高频数据下基于VaR模型的我国金融市场研究  

Study on the High Frequency Data of the Financial Market in China by Using the VaR Method

作　　者：魏正元[1] 霍艳[1] 李文[1] 

机构地区：[1]重庆理工大学数学与统计学院,重庆400054

出　　处：《重庆理工大学学报（自然科学）》2014年第8期126-131,共6页Journal of Chongqing University of Technology：Natural Science

基　　金：重庆市自然科学基金资助项目(cstc2012jjA00018);重庆市教委科学技术研究项目(KJ130810);重庆市教委高教研究项目(1203053)

摘　　要：基于"国内外市场间的异构性质"和"传统的风险模型是否能有效地应用于今天的高频金融市场"的考虑,设计了历史模拟法、蒙特卡洛模拟法和极值理论方法,依次对深市的"宝安地产、长江证券"与沪市的"沪深300"3支个股进行对比研究,并进行失败率检验。结果发现:国内两大金融市场并无明显差异;历史模拟法和蒙特卡洛模拟法并不能对风险值进行有效的估计;极值理论可以对国内高频金融市场进行有效的风险度量。同时实验的结果也反向论证了模型适用的前提条件的重要性。With the rapid development of storage and computing technology,high frequency data with real-time transaction acquisition market become true. In order to study the relations between the two major domestic financial market,we choose two stocks named as＂Changjian zhengquan＂and＂Bao＇an dichan＂from Shanghai market and＂Hushen 300＂from Shenzhen market. Monte Carlo simulation method,extreme value and historical simulation method will be selected to analysis each of the above three stock,then tested the failure rate. The results show that there is no remarkable difference between Chinese two financial market; the historical simulation method and Monte Carlo simulation method is not effective for risk estimation; extreme value theory can effectively measure the risk of domestic high-frequency Market.

关 键 词：历史模拟法 蒙特卡洛模拟法 在值风险(VaR) 极值理论 

分 类 号：O21[理学—概率论与数理统计]