基于贝叶斯滤波的股指动态结构特征研究

运筹与管理 ›› 2011, Vol. 20 ›› Issue (6): 147-156.

基于贝叶斯滤波的股指动态结构特征研究

郝立亚¹, 朱慧明¹, 虞克明²

1.湖南大学工商管理学院, 湖南长沙 410082;
2.Brunel大学数学系, 英国伦敦 UB83PH

收稿日期:2010-01-13 出版日期:2011-12-25
作者简介:郝立亚(1983-),女,河北邯郸人,博士研究生,研究方向为金融工程与风险管理,金融计量经济模型;朱慧明(1966-),男,湖南湘潭人,教授,博士生导师,研究方向为金融工程与计量经济模型,质量工程与可靠性管理,金融计算与仿真分析;虞克明,英国Brunel大学数学系教授,研究方向为方贝叶斯分位回归方法、金融风险管理。
基金资助:
国家自然科学基金资助项目(70771038,71031004);教育部留学回国人员科研启动基金资助项目(教外司留[2010]609);湖南省自然科学基金创新群体项目(09JJ702);教育部长江学者与发展创新团队项目

Bayesian Filtering Method for Stock Index Dynamic Characteristics with Regime-Switching

HAO Li-ya¹, ZHU Hui-ming¹, YU Ke-ming²

1. College of Business Administration, Hunan University, Changsha 410082, China;
2. Department of Mathematical Science, London UB83PH, UK

Received:2010-01-13 Online:2011-12-25

摘要/Abstract

摘要： 针对股指波动所具有的动态结构信息特征,在状态空间建模理论的框架下,将服从Markov过程的潜在波动状态变量引入状态方程,同时在观测方程中考虑极值点的影响,构造出一类非高斯Markov随机波动状态空间模型。针对传统的MCMC方法对该类模型估计时效率低下的缺陷,设计了基于序贯Monte Carlo方法的贝叶斯滤波算法进行仿真分析,并且从算法效率和准确性方面对两种方法进行了比较。通过对沪深300股指波动的实证研究表明:对于一类非线性非高斯状态空间模型,贝叶斯滤波算法在保证估计精度的同时较MCMC方法更加有效率,能够有效刻画股指波动的动态结构特征。

关键词: 仿真分析, 随机波动, 贝叶斯方法, 滤波

Abstract: To demystify the regime-switching information hidden in the stock index, a kind of non-Gauss nonlinear state space model is brought forward to allow for fat-tails in the mean equation innovation to capture the changes in volatility caused by economic forces and for Markov switching process in the latent volatility equation. In the sequential Bayesian perspective we provide a Bayesian filtering algorithm for parameter learning and state filtering of the model. In empirical study, the regime-switching information based on the stochastic volatility model is demystified by using this algorithm on CSI300 index spots open price futures. In the applications, we compare the algorithm with MCMC method in both efficiency and accuracy. We find that the Bayesian filtering algorithm outperforms existing MCMC.

中图分类号:

F830.91

郝立亚, 朱慧明, 虞克明. 基于贝叶斯滤波的股指动态结构特征研究[J]. 运筹与管理, 2011, 20(6): 147-156.

HAO Li-ya, ZHU Hui-ming, YU Ke-ming. Bayesian Filtering Method for Stock Index Dynamic Characteristics with Regime-Switching[J]. Operations Research and Management Science, 2011, 20(6): 147-156.

参考文献

[1] Taylor S J. Modelling financial time series[M]. New York : Wiley and Sons, 1986.
[2] Kim S, Shephard N, Chib S. Stochastic volatility: likelihood inference and comparison with ARCH models[J]. Review of Economic Studies, 1998, 65(3): 361-393.
[3] Geweke J. Contemporary bayesian econometrics and statistics[M]. New Jersey: John Wiley &Sons, 2005.
[4] So M K P, Lam K, Li W K. A stochastic volatility model with markov switching[J]. Journal of Business Econometric Statistics, 1998, 16(2): 244-253.
[5] Eraker B, Johannes M S, Polson N G. The impact of jumps in volatility and returns[J]. The Journal of Finance, 2003, 58: 1269-1300.
[6] Madhu K, Raul S. Regime-switching stochastic volatility and short-term interest rates[J]. Journal of Empirical Finance, 2004, 11(3): 309-329.
[7] Harvey A C, Koopman S J, Shephard N. State space and unobserved component models[M]. Cambridge: Cambridge University Press, 2004.
[8] Jacques J F, Koopman S J. An introduction to state space time series analysis[M]. New York: Oxford University Press, 2007.
[9] Jacquier E, Polson N G, Rossi P E. Bayesian analysis of stochastic volatility models(with discussion)[J]. Journal of Business and Economic Statistics, 1994, 12(3): 371-417.
[10] Chiba S, Nardari F, Shephard N. Markov Chain monte carlo methods for stochastic volatility models[J]. Journal of Econometrics, 2002, 108(2): 281-316.
[11] 朱慧明,李峰,杨锦明.基于MCMC模拟的贝叶斯厚尾金融随机波动模型分析[J].运筹与管理,2007,16(4):111-115.
[12] Fearnhead P. Markov chain monte carlo, sufficient statistics, and particle filters[J]. Journal of Computational and Graphical Statistics, 2002, 11(4):848-862.
[13] Fearnhead P, Clifford P. On-line inference for hidden Markov models via particle filters[J]. Journal of the Royal Statistical Society B, 2003, 65: 887-899.
[14] Doucet A, de Freitas J, Gordon N. Sequential monte carlo methods in practice[C]. New York: Springer, 2001.
[15] Chopin N. A sequential particle filter method for static models[J]. Biometrika, 2002, 89: 539-552.
[16] Storvik G. Particle filters in state space models with the presence of unknown static parameters[J]. IEEE Trans of Signal Processing, 2002, 50: 281-289.
[17] Stroud Jonathan, Nicholas Polson, Peter Muller. Practical filtering for stochastic volatility models[A]. Harvey A. State Space and Unobserved Components models[C]. New York: Oxford University Press, 2004. 236-247.
[18] Drew D C. Analysis of filtering and smoothing algorithms for Lévy-driven stochastic volatility models[J]. Computational Statistics & Data Analysis, 2008, 52(6): 2863-2876.
[19] Carvalho C M, Lopes H F. Simulation-based sequential analysis of Markov switching stochastic volatility models[J]. Computational Statistics and Data Analysis, 2007, 51: 4526-4542.
[20] Del Moral P, Doucet A, Jasra A. Sequential monte carlo samplers[J]. Journal of Royal Statistical Society B, 2006, 68: 411-436.
[21] Del M P, Doucet A, Jasra A. Sequential monte carlo for bayesian computation[J]. Bayesian Statistics, 2007, 8(1): 1-34.
[22] Liu J, West M. Combined parameters and state estimation in simulation based filtering[A]. Eds A, Doucet N, de Freitas, N Gordon. Sequential Monte Carlo Methods in Practice[C]. New York: Springer-Verlag, 2001. 197-223.