注册 投稿
经济金融网 中国经济学教育科研网 中国经济学年会 EFN通讯社

预告丨经济波动与增长在线讲座

经济波动与增长在线讲座:
 
成员档案与社区网络自回归的统计推断
 
主办:北京大学汇丰商学院、萨金特数量经济与金融研究所
 
时间:2020.8.14 上午9:00-11:00
 
ZOOM会议号:939 473 07439
 
会议密码: 944999
 
 
摘要
 
Statistical Inference on Membership Profiles and Community Network Autoregression
 
Network data is prevalent in many contemporary big data applications in which the nodes can be broadly defined such as individuals, economic entities, documents, or medical disorders in social, economic, text, or health networks.  Yet, simple questions of how to quantify the statistical uncertainty associated with the link identification and how to use community structures in VAR models remain largely unexplored.
 
To answer thefirst question, we propose a method for statistical inference on membership profilesin large networks (SIMPLE) for degree-corrected mixed membership model.  Under some mild conditions, we establish theexact limiting distributions of the SIMPLE test statistics, which are pivotalunder the null hypothesis and have asymptotic power one. Simulation studies and real network examples lend further support of our methods and theory.
 
To answer the second question, we introduce a novel network vector autoregressive model to reduce the number of coefficients in high-dimensional vector auto regression.    We propose new econometrics method,leveraging on the community structure, and establish related asymptotic inference tools.  The advantages of the CNAR model are nicely illustrated by synthetic and real datasets.
 
(Joint work with Yingying Fan, Xiao Han and Jinchi Lv and joint work with Elynn Chen and Xuening Zhu)
 
参考文献
 
Paper 1:  Fan, J., Fan, Y., Han, X. and Lv, J.(2019).
SIMPLE: statistical inference on membership profiles in large network.
Manuscript.
 
Paper 2: Chen, E. Y., Fan, J., and Zhu, X. (2020).
Community Network Auto-Regression for High-Dimensional Time Series
Manuscript.
 
嘉宾介绍
 
主讲人:范剑青
 
Frederick L. Moore'18 金融教授,统计学教授,美国普林斯顿大学运营研究与金融工程系前任系主任,曾于CUHK, UNC-Chapel Hill和UCLA担任教职。撰写及合著超250篇文章,内容涉及金融计量经济学,统计机器学习,大数据分析以及统计学理论与方法的各个方面。其著作曾获2000 COPSS Presidents’ Award, the 2007 Morningside Gold Medal of Applied Mathematics, and a Guggenheim Fellowship in 2009, Academian of Academia Sinica 2012, P.L. Hsu prize in 2013,  Guy Medal in Silver, 2014, and Noether Senior Scholar Award in 2018等多个奖项。作为美国科学促进会、金融计量经济学学会、数理统计研究所和美国统计协会的当选院士,数理统计研究所的前任主席,其曾参与多个国内外一流学术期刊的编辑工作。现任Journal of Business and Economics Statistics 联合编辑; 曾任Journalof Econometrics, Annals of Statistics, Probability Theory and Related Fields, and Ecnometrics Journal 编辑; Econometrica, Journal of American Statistical Association and Journal of Financial Econometrics 副主编。
 
来源:“北大汇丰学术动态”微信公众号
相关阅读
文章评论
关注我们

快速入口
回到顶部
深圳网站建设