主 題：Spillover effect of information arrivals in security trading
Abstract: In the standard bivariate mixture distribution model for a single security market, the flow of information arrivals determines the dynamics of stock price volatility and trading volume. Due to the contemporaneous and cross-sectional dependence of information arrivals among several securities, a spillover effect might occur. To model such effect, we extend the mixture distribution hypothesis to the case of multiple securities, and use a latent vector autoregressive process to characterize information arrivals. We further use a stochastic approximation algorithm with Markov chain Monte Carlo method to estimate the dynamics of information arrivals. We apply our models and inference procedure to analyze markets of multiple securities and show the spillover effects in them are significant.
State University of New York, Stony Brook, USA.
Prof. Xing graduated from Stanford’s statistics department with a doctorate in 2005. He taught at Columbia’s statistics department fro two years and then moved to Stony Brook University in 2008. He also served as a consultant for the office of Chief Economist and Vice President at the World Bank during May 2010-June 2011. His research focuses on (i) change-points detection, parameter estimation and adaptive control problems and their applications in engineering, economics and genetics; (ii) statistical models and methods in financial econometrics and engineering; and (iii) time series modeling.His work includes papers published in the Annals of Applied Statistics, Statistica Sinica, Journal of American Statistical Association, Sequential Analysis, and Journal of Banking and Finance. He is co-author, with T.L. Lai of Stanford, of two major textbooks on financial statistics and risk management.
時間：2017年7月10日（星期一）🧑🏽🦳，14:00-16:00
返回頂部
