报告时间：2023年4月25日

               上午10:00-11:00

报告地点：中国人民大学明德主楼1016

报告嘉宾：杨立坚

报告主题：The story of ERP: functional data with temporally dependent errors

报告摘要

The story of ERP: functional data with temporally dependent errors

Event-related potentials (ERP) are segments of electroencephalogram (EEG) signal recorded in response to specific events or stimuli. Analyzing ERP data plays an important role in cognitive neuroscience as it sheds light on how brain reacts in real time to a defined event (Luck 2014). ERP data are contaminated with correlated errors due to artifacts such as like eye movements, muscle artifacts, electrocardiogram, etc. In this talk, I present recent works on simultaneous confidence regions (SCRs) for the mean and covariance functions of ERP data, within the broad framework of functional data measured with infinite moving average errors. The proposed SCRs enjoy “oracle efficiency” in the sense that they are asymptotically the same as if the ERP signals are recorded without errors, over the entire time period. For a small ERP data from Tsinghua University Psychology Department, The SCRs have unveiled a number of interesting phenomena both in terms of components’ comparison and principal components inference.

个人简介

杨立坚，清华大学统计学研究中心与工业工程系长聘教授。北京大学数学学士（1987）、美国北卡罗来纳大学教堂山分校统计学博士（1995）、德国洪堡大学博士后（1995-97）。曾任美国密西根州立大学统计与概率系助理教授（1997-2001）、终身副教授（2001-06）、终身正教授（2006-14）、研究生主任（2007-10）、苏州大学特聘教授、高等统计与计量经济中心主任（2011-16）。获美国耶鲁大学出版社Tjalling C. Koopmans Econometric Theory Prize、美国统计协会会士（ASA Fellow）、国际数理统计学会会士（IMS Fellow）、国际工程技术协会杰出会士（IETI Distinguished Fellow）、国际统计学会当选会员（ISI Elected Member）。研究领域：函数型数据、非线性时间序列数据、抽样调查数据的统计推断，高维数据的半参数降维，同时置信带的理论与方法，统计学对经济学、食品科学、遗传学、神经科学、和管理科学的应用。在包括《Annals of Statistics》《Annals of Probability》《Journal of the American Statistical Association》《Journal of the Royal Statistical Society B》《Journal of Econometrics》《Journal of Business and Economic Statistics》的SCI期刊发表论文80余篇。