统计与数据科学系系列学术报告之四百二十八-四百二十九期

时   间：2024年5月7日（周二）15:00-16:00

地   点：史带楼502室

主持人：复旦大学 管理学院 统计与数据科学系黎德元 教授

报告人：陈昱 副教授  中国科学技术大学

题   目：Inference for Extreme Value Index through Individualized Fusion Learning

摘   要：Making inferences for extreme value index under a heavy-tailed framework is an essential problem in extreme value theory. In this paper, we estimate the extreme value index through a new fusion learning approach called individual fusion learning (abbreviated as iFusion). For a target individual, we consider inference for its extreme value index by strategically ``borrowing strength'' from relevant individuals to enhance the efficiency while preserving its validity, which is the highlight of iFusion. Due to the fact that iFusion can naturally fit in the ``divide-and-conquer'' algorithm when the samples are generated independently from each individual, we build a general theory for the estimation of extreme value index in the context of distributed inference. Our approach is supported by the general results of the Hill estimator. Considering the case where the number of observations involved in each individual is heterogeneous, we establish the consistency and asymptotic normality of the so-called iFusion estimators. We extend our methodology to special scenarios where there exists a dependence structure between the observations from different individuals. The validity of the proposed methodology is explored with simulation studies and through an application using real datasets.

个人简介：陈昱，中国科学技术大学管理学院统计与金融系副教授。研究方向为风险理论中的极限定理, 金融计量模型，网络风险分析，多元统计分析理论及时间序列分析等。主持国家自然科学基金面上项目三项，青年一项，国家社科基金项目一项，国家重点研发专项“重大事故灾难次生衍生与多灾种耦合致灾机理与规律”的研究骨干，在 Annals of Applied Statistics, Journal of Econometrics, Journal of Business & Economic Statistics及Journal of Computational and Graphic Statistics等统计学期刊上发表论文40余篇。

统计与数据科学系系列学术报告之四百二十九期

时   间：2024年5月21日（周二）16:00-17:00

地   点：思源教授楼726室

主持人：复旦大学 管理学院 统计与数据科学系 郁文 教授

报告人：Prof.Danyu Lin

              Dennis Gillings Distinguished Professor of Biostatistics

              The University of North Carolina at Chapel Hill, USA

题   目：Evaluating the Effectiveness of COVID-19 Vaccines

摘   要：Approximately 800 million COVID-19 cases and 7 million COVID-19 deaths have been reported to the World Health Organization thus far.  Vaccination is a major tool to combat the COVID-19 pandemic, but its effectiveness wanes over time and tends to be lower against new SARS-CoV-2 variants. The knowledge about the waning effects of vaccination can guide boosting strategies. In a series of papers published in New England Journal of Medicine, JAMA and The Lancet, we reported several large cohort studies using COVID-19 vaccination and case surveillance data from the states of North Carolina and Nebraska, as well as electronic health records from the Cleveland Clinic Health System. We developed a novel statistical framework to evaluate the time-varying effects of the three generations of COVID-19 vaccines produced in the United States on infections with different SARS-CoV-2 variants and on severe outcomes (hospitalization and death). Our findings have been used by the World Health Organization and the U.S. Centers for Disease Control and Prevention and Food and Drug Administration and reported by The New York Times, The Washington Post and NBC News.

个人简介：Danyu Lin, Ph.D., is the Dennis Gillings Distinguished Professor of Biostatistics at the University of North Carolina at Chapel Hill. Dr. Lin has published 300 papers, with 45,000 citations and an h-index of 97. The statistical methods he developed have been used in thousands of scientific studies. His publications on COVID-19 vaccines and treatments (5 in New England Journal of Medicine, 3 in JAMA, and 2 in Lancet —all as first and corresponding author) have been viewed 1 million times, cited by the Centers for Disease Control and Prevention, the Food and Drug Administration, the European Medicines Agency, and the World Health Organization, and reported by The New York Times, The Washington Post, and NBC News. Dr. Lin is an elected fellow of American Statistical Association and Institute of Mathematical Statistics, a recipient of Mortimer Spiegelman Award from American Public Health Association, and a recipient of George W. Snedecor Award from the Committee of Presidents of Statistical Societies.

统计与数据科学系

2024-4-26