Analysis of oil price value at risk using Bayesian CAViaR model
CHEN Lei1, Anthony H. TU2, ZENG Yong1
1. School of Management and Economics, University of Electronic Science and Technology of China, Chengdu 610054, China; 2. New Huadu Business School, Minjiang University, Fuzhou 350108, China
Abstract：CAViaR model is usually used to estimate value at risk (VaR). However, it is difficult to estimate parameters and check model specification for CAViaR model. This paper develops Bayesian CAViaR model, adopts this model to estimate oil price VaR, and analyzes the roles of Bayesian CAViaR model in parameter estimation, model selection and VaR forecast. Using daily data of Brent crude oil price, the results show Bayesian CAViaR model can control estimation risk and model risk effectively, and has the better forecast performance than traditional CAViaR model. This paper also indicates oil price VaR has autoregressive effects and is affected by prior returns. The positive and negative returns have asymmetry effects on VaR. Asymmetric slope CAViaR model is the best model to describe the dynamics of oil price VaR.
陈磊, 杜化宇, 曾勇. 基于贝叶斯CAViaR模型的油价风险研究[J]. 系统工程理论与实践, 2013, 33(11): 2757-2765.
CHEN Lei, Anthony H. TU, ZENG Yong. Analysis of oil price value at risk using Bayesian CAViaR model. Systems Engineering - Theory & Practice, 2013, 33(11): 2757-2765.
[1] Engle R F, Mangaelli S. CAViaR: Conditional autoregressive value at risk by regression quantiles[J]. Journal of Business and Economic Statistics, 2004, 22(4): 367-381. [2] Manganelli S, Engle R F. A comparison of value-at-risk models in finance[M]//Szegö G. Risk Measures for the 21st Century, Wiley, Chichester UK, 2004: 123-144. [3] Bao Y, Lee T, Saltoğlu B. Evaluating the predictive performance of value-at-risk models in emerging markets: A reality check[J]. Journal of Forecasting, 2006, 25: 101-128. [4] Fuss R, Adams Z, Kaiser D G. The predictive power of value-at-risk models in commodity futures markets[J]. Journal of Asset Management, 2010, 11(4): 261-285. [5] Cabedo J, Moya I. Estimating oil price value at risk using the historical simulation approach[J]. Energy Economics, 2003, 25(3): 239-253. [6] Sadeghi M, Shavvalpour S. Energy risk management and value at risk modeling[J]. Energy Policy, 2006, 34(18): 3367-3373. [7] Fan Y, Jiao J L. An improved historical simulation approach for estimating 'value at risk' of crude oil price[J]. International Journal of Global Energy Issues, 2006, 25(1-2): 83-93. [8] 张意翔, 胥朝阳, 成金华. 基于VaR 方法的中国石油企业跨国并购的价格风险评价[J]. 管理学报, 2010, 7(3): 440-444.Zhang Y X, Xu Z Y, Cheng J H. Price risk evaluation for overseas merger and acquisition of Chinese oil companies based on VaR modeling[J]. Chinese Journal of Management, 2010, 7(3): 440-444. [9] Giot P, Laurent S. Market risk in commodity markets: A VaR approach[J]. Energy Economics, 2003, 25(5): 435-457. [10] Costello A, Asem E, Gardner E. Comparison of historically simulated VaR: Evidence from oil prices[J]. Energy Economics, 2008, 30(5): 2154-2166. [11] Hung J C, Lee M C, Liu H C. Estimation of value-at-risk for energy commodities via fat-tailed GARCH models[J]. Energy Economics, 2008, 30(3): 1173-1191. [12] Fan Y, Zhang Y J, Tsai H T, et al. Estimating ‘value at risk’ of crude oil price and its spillover effect using the GED-GARCH approach[J]. Energy Economics, 2008, 30(6): 3156-3171. [13] 冯春山, 吴家春, 蒋馥. 