Lévy过程驱动的非高斯OU随机波动模型及其贝叶斯参数统计推断方法研究

doi:10.16381/j.cnki.issn1003-207x.2015.08.001

中国管理科学 ›› 2015, Vol. 23 ›› Issue (8): 1-9.doi: 10.16381/j.cnki.issn1003-207x.2015.08.001

• 论文 • 下一篇

Lévy过程驱动的非高斯OU随机波动模型及其贝叶斯参数统计推断方法研究

刘志东, 刘雯宇

中央财经大学管理科学与工程学院, 北京 100081

收稿日期:2014-07-25 修回日期:2014-12-24 出版日期:2015-08-20 发布日期:2015-08-19
作者简介:刘志东(1973-),男(汉族),内蒙古赤峰人,中央财经大学管理科学与工程学院博士,教授,博士内蒙古赤峰人,生导师,研究方向:金融工程与金融计量.
基金资助:
国家自然科学基金资助项目(71271223;70971145);教育部新世纪优秀人才支持计划项目(NCET-13-1054); 中央财经大学青年创新团队项目;中央财经大学博士研究生重点选题支持计划。

The Non Ornstein-Uhlenbeck Models Driven by the General Lévy Process and Its Bayesian Inference

LIU Zhi-dong, LIU Wen-yu

School of Management Science and Engineering, Central University of Finance and Economics, Beijing, 100081, China

Received:2014-07-25 Revised:2014-12-24 Online:2015-08-20 Published:2015-08-19

摘要/Abstract

摘要： 本文采用CGMY和GIG过程对非高斯OU随机波动率模型进行扩展,建立连续叠加Lévy过程驱动的非高斯OU随机波动率模型,并给出模型的散粒噪声(Shot-Noise)表现方式与近似。在此基础上,为了反映的波动率相关性,本文把回顾抽样(Retrospective Sampling)方法扩展到连续叠加的Lévy过程驱动的非高斯OU随机波动模型中,设计了Lévy过程驱动的非高斯OU随机波动模型的贝叶斯参数统计推断方法。最后,采用金融市场实际数据对不同模型和参数估计方法进行验证和比较研究。本文理论和实证研究均表明采用CGMY和GIG过程对非高斯OU随机波动率模型进行扩展之后,模型的绩效得到明显提高,更能反映金融资产收益率波动率变化特征,本文设计的Lévy过程驱动的非高斯OU随机波动模型的贝叶斯参数统计推断方法效率也较高,克服了已有研究的不足。同时,实证研究发现上证指数收益率和波动率跳跃的特征以及波动率序列具有明显的长记忆特性。

关键词: Lévy过程, 非高斯OU过程, 可逆跳跃MCMC, 长记忆

Abstract: The currently most popular models for the volatility of financial time series, non Gaussian Ornstein-Uhlenbeck stochastic processes are extended to more general non Ornstein-Uhlenbeck models driven by the general Lévy process, such as Generalized Inverse Gaussian(GIG)and Tempered Stable distributions(CGMY). In particular, means of making the correlation structure in the volatility process more flexible based on continuous superpositions of the more general non Ornstein-Uhlenbeck models are investigated, which can introduce long-memory into the volatility model. A shot-noise process and approximation for the continuous superpositions process are represented. Inference is carried out in a Bayesian framework, with computation using extended Reversible Jump Markov chain Monte Carlo and dependent thinning to the continuous superposition case. Empirical research demonstrates that the efficient Markov chain Monte Carlo methods appear to be successful in the case of the general GIG and CGMY marginal model, and that those models can be fitted to real share price returns data, and that results indicate that for the series we study, the long-memory aspect of the model is supported.

Key words: Lévy process, no Gaussian Ornstein-Uhlenbeck stochastic processes, reversible jump Markov chain Monte Carlo, long-memory

中图分类号:

F830
F832

刘志东, 刘雯宇. Lévy过程驱动的非高斯OU随机波动模型及其贝叶斯参数统计推断方法研究[J]. 中国管理科学, 2015, 23(8): 1-9.

LIU Zhi-dong, LIU Wen-yu. The Non Ornstein-Uhlenbeck Models Driven by the General Lévy Process and Its Bayesian Inference[J]. Chinese Journal of Management Science, 2015, 23(8): 1-9.

参考文献

[1] Barndorff-Nielsen O E, Shephard N. Non-Gaussian OU based models and some of their uses in financial economics [J]. Journal of the Royal Statistical Society.Series B (Statistical Methodology), 2001a, 63(2): 167-241.

[2] Barndorff-Nielsen O E.Shephard N. Modeling by Lévy Processes for Financial Econometrics[M]//Barndorff-Nielse O E, Mikosch T,Resnick S.Lévy Processes-Theory and Applications. Boston: Birkhauser, 2001b: 283-318.

[3] Eraker B, Johannes M, Polson N. The impact of jumps in volatility and returns [J]. Journal of Finance, 2003, 58(3):1269-1300.

