基于多分形理论的动态VaR预测模型研究

中国管理科学 ›› 2012, Vol. 20 ›› Issue (5): 7-15.

基于多分形理论的动态VaR预测模型研究

魏宇

西南交通大学经济管理学院, 四川成都 610031

收稿日期:2011-04-24 修回日期:2012-07-18 出版日期:2012-10-29 发布日期:2012-10-27
基金资助:
国家自然科学基金资助项目(70771097,71071131,71090402);教育部创新团队发展计划(PCSIRT0860);中央高校基本科研业务费专项资金资助项目(SWJTU11ZT30,SWJTU11CX137)

Forecasting Model for Dynamic Value-at-Risk Based on Multifractal Theories

WEI Yu

School of Economics &Management, Southwest Jiaotong University, Chengdu 610031, China

Received:2011-04-24 Revised:2012-07-18 Online:2012-10-29 Published:2012-10-27

摘要/Abstract

摘要： 经济物理学(econophysics)的大量研究表明,金融市场的波动具有复杂的多分形(multifractal)特征,因此准确地测度和预测市场波动,对金融风险管理工作的意义重大。在已有多分形波动率(multifractal volatility)测度及其模型应用基础上,以上证综指10年的高频数据为对象,提出了基于多分形波动率的样本外动态风险价值(out-of-sample dynamic VaR)预测法。通过两种规范的后验分析(backtesting)结果表明,与8种主流的线性和非线性GARCH族模型相比,在高风险水平上,基于多分形波动率测度的VaR模型明显具有更高的样本外动态风险预测精度。

关键词: 多分形, 波动率, 样本外动态风险价值, 预测, Backtesting

Abstract: Much literature in Econophysics reveals that the volatility in financial markets presents multifractal features. Thus, measuring and forecasting the market volatility accurately is very important for financial risk management. Based on the earlier research of multifractal volatility and its model, an out-of-sample dynamic VaR forecasting method is proposed in this paper. The empirical results on two backtesting techniques show that, on high-risk levels, VaR model based on multifractal volatility produces much better out-of-sample VaR forecasts than eight popular linear and nonlinear GARCH models.

Key words: multifractal, volatility, out-of-sample dynamic VaR, forecasting, backtesting

中图分类号:

F224

魏宇 . 基于多分形理论的动态VaR预测模型研究[J]. 中国管理科学, 2012, 20(5): 7-15.

WEI Yu. Forecasting Model for Dynamic Value-at-Risk Based on Multifractal Theories[J]. Chinese Journal of Management Science, 2012, 20(5): 7-15.

