【主 题】 Cross-Sectional Dispersion of Risk in Trading Time

【报告人】 Viktor Svetlinov Todorov, 教授

Kellogg School of Management, Northwestern University

【时 间】 2019年8月19日（星期一）15:30-16:15

【地 点】 上海财经大学统计与管理学院大楼1208会议室

【摘 要】We study the temporal behavior of the cross-sectional distribution of market betas using a large panel of high-frequency returns. The asymptotic setup is one in which the sampling frequency of the returns increases to infinity, with the time span of the data remaining fixed, and the cross-sectional dimension of the panel is either fixed or increases to infinity. We derive a finite-dimensional Central Limit Theorem for a measure of cross-sectional beta dispersion at fixed points in time, which can be used to test whether this quantity changes during the trading hours. We further derive a functional Central Limit Theorem for the dispersion statistics which allows us to test whether the dispersion in betas as a function of the time of the trading day changes across days. We extend the above analysis by developing inference techniques for the entire cross-sectional beta distribution at fixed points in time. Upon implementing the developed econometric tools on data on the constituents of the S&P 500 stock market index, we find that the dispersion in betas is high at market open and it gradually declines over the trading day, reaching its low around market close (which is less than half of its value at market open). The shape of the intraday pattern in beta dispersion has changed over time and it also looks different on days with pre-scheduled economic announcements versus days without such events. We show that the documented intraday variation in market betas is a source of priced risk.

【嘉宾简介】Viktor Todorov is Harold H. Hines Jr. Professor of Risk Management and Professor of Finance at the Kellogg School of Management, Northwestern University. Professor Todorov is a Fellow of the Society for Financial Econometrics and the Journal of Econometrics. His research interests are in the areas of theoretical and empirical asset pricing, econometrics and applied probability. He has published extensively in these fields. His recent work focuses on the robust estimation of asset pricing models using high-frequency financial data as well as the development and application of parametric and nonparametric methods of inference for studying risks and risk premia using derivatives markets data. He currently serves as a Co-Editor for Econometric Theory, and is on the editorial board of a number of leading academic journals, including Econometrica and the Journal of Econometrics. He received his PhD in Economics from Duke University in 2007.

【主持人】张志远