讲座题目：Covariance Regression Analysis

时  间：4月9日15:30-17:00

地  点：博学楼520教室

主讲人：邹韬(澳大利亚国立大学助理教授)

举办方：金融学院

主讲人简介：

邹韬，澳大利亚国立大学助理教授，北京大学光华管理学院经济学博士，曾是澳大利亚莫纳什大学、美国爱荷华州立大学访问学者；主要从事金融统计和金融计量等方面的教学与研究工作；曾在Journal of Econometrics、Journal of Business and Economic Statistics、Journal of American Statistical Association等国际顶级期刊发表多篇论文。

论文摘要:

In the area of empirical finance with responses being returns of stocks, the covariance matrix of responses plays an important role for the risk management and portfolio allocation (see, e.g., Markowitz 1952; Jagannathan and Ma 2003; Kan and Zhou 2007). Many researchers have shown that such a covariance matrix is affected by firms’ fundamentals (Roll 1988; Chan, Karceski, and Lakonishok 1998, 1999). This article introduces covariance regression analysis for a p-dimensional response vector. The proposed method explores the regression relationship between the p-dimensional covariance matrix and its associated relevant explanatory variables. We study three types of estimation for this covariance regression model and we obtain the high dimensional and large sample properties of the corresponding covariance matrix estimators. Simulation experiments are presented to demonstrate the performance of both regression and covariance matrix estimates. An example is analyzed from the Chinese stock market to illustrate the usefulness of the proposed covariance regression model.