报告题目：Two approaches of analyzing matrix time series: matrix AR models and matrix factor models

    时间：2016年6月22（星期三）15：40-16：40

    地点：学院南路校区，学术会堂(603)

    报告人：陈嵘教授，中央财经大学长江学者讲座教授，美国罗格斯大学统计与生物统计系教授

    报告摘要：

In finance, economics and many other fields, observations in a matrix form are often observed over time. For example, many economic indicators are obtained in different countries over time. Various financial characteristics of many companies are recorded over time. Although it is natural to turn the matrix observations into a long vector then use standard vector time series models or factor analysis, it is often the case that the columns and rows of a matrix represent different sets of information that are closely interplayed. We propose two approaches: a matrix autoregressive model and a matrix factor model. Both approaches maintain and utilize the matrix structure to achieve greater dimensional reduction as well as easier interpretable structure. The research is ongoing. Preliminary results on estimation procedures and their theoretical properties as well as model validation procedures will be presented, along with some simulated and real examples.

    报告人简介：

    陈嵘教授1985年本科毕业于北京大学数学系，分别于1987年和1990年在美国卡耐基梅隆大学获得统计学硕士和统计学博士学位。曾经在美国德州农工大学统计系、伊利诺伊大学芝加哥分校商学院担任副教授、教授等教职，曾经担任美国国家自然科学基金委数学科学部项目主任，是北京大学光华管理学院商务统计与经济计量系的创立者和第一任系主任。现任及曾任多个统计学国际顶级专业期刊的副主编。主要研究领域包括：时间序列分析、蒙特卡罗等统计方法的理论研究、以及在经济与商务等领域中的应用。

[编辑]：孙颖