活动时间：7月5日9：30-11:00
活动地点：统计学院资料室
1. 报告题目：Detection of Multiple Structural Breaks in Large Covariance Matrices
主讲人：李德柜
报告摘要： This paper studies multiple structural breaks in large covariance matrices of high-dimensional time series variables satisfying the approximate factor model structure. The breaks in the second-order structure of the common components are due to sudden changes in either factor loadings or covariance of latent factors, requiring appropriate transformation of the factor models to facilitate estimation of the (transformed) common factors and factor loadings via the classical principal component analysis. With the estimated factors and idiosyncratic errors, an easy-to-implement CUSUM-based detection technique is introduced to consistently estimate the location and number of breaks and correctly identify whether they originate in the common or idiosyncratic error components. The algorithms of Wild Binary Segmentation and Wild Sparsified Binary Segmentation are used to estimate the breaks in the common and idiosyncratic error components, respectively. Under some mild conditions, the asymptotic properties of the proposed methodology are derived with near-optimal rates (up to a logarithmic factor) achieved for the estimated change points. Some numerical studies are conducted to examine the finite-sample performance of the developed method and its comparison with other existing approaches. This is a joint work with Yu-Ning Li (Zhejiang University) and Piotr Fryzlewicz (London School of Economics).
报告人简介：李德柜，约克大学终身教授，2008年于浙江大学数学系取得理学博士学位，师从林正炎教授。随后在澳大利亚阿德莱德大学，莫纳什大学从事博士后研究，曾获2011年度澳大利亚优秀青年研究奖。现为约克大学数学系教授。李德柜教授研究兴趣集中在时间序列，半参数与非参数统计，面板数据，目前已发表论文42篇，其中15篇发表在Journal of Econometric, Annals of Statistics, Journal of the American Statistical Association, Journal of Business and Economic Statistics, Econometric Theory.他目前是Econometric and Statistics的副主编。
2. 报告题目：Robust Estimation for Large-dimensional Elliptical Factor Model
主讲人：何勇
报告摘要： In this talk, I briefly introduce some recent work on large-dimensional factor model analysis. From a robust perspective, we consider the Elliptical Factor Model (EFM) framework, in which we assume the latent factors and the idiosyncratic errors jointly follow elliptical distribution. We discuss how to estimate the factor number , the factor loading/ score matrices in the EFM framework and discuss some possible future directions.
报告人简介：何勇2017年毕业于复旦大学，山东财经大学引进人才，预聘副教授。研究方向为金融数据、医学数据的统计建模与推断。