参考文献

[1] Matteo T D. Multi-scaling in finance [J]. Quantitative Finance, 2007, 7(1): 21-36.
[2] Mandelbrot B B. A multifractal walk down wall street [J]. Scientific American, 1999, 280(2): 70-73.
[3] Stanley H E, Amaral L A N, et al. Similarities and differences between physics and economics [J]. Physica A, 2001, 299(1-2): 1-15.
[4] Bacry E, Delour J, et al. Modeling financial time series using multifractal random walks [J]. Physica A, 2001, 299(1-2): 84-92.
[5] Calvet L, Fisher A. Multifractality in asset returns: theory and evidence [J]. Review of Economics and Statistics, 2002, 84(3): 381-406.
[6] Xu Zhaoxia, Gencay R. Scaling, self-similarity and multifractality in FX markets [J]. Physica A, 2003, 323: 578-590.
[7] 何建敏,常松.中国股票市场多重分形游走及其预测[J].中国管理科学,2002,10(3):11-17.
[8] 张永东,毕香秋.中国股票市场多标度行为的实证分析[J].预测,2002,21(4):56-59.
[9] 胡雪明,宋学锋.沪深股票市场的多重分形分析[J].数量经济技术经济研究,2003,(8):124-127.
[10] 施锡铨,艾克凤.股票市场风险的多重分形分析[J].统计研究,2004,(9):33-36.
[11] 魏宇,黄登仕.金融市场多标度分形现象及与风险管理的关系[J].管理科学学报,2003,6(1):87-91.
[12] 魏宇,黄登仕.基于多标度分形理论的金融风险测度指标研究[J].管理科学学报,2005,8(4):50-59.
[13] 周孝华,宋坤,等.股票价格持续大幅度波动前后多重分形谱的异常及分析[J].管理工程学报,2006,20(2):92-96.
[14] 苑莹,庄新田.股票市场多重分形性的统计描述[J].管理评论,2007,19(12):3-8.
[15] Faruk S, Ramazan G. Intraday dynamics of stock market returns and volatility [J]. Physica A, 2006, 367: 375-387.
[16] 魏宇.金融市场的多分形波动率测度、模型及其SPA检验[J].管理科学学报,2009,12(5):88-99.
[17] 魏宇.多分形波动率测度的VaR计算模型[J].系统工程理论与实践,2009,29(9):7-15.
[18] Swanson N R, Elliott G, et al. Predictive methodology and application in economics and finance: volume in honor of the accomplishments of Clive W.J. Granger [J]. Journal of Econometrics, 2006, 135(1-2): 1-9.
[19] Ashely R, Granger C W J, et al. Advertising and aggregate consumption: an analysis of causality [J]. Econometrica, 1980, 48(5): 1149-1167.
[20] Lo A W, MacKinlay A C. Data-snooping biases in tests of financial asset pricing models [J]. Review of Financial Studies, 1990, 3(3): 431-467.
[21] Foster F D, Smith T, et al. Assessing goodness-of-fit of asset pricing models: the distribution of the maximal R² [J]. Journal of Finance, 1997, 52(2): 591-607.
[22] Koopman S J, Jungbacker B, et al. Forecasting daily variability of the S&P100 stock index using historical, realized and implied volatility measurements [J]. Journal of Empirical Finance, 2005, 12(3): 445-475.
[23] Andersen T G, Bollerslev T, et al. The distribution of realized stock return volatility [J]. Journal of Financial Economics, 2001, 61(1): 43-76.
[24] Cont R. Empirical properties of asset returns: stylized facts and statistical issues [J]. Quantitative Finance, 2001, 1(2): 223-236.
[25] Hansen P R, Lunde A. A forecast comparison of volatility models: does anything beat a GARCH(1,1)?[J]. Journal of Applied Econometrics, 2005, 20(7): 873-889.
[26] 龚锐,陈仲常,等.GARCH族模型计算中国股市在险价值(VaR)风险的比较研究与评述[J]. 数量经济技术经济研究,2005,(7):67-81.
[27] Kupiec P H. Techniques for verifying the accuracy of risk measurement models [J]. Journal of Derivatives, 1995,3(2): 73-84.
[28] Engle R, Manganelli S. CAViaR: conditional autoregressive value at risk by regression quantiles [J]. Journal of Business and Economic Statistics, 2004, 22(4): 367-381.
[29] Kang S H, Kang S M, et al. Forecasting volatility of crude oil markets [J]. Energy Economics, 2009, 31(1): 119-125.
[30] Wei Yu, Wang Yudong, Huang Dengshi. Forecasting crude oil market volatility: further evidence using GARCH-class models [J]. Energy Economics, 2010, 32(6): 1477-1484.
[31] Angelidis T, Benos A, et al. The use of GARCH models in VaR estimation [J]. Statistical Methodology, 2004, 1(1-2): 105-128.
[32] So M K P, Yu P L H. Empirical analysis of GARCH models in value at risk estimation [J]. Journal of International Financial Markets, Institutions and Money, 2006, 16(2): 180-197.
[33] 周炜星.金融物理学导论[M].上海:上海财经大学出版社,2007.
[34] Jiang Zhiqiang, Zhou Weixing. Multifractality in stock indexes: fact or fiction? [J]. Physica A, 2008, 387(14): 3605-3614.