基于价格持续时间的中国股市日内风险价值预测  

Forecasting Intraday Value-at-Risk Based on Price Duration in China Stock Market

作　　者：鲁万波[1] 王卫东[2] 

机构地区：[1]西南财经大学统计学院,四川成都610074 [2]西南财经大学金融学院,四川成都610074

出　　处：《数理统计与管理》2012年第3期527-536,共10页Journal of Applied Statistics and Management

基　　金：教育部人文社会科学研究项目(09YJC910009);西南财经大学"211工程"三期青年教师成长项目(211QN09020);西南财经大学"211工程三期"统计学重点学科建设项目资助

摘　　要：基于高频数据度量日内交易活动的风险是目前日内金融数据与风险管理中极具挑战性的研究课题之一。本文从实时交易的角度,使用中国股市分笔交易数据,基于价格持续时间的自回归条件持续时间(ACD)模型,研究日内不规则交易数据的风险测度,利用日内不等间隔波动模型估计了日内交易的即时条件波动率,对日内不等间隔风险价值进行了预测和检验。实证结果发现日内不等间隔风险价值模型能够比较好的刻画日内交易风险,股票投资者和市场监管者可以基于该工具对日内风险做出合理的预测,达到止损避险和控制风险的目的。It is one of the challenging topics to measure the risk of intraday trading activity based on high frequency data in risk management. From the perspective of real-time transactions, this paper uses the tick-by-tick data in China stock market to study the risk measurement for the irregular trading data based on the ACD model of price duration. The instantaneous conditional volatility is estimated by using intraday irregular volatility model, which is applied to forecast the irregularly spaced intraday Value-at-Risk and carry out the back testing. The empirical results show that the irregularly spaced intraday Value-at-Risk model is good for forecasting the maximum losses in the different probability of loss.

关 键 词：价格持续时间 风险价值 超高频数据 ACD模型 

分 类 号：C81[社会学—统计学] O212[理学—概率论与数理统计]