostly intuitive introduction to response envelopes inthe multivariate linear model and then brieflydescribe some of the asymptoticresults and inner workings of envelopes. This will be followed by a discussion ofpredictor envelopes and their connection to partial least squares. We will also describe how to extend the scope of envelope methods beyond linear models.
南开大学统计研究院
2014年5月15日