变点分析与极值指标和SV-t-GPD模型在原油极端风险测度中的应用  

Application Research on Extreme Risk of Crude Oil Market Based on Change Points Analysis,Extremal Index and SV-t-GPD Model

作　　者：李强[1,2] 邹晓峰[1] 

机构地区：[1]贵州财经大学金融学院,贵州贵阳550004 [2]重庆大学经管学院,重庆400030

出　　处：《数理统计与管理》2015年第4期592-602,共11页Journal of Applied Statistics and Management

基　　金：国家自然科学基金资助项目(70473107,71061003);2013年度贵州财经大学引进人才科研项目

摘　　要：引入VaR和ES的极值理论对BRENT原油现货市场的价格风险进行研究,运用变点理论对传统Hill估计方法的阈值选择进行了改进,定量选取阈值,相应降低了因主观判断失误引致的阈值选取误差。针对GPD模型要求金融时序服从独立同分布条件,引入两种方法来消除超阈值的局部相关性:一是结合GPD模型与极值指标;二是基于BRENT收益率序列采用SV-t模型进行过滤处理,建立起度量BRENT市场波动风险的动态VaR和ES模型。实证结果表明:针对BRENT市场极端风险,结合变点分析和极值指标构建的改进型阈值定量模型在风险测度方面具有有效性和精确性。相应地,构建的动态SV-t-GPD模型在测度BRENT极端风险方面具有稳健性。This paper introduces the extreme value theory of VaR（Value at Risk） and ES（Expected Shortfall） into the research on the price risk of BRENT crude oil spot market.A modified method using change point theory to improve the traditional Hill estimator method in threshold selection was proposed.The proposed can realize quantative threshold selection,reducing errors of threshold selection by subjective judgment.So two methods are used to remove the local relation.One is that extremal index is introduced to GPD（Generalized Pareto Distribution） model.The other is to filter BRENT returns series using SV-t model.The empirical results show that the introduction of change point and extremal index improve validity and veracity of VaR based on GPD model.Moveover,the dynamic SV-t-GPD model is robust in BRENT market earnings risk measureme.

关 键 词：变点分析 极值指标 SV-t-GPD模型 风险价值 

分 类 号：F830[经济管理—金融学] O212[理学—概率论与数理统计]