估计带跳资产价格的时点波动时,需要用门限过滤方法消除跳的影响。在有限样本下,门限过滤会产生错滤偏误和漏虑偏误,降低估计精度。跳错滤产生的偏误可通过对错滤样本进行补足的方法进行纠偏,但由于发生时点未知,跳漏滤产生的偏误无法纠正,只能通过估计量设计来减少漏滤偏误。本文首次提出基于门限双幂变差的时点波动估计量,采用核平滑方法对资产价格时点波动进行非参数估计,有效减少跳错滤导致的偏误。采用随机阵列极限理论,本文证明了估计量的一致性和渐进正态性,在分析有限样本偏误的基础上,给出估计量的纠偏方法。蒙特卡洛模拟表明,本文给出的估计量,漏滤偏误明显小于基于二次变差构造的估计量,对时点波动估计的性质具有实质改进。采用Kupiec动态VaR精度检验对沪深300指数的实证分析表明,本文给出的时点波动估计更能描述资产收益的波动特征。
The threshold jump-annihilating method to estimate spot volatility of jump-diffusion asset price processes can miss the small jumps and bring about upward bias. In this paper, a new spot volatility estimator of asset prices is proposed based on bipower variation that reduces significantly finite-sample upward bias from jump-filtering-missing. The consistency and asymptotic normality is established. An extensive Monte Carlo simulation shows that the estimator in the paper outperforms the others in literature. The empirical study using Kupiec test based on sample from CSI300 shows that our spot volatility estimator can capture the feather of market risk more accurately.
[1] Fan Jianqing, Wang Yazhen. Spot volatility estimation for high-frequency data[J]. Statistics and its Interface, 2008, 1(2):279-288.
[2] Kristensen D. Nonparametric filtering of the realized spot volatility: A kernel-based approach[J]. Econometric Theory, 2010, 26(1): 60-93.
[3] Bandi M, Reno R. Time-varying leverage effects[J]. Journal of Econometrics, 2012, 169(1):94-113.
[4] Bollerslev T, Todorov V. Estimation of jump tails[J]. Econometrica, 2011, 79(6):1727-1783.
[5] Ait-Sahalia Y, Fan Jianqing, Li Yazhen. The leverage effect puzzle: Disentangling sources of bias at high frequency[J]. Journal of Financial Economics, 2013, 109(1):224-249.
[6] 沈根祥. 沪深300指数跳的逐点检验及动态分析[J]. 中国管理科学, 2012, 20(1):43-50.
[7] 沈根祥. 带Poisson跳和杠杆效应的资产价格时点波动非参数估计[J]. 数量经济技术经济研究, 2012, 29(12):82-96.
[8] Mancini C. Non-parametric threshold estimation for models with stochastic diffusion coefficient and jumps[J]. Scandinavian Journal of Statistics, 2009, 36(2):270-296.
[9] Corsi F, Pirin D, Reno R. Threshold bipower variation and the impact of jumps on volatility forecasting[J]. Journal of Econometrics, 2010, 159(2):276-288.
[10] 陈浪南, 孙坚强. 股票市场资产收益的跳跃行为研究[J]. 经济研究, 2010, (4):54-66.
[11] 刘志东, 陈晓静. 无限活动纯跳跃Levy金融资产价格模型及其CF-CGMM参数估计与应用[J]. 系统管理学报, 2010, 19(4):428-438.
[12] 王春峰, 姚宁, 房振明, 等. 中国股市已实现波动率的跳跃行为研究[J]. 系统工程, 2008, 26(2):1-6.
[13] 陈国进, 王占海. 我国股票市场连续性波动与跳跃性波动实证研究[J]. 系统工程理论与实践, 2010, 30(9):1554-1562.
[14] 杨科, 陈浪南. 基于C-TMPV的中国股市高频波动率的跳跃行为研究[J]. 管理科学, 2011, 24(2):103-112.
[15] Lee S S, Mykland P A. Jumps in nancial markets:A new nonparametric test and jump dynamics[J]. Review of Financial Studies, 2008, 21(6): 2535-2563.
[16] 杨科, 田凤平, 林洪. 跳跃的估计、股市波动率的预测以及预测精度评价[J]. 中国管理科学, 2013, 21(3):50-60.
[17] Barndorff-Nielsen O E, Shephard N. Econometrics of testing for jumps in financial economics using bipower variation[J]. Journal of Financial Econometrics, 2006, 4(1):1-30.
[18] Mykland P A, Zhang Lan. The econometrics of high-frequency data[M]// Kessler M, Lindner A, Sorensen M. Statistical methods for stochastic differential equations, United Kingdom:Talor & Francis, LLC, 2012.
[19] Jacod J, Shiryaev N. Limit theorems for stochastic processes[M]. Berlin:Springer Science & Business Media, 2003.
[20] Barndorff-Nielsen O, Graversen S, Jocod J, et al. A central limit theorem for realized power and bipower variations of continuous martingales[M]//Kabanov Y, Lipster R, Stoyanov J. From stochastic calculus to mathematical finance. Heidelberg:Springer, 2006:33-68.
[21] Kupiec P. Techniques for verifying the accuracy of risk measurement models[J]. Journal of Derivatives, 1995, 3(2):73-84.
