【95周年校庆系列讲座】Time Series Analysis of COVID-19 Infection Curve: A Change-Point Perspective

时间:2020-07-23         阅读:

光华讲坛——社会名流与企业家论坛第 5762 期

(线上讲座)

主题Time Series Analysis of COVID-19 Infection Curve: A Change-Point Perspective

主讲人伊利诺伊大学香槟分校 邵晓峰教授

主持人统计学院 常晋源教授

时间2020年7月24日(周五)9:30-10:30

直播平台及会议IDZoom,会议ID:921 1079 7812

主办单位:统计研究中心 数据科学与商业智能联合实验室 统计学院 科研处

主讲人简介:

Dr. Shao is Professor of Statistics and PhD program director, at the Department of Statistics, University of Illinois at Urbana-Champaign (UIUC). He received his PhD in Statistics from University of Chicago in 2006 and has been on the UIUC faculty since then. Dr. Shao's research interests include time series analysis, high-dimensional data analysis, functional data analysis, change-point analysis, resampling methods and asymptotic theory. He is an elected ASA and IMS fellow.

邵晓峰,美国伊利诺伊大学香槟分校统计学教授,博士生项目主任。他于2006年获得了芝加哥大学的统计学博士学位,此后一直在美国伊利诺伊大学香槟分校任教。主要研究方向为时间序列分析、高维数据分析、函数型数据分析、变点分析、重采样方法和渐进理论。他是当选的ASA和IMS成员。

内容提要:

I will present our recent work to model the trajectory of the cumulative confirmed cases and deaths of COVID-19 (in log scale) via a piecewise linear trend model. The model naturally captures the phase transitions of the epidemic growth rate via change-points and further enjoys great interpretability due to its semiparametric nature. On the methodological front, we advance the nascent self-normalization (SN) technique (Shao, 2010) to testing and estimation of a single change point in the linear trend of a nonstationary time series. We further combine the SN-based change-point test with the NOT algorithm (Baranowski et al., 2019) to achieve multiple change-point estimation. Using the proposed method, we analyze the trajectory of the cumulative COVID-19 cases and deaths for 30 major countries and discover interesting patterns with potentially relevant implications for effectiveness of the pandemic responses by different countries. Furthermore, based on the change-point detection algorithm and a flexible extrapolation function, we design a simple two-stage forecasting scheme for COVID-19 and demonstrate its promising performance in predicting cumulative deaths in the U.S. Joint work with Feiyu Jiang and Zifeng Zhao.

本报告将介绍我们最近的工作——通过分段线性趋势模型对COVID-19累计确诊病例和死亡人数(以对数为尺度)的轨迹进行建模。该模型能通过变点自然地捕捉传染病增长率的相变,并且由于其半参数性而具有很强的可解释性。在方法层面,本报告采用新兴自归化(SN)技术(Shao, 2010)来检验和估计非平稳时间序列线性趋势中的单一变点。进一步将基于SN的变点测试与NOT算法(Baranowski et al., 2019)相结合来实现多变点估计。利用所提出的方法,本报告分析了30个主要国家COVID-19累计病例和死亡人数的轨迹,发现了一些有趣的现象可能对不同国家应对疫情的有效性产生相关影响。此外,基于变点检测算法和可扩展的外推函数,本报告对COVID-19设计了一个简单的两阶段预测方案,并在预测美国累计死亡人数方面能有很好的表现。本研究是与Feiyu Jiang和Zifeng Zhao一起合作完成的。