[4] Elerian O, Chib S, Shephard N. Likelihood inference for discretely observed non-linear diffusions [J]. Econometrica, 2001, 69(4):959-993.

[5] Jones C. Nonlinear mean reversion in the short-term interest rate [J]. The Review of Financial Studies, 2003, 16(3):793-843.

[6] Roberts G O, Stramer O. On inference for partially observed nonlinear diffusion models using the Metropolis-Hastings algorithm [J]. Biometrika, 2001, 88(3):603-621.

[7] Li Haitao, Wells M T, Yu C L.A Bayesian analysis of returns dynamics with Lévy jumps [J]. Review of Financial Studies, 2008, 21(5): 2345-2378.

[8] 朱慧明,黄超,郝立亚,等. 基于状态空间的贝叶斯跳跃厚尾金融随机波动模型研究[J].中国管理科学,2010,18(6):17-25.

[9] Roberts G O, Papaspiliopoulos O, Dellaportas P.Bayesian inference for non-Gaussian Ornstein-Uhlenbeck stochastic volatility processes[J].Journal of the Royal Statistical Society.Series B(Statistical Methodology), 2004, 66(2): 369-393.

[10] Griffin J E, Steel M F J. Inference with non-Gaussian Ornstein-Uhlenbeck processes for stochastic volatility [J].Journal of Econometrics, 2006, 134(2):605-644.

[11] Green P J. Reversible jump Markov chain Monte Carlo computation and Bayesian model determination [J]. Biometrika, 1995, 82(4), 711-732.

[12] Griffin J E, Steel M F J. Bayesian inference with stochastic volatility models using continuous superpositions of non-Gaussian Ornstein-Uhlenbeck processes[J].Computational Statistics and Data Analysis, 2010,54(11):2594-2608.

[13] Gander M P S, Stephens D A. Stochastic volatility modelling with general marginal distributions: Inference, prediction and model selection [J]. Journal of Statistical Planning and Inference, 2007a, 137(10):3068-3081.

[14] Gander M P S, Stephens D A. Simulation and inference for stochastic volatility models driven by Lévy processes [J].Biometrika, 2007b, 94(3): 627-646.

[15] Barndorff-Nielsen O E. Superposition of Ornstein-Uhlenbeck type processes [J]. Theory of Probability and its Applications, 2001, 45(2):175-194.

[16] Cox D R, Isham V. Point processes [M]. London, UK: Chapman & Hall, 1988.

[17] Black F. Studies of stock price volatility changes[C]. Proceedings of the Meetings of the Business & Economics Statistics, 1976:177-181.

[18] Nelson D B. Conditional heteroskedasticity in asset return: a new approach [J].Econometrica, 1991, 59(2): 347-370.

Lévy过程驱动的非高斯OU随机波动模型及其贝叶斯参数统计推断方法研究

The Non Ornstein-Uhlenbeck Models Driven by the General Lévy Process and Its Bayesian Inference

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

Metrics

本文评价

推荐阅读 0

[1]	陈淼鑫, 黄振伟. 股价波动的长记忆性与横截面股票收益——基于中国市场的实证研究[J]. 中国管理科学, 2023, 31(4): 1-10.
[2]	张跃军, 张晗, 王金丽. 考虑结构变化和长记忆性的国际原油价格波动率预测研究[J]. 中国管理科学, 2021, 29(9): 54-64.
[3]	吴鑫育, 李心丹, 马超群. 双因子非对称已实现SV模型及其实证研究[J]. 中国管理科学, 2018, 26(2): 1-13.
[4]	周伟杰, 党耀国, 顾荣宝. 基于灰色算子的分形法及应用[J]. 中国管理科学, 2017, 25(10): 89-99.
[5]	李云红, 魏宇, 张帮正. 股票市场历史信息的长记忆性特征研究[J]. 中国管理科学, 2015, 23(9): 37-45.
[6]	曹广喜, 曹杰, 徐龙炳. 双长记忆GARCH族模型的预测能力比较研究——基于沪深股市数据的实证分析 [J]. 中国管理科学, 2012, (2): 41-49.
[7]	余俊, 方爱丽, 熊文海. 国际股票市场收益的长记忆性比较研究[J]. 中国管理科学, 2008, 16(4): 24-29.
[8]	何建敏, 赵巍. 股市波动长记忆性聚合效应的半参数检验[J]. 中国管理科学, 2008, 16(4): 12-17.
[9]	耿克红, 张世英. 中国股市超高频持续期序列长记忆性研究[J]. 中国管理科学, 2008, 16(2): 7-13.
[10]	许友传, 何佳. 长期冲击、价格调整与股票组合收益的互相关关系[J]. 中国管理科学, 2007, 15(4): 9-13.
[11]	刘金全, 李庆华, 郑挺国. 具有平滑迁移的ARFIMA模型及其应用[J]. 中国管理科学, 2007, 15(3): 6-13.
[12]	赵巍, 何建敏. 附加噪声长记忆过程的半参数估计方法研究[J]. 中国管理科学, 2006, (4): 1-5.