金融资产收益率分布具有"尖峰"、"肥尾"、"有偏"、"非对称"等典型事实,传统的正态分布、t分布、SKST分布无法完全描述这些特征,影响了以收益率分布设定为基础之一的参数法VaR模型度量的效果。近年来,理论界提出了AEPD、AST、ALD等分布来改善对金融资产收益率分布的描述。本文以沪深300指数为例,比较和分析了这些分布对金融资产收益率典型事实特征的描述及其在VaR度量效果上的差异。研究表明并非捕捉金融资产收益率分布典型事实越多的模型测度风险的效果越好:AEPD、 AST、ALD分布能较好地描述金融资产收益率的典型特征,但是在风险度量效果上却只能证明AEPD、AST分布绝对优于正态分布,而与SKST分布相比无明显差异; ALD分布在度量空头VaR时效果甚至比正态分布更差,但在计算低分位水平下的多头VaR值时却明显优于其他分布。
The financial asset's yield distribution has some typical characteristics such as "leptokurtic", "fat tail","skewed" and "Asymmetry", but the traditional normal distribution, t distribution, SKST distribution cannot fully describe these characteristics, which has influenced the efficiency of parameter method of VaR models based on them. In recent years, the theoretical circle has proposed AEPD, AST, ALD and other distributions to improve the description of the financial asset's yield distribution. The CSI 300 index is choosed to analysis and compare the description on the typical characteristics of financial asset's yield distribution and also the measurement differences of VaR models based on them. The empirical results show that the more typical characteristics of financial asset's yield distribution the model captures, the better to measure VaR. It only proves that the measurement effects of the VaR models based on AEPD, AST distribution are absolutely better than the model based on normal distribution, but have no obvious difference with model based SKST distribution; Model based on ALD performs even worse when measuring the short VaR but performs best when measuring the long VaR under the low quantile.
[1] Manganelli S, Engle R F. Value at risk models in finance[R]. European Central Bank Working Paper, 2001.
[2] Engle R F. Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation [J]. Econometrica, 1982,50(4): 987-1007.
[3] Bollerslev T. Generalized autoregressive conditional heteroskedasticity [J].Journal of Econometrics,1986,31(3):307-327.
[4] Ding Zhuanxin, Granger C W J, Engle R F. A long memory property of stock market returns and a new model [J].Journal of Empirical Finance,1993,1(1):83-106.
[5] Nelson D B. Conditional heteroskedasticity in asset returns: A new approach [J].Econometrica,1991,59(2): 347-370.
[6] Glosten L R. Jagannathan R, Runkle D E. On the relation between the expected value and the volatility of the nominal excess return on stocks[J]. The Journal of Finance, 1993,48(5): 1779-1801.
[7] Baillie R T, Bollerslev T, Mikkelsen H O. Fractionally integrated generalized autoregressive conditional heteroskedasticity[J]. Journal of Econometrics, 1996,74(1): 3-30.
[8] Mabrouk S, Saadi S. Parametric value-at-risk analysis: Evidence from stock indices[J]. The Quarterly Review of Economics and Finance, 2012,52(3): 305-321.
[9] Orhan M, Koksal B. A comparison of GARCH models for VaR estimation[J]. Expert Systems with Applications, 2012,39(3): 3582-3592.
[10] Bollerslev T. A conditional heteroskedastic time series model for speculative prices and rates of return[J]. The Review of Economics and Statistics, 1987,69(3): 542-547.
[11] Hansen B E. Autoregressive conditional density estimation[J]. International Economic Review, 1994,35(3): 705-730.
[12] Zhu Dongming, Galbraith J W. A generalized asymmetric student-t distribution with application to financial econometrics[J]. Journal of Econometrics, 2010,157(2):297-305.
[13] Zhu Dongming, Zinde-Walsh V. Properties and estimation of asymmetric exponential power distribution[J]. Journal of Econometrics, 2009,148(1): 86-99.
[14] Nadarajah S, Teimourib M.On the characteristic function for asymmetric exponential power distributions[J]. Econometric Reviews,2012,31(4): 475-481.
[15] Lu Zudi, Huang Hai,Gerlach R. Estimating value at risk: From JP Morgan's Standard-EWMA to Skewed-EWMA Forecasting. OME Working Paper, the University of Sydney,2010.
[16] Zhu Dongming, Galbraith J W. Forecasting expected shortfall with a generalized asymmetric student-t distribution. Working Paper, 2009.
[17] Chen Qian, Gerlach R, Lu Zudi. Bayesian Value-at-Risk and expected shortfall forecasting via the asymmetric Laplace distribution[J]. Computational Statistics and Data Analysis, 2010,56(11):3498-3516.
[18] 徐炜,黄炎龙. GARCH模型与VaR的度量研究[J]. 数量经济技术经济研究,2008,25(1):120-132.
[19] 林宇,卫贵武,魏宇,等. 基于Skew-t-FIAPARCH的金融市场动态分险VaR测度研究[J]. 中国管理科学,2009,17(6):17-24.
[20] Kupiec P H. Techniques for verifying the accuracy of risk measurement models[J]. Journal of Derivatives, 1995,3(2):173-184.
[21] Engle R F, Manganelli S. CAViaR: Conditional autoregressive value at risk by regression quantiles[J]. Journal of Business & Economic Statistics, 2004,22(4):367-381.
