光華講壇——社會(huì)名流與企業(yè)家論壇第6555期

主 題：Some Recent Developments in Expected Shortfall Regression 期望短缺回歸的最新進(jìn)展

主講人：華盛頓大學(xué) 圣路易斯何旭銘教授

主持人：統(tǒng)計(jì)學(xué)院 林華珍教授

時(shí)間：6月6日 14:30-15:30

舉辦地點(diǎn)：柳林校區(qū)弘遠(yuǎn)樓408會(huì)議室

主辦單位：統(tǒng)計(jì)研究中心和統(tǒng)計(jì)學(xué)院 國(guó)際交流與合作處 科研處

主講人簡(jiǎn)介：

Xuming He is Kotzubei Beckmann Distinguished Professor and Inaugural Chair of the Department of Statistics and Data Science at Washington University in St. Louis. Xuming He’s research focuses on robust statistical analysis of observational data and designed experiments, particularly in areas such as quantile regression analysis, Bayesian computation for model selection, subgroup analysis, and post-selection inference.

Xuming He is an elected Fellow of the American Association for the Advancement of Science, the American Statistical Association, and the Institute of Mathematical Statistics. He served as Editor and Co-Editor of several journals including the Journal of the American Statistical Association (Theory & Methods). He has been honored as a Medallion Lecturer and Keynote Speaker at the 2007 Joint Statistical Meetings and delivered The International Association for Statistical Computing's President's Lecture at the 62nd World Statistics Congress (2019). He received the Distinguished Achievement Award from the International Chinese Statistical Association in 2015, the Distinguished Faculty Achievement Award from the University of Michigan in 2021. In addition, he was awarded the Carver Medal (2022) from the Institute of Mathematical Statistics and the Founders Award (2021) from the American Statistical Association for his decade-long leadership in the profession.

Currently, Xuming He serves as President of the International Statistical Institute, the only non-government global statistical organization with consultative status at the United Nations Economic and Social Council.

何旭銘是華盛頓大學(xué)-圣路易斯統(tǒng)計(jì)與數(shù)據(jù)科學(xué)系的Kotzubei Beckmann杰出教授和首任系主任。他的主要研究領(lǐng)域包括分位數(shù)回歸分析、貝葉斯模型選擇計(jì)算、亞組分析以及選擇后推斷等方面。

他是美國(guó)科學(xué)促進(jìn)會(huì)（AAAS）、美國(guó)統(tǒng)計(jì)學(xué)會(huì)（ASA）和國(guó)際數(shù)理統(tǒng)計(jì)學(xué)會(huì)（IMS）的Fellow。曾擔(dān)任JASA等多個(gè)期刊的主編。他曾在2007年的聯(lián)合統(tǒng)計(jì)會(huì)議上擔(dān)任Medallion Lecturer 和 Keynote Speaker，并在2019年第62屆世界統(tǒng)計(jì)大會(huì)上擔(dān)任國(guó)際統(tǒng)計(jì)計(jì)算協(xié)會(huì)主席并發(fā)表演講。曾獲得國(guó)際泛華統(tǒng)計(jì)協(xié)會(huì)（ICSA）杰出成就獎(jiǎng)（2015）、密歇根大學(xué)杰出教師成就獎(jiǎng)（2021）、國(guó)際數(shù)理統(tǒng)計(jì)學(xué)會(huì)（IMS）的卡弗(Carver)獎(jiǎng)?wù)拢?022）以及美國(guó)統(tǒng)計(jì)學(xué)會(huì)（ASA）創(chuàng)始人獎(jiǎng)（2021）等。

何旭銘現(xiàn)任國(guó)際統(tǒng)計(jì)學(xué)會(huì)（ISI）主席，該協(xié)會(huì)是唯一在聯(lián)合國(guó)經(jīng)濟(jì)及社會(huì)理事會(huì)享有咨詢地位的非政府全球統(tǒng)計(jì)組織。

內(nèi)容簡(jiǎn)介：

Expected shortfall, measuring the average outcome (e.g., portfolio loss) above a given quantile of its probability distribution, is a common financial risk measure. The same measure can be used to characterize treatment effects in the tail of an outcome distribution, with applications ranging from policy evaluation in economics and public health to biomedical investigations. Expected shortfall regression is a natural approach of modeling covariate-adjusted expected shortfalls. Because the expected shortfall cannot be written as a solution of an expected loss function at the population level, computational as well as statistical challenges around expected shortfall regression have led to stimulating research. We discuss some recent developments in this area, with a focus on a new optimization-based semiparametric approach to estimation of conditional expected shortfall that adapts well to data heterogeneity with minimal model assumptions. The talk is based on joint work with Yuanzhi Li and Shushu Zhang.

期望短缺（Expected Shortfall）是一種常見(jiàn)的金融風(fēng)險(xiǎn)度量，衡量給定分位數(shù)以上的平均結(jié)果（例如，投資組合損失）。同樣的度量可以用于描述結(jié)果分布尾部的處理效應(yīng)，應(yīng)用范圍包括經(jīng)濟(jì)學(xué)和公共衛(wèi)生政策評(píng)估以及生物醫(yī)學(xué)研究。期望短缺回歸是一種自然的方法，用于建模協(xié)變量調(diào)整后的期望短缺。由于期望短缺不能表示為總體水平上的期望損失函數(shù)的解，圍繞期望短缺回歸的計(jì)算和統(tǒng)計(jì)挑戰(zhàn)激發(fā)了大量研究。主講人將討論該領(lǐng)域的一些最新進(jìn)展，重點(diǎn)介紹一種新的基于優(yōu)化的半?yún)?shù)估計(jì)方法，用于條件期望短缺的估計(jì)，該方法能夠在最小模型假設(shè)下很好地適應(yīng)數(shù)據(jù)異質(zhì)性。該演講基于與Yuanzhi Li和Shushu Zhang的合作研究。