应用半参数法计算石油市场风险价值[J]. 湖北大学学报:自然科学版, 2004, 26(3): 213-217.Feng C S, Wu J C, Jiang F. To compute the oil market value at risk by applying semi-parametric approach[J]. Journal of Hubei University: Natural Science Edition, 2004, 26(3): 213-217. [14] 潘慧峰, 张金水. 用VaR度量石油市场的极端风险[J]. 运筹与管理, 2006, 15(5): 94-98.Pan H F, Zhang J S. Using value at risk to measure extreme risk in oil market[J]. Operations Research and Management Science, 2006, 15(5): 94-98. [15] 沈沛龙, 邢通政. 基于GARCH 模型的WTI和Brent原油价格风险分析[J]. 哈尔滨工业大学学报:社会科学版, 2010, 12(3): 88-93.Shen P L, Xing T Z. GARCH model based WTI and Brent crude oil price risk analysis[J]. Journal of HIT: Social Science Edition, 2010, 12(3): 88-93. [16] 沈沛龙, 邢通政. 国际油价波动与中国成品油价格风险研究[J]. 重庆大学学报:社会科学版, 2011, 17(1): 35-41.Shen P L, Xing T Z. Research on international oil price volatility and China's refined oil price risk[J]. Journal of Chongqing University: Social Science Edition, 2011, 17(1): 35-41. [17] 柴建, 郭菊娥, 龚利, 等. 基于Bayesian-SV-SGT模型的原油价格'Value at Risk'估计[J]. 系统工程理论与实践, 2011, 31(1): 8-17.Chai J, Guo J E, Gong L, et al. Estimating crude oil price 'Value at Risk' using the Bayesian-SV-SGT approach[J]. Systems Engineering — Theory & Practice, 2011, 31(1): 8-17. [18] Krehbiel T, Adkins L C. Price risk in the NYMEX energy complex: An extreme value approach[J]. Journal of Futures Markets, 2005, 25(4): 309-337. [19] Marimoutou V, Raggad B, Trabelsi A. Extreme value theory and value at risk: Application to oil market[J]. Energy Economics, 2009, 31(4): 519-530. [20] 余炜彬, 范英, 魏一鸣. 基于极值理论的原油市场价格风险VaR的研究[J]. 系统工程理论与实践, 2007, 27(8): 12-20.Yu W B, Fan Y, Wei Y M. Price risk in crude oil markets: A VaR approach of EVT[J]. Systems Engineering — Theory & Practice, 2007, 27(8): 12-20. [21] Huang D, Yu B, Fabozzi F, et al. CAViaR-based forecast for oil price risk[J]. Energy Economics, 2009, 31(4): 511-518. [22] 王新宇, 宋学锋. 间接TARCH-CAViaR模型及其MCMC 参数估计与应用[J]. 系统工程理论与实践, 2008, 28(9): 46-51.Wang X Y, Song X F. Indirect TARCH-CAViaR model and its parameter estimation by MCMC method with an application[J]. Systems Engineering — Theory & Practice, 2008, 28(9): 46-51. [23] 王新宇, 宋学锋. 基于贝叶斯分位数回归的市场风险测度模型与应用[J]. 系统管理学报, 2009, 18(1): 40-48.Wang X Y, Song X F. Measure market risk based on Bayesian quantile regression model with an application[J]. Journal of Systems and Management, 2009, 18(1): 40-48. [24] Gerlach R, Chen C, Chan N. Bayesian time-varying quantile forecasting for value-at-risk in financial markets[J]. Journal of Business and Economic Statistics, 2011, 29(4): 481-492. [25] Yu K, Zhang J. A three-parameter asymmetric Laplace distribution and its extension[J]. Communications in Statistics — Theory and Methods, 2005, 34: 1867-1879. [26] Ntzoufras I. Bayesian modeling using WinBUGS[M]. John Wiley & Sons, Inc, 2009. [27] Kass R, Raftery A. Bayes factors[J]. Journal of American Statistical Association, 1995, 90(430): 773-795. [28] Berkowitz J, Christoffersen P, Pelletier D. Evaluating value-at-risk models with desk-level data[J]. Management Science, 2011, 57(2): 2213-2227. [29] Hendricks D. Evaluation of value-at-risk models using historical data[J]. Economic Policy Review, 1996, 2: 39-69. [30] Reed C, Yu K. A partially collapsed Gibbs sampler for Bayesian quantile regression[R]. Working Paper, Brunel University, 2009.
2013, Vol. 33 
