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

中国管理科学 ›› 2012, Vol. ›› Issue (2): 41-49.

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

曹广喜^1,2, 曹杰¹, 徐龙炳²

1. 南京信息工程大学经济管理学院, 江苏南京 210044;
2. 上海财经大学金融学院, 上海 200433

收稿日期:2011-03-20 修回日期:2011-12-12 出版日期:2012-04-29 发布日期:2012-04-25
基金资助:
国家自然科学基金项目(70901044,60804047,71073100);中国博士后基金项目(20100480577);江苏省高校哲学社会科学基金项目(09SJB880113);江苏省高校"青蓝工程"资助项目;江苏省政府留学基金项目

Comparative Research on Forecast Ability of Double-Long-Memory GARCH Family Models ——Empirical Analysis of Shanghai and Shenzhen Stock Markets

CAO Guang-Xi^1,2, CAO Jie¹, XU Long-bing²

1. School of Economics and Management, Nanjing University of Information Science & Technology, Nanjing 210044, China;
2. School of Finance, Shanghai University of Finance and Economics, Shanghai 200433, China

Received:2011-03-20 Revised:2011-12-12 Online:2012-04-29 Published:2012-04-25

摘要/Abstract

摘要： GARCH族模型在金融风险的度量中有着广泛的应用。在考虑股市收益率和波动率序列双长记忆性的基础上,基于上证综合指数和深圳成份指数的日收盘价序列,从证券投资风险量化的角度,引入受险值VaR和相对正确符号指标PCS作为模型预测误差衡量指标,比较分析了双长记忆GARCH族模型在不同分布假设情况下的的拟合与预测精度。结果显示:偏t分布能较好描述沪深股市的厚尾特征;在较小的VaR水平下ARFIMA(2,d₁,0)-FIAPARCH(1,d₂,1)-skt模型对股市波动风险具有较强的预测能力,而ARFIMA(2,d₁,0)-HYGARCH(1,d₂,1)-skt对股市的涨跌趋势具有较强的预测能力。

关键词: VaR, 长记忆, ARFIMA, FIAPARCH, HYGARCH

Abstract: GARCH family models have been widely used in financial risk measurement. There is double long memory characteristic in stock market. That is returns and fluctuations series of stock prices usually have long memory feature respectively. Hereby, by using Shanghai and Shenzhen stock markets returns series, double-long-memory GARCH family models with different distributions are comparative analyzed, based on the instruction of VaR computation and PCS indicator which can be used to measure investment risk and risk disgust degree respectively. As fitting and forecasting results shown, skewed t distribution can describe the "fat tail" feature of stock markets, and under the small VaR condition the ARFIMA(2,d₁,0)-FIAPARCH(1,d₂,1)-skt model show stronger forecast ability to the fluctuation risk of stock market while the ARFIMA(2,d₁,0)-HYGARCH(1,d₂,1)-skt model present stronger ability to the trends of rise and fall.

Key words: VaR, long memory, ARFIMA, FIAPARCH, HYGARCH

中图分类号:

F830.9

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.

CAO Guang-Xi, CAO Jie, XU Long-bing. Comparative Research on Forecast Ability of Double-Long-Memory GARCH Family Models ——Empirical Analysis of Shanghai and Shenzhen Stock Markets[J]. Chinese Journal of Management Science, 2012, (2): 41-49.

参考文献

[1] Laurent,S., Peters, J. P..G@RCH2.2: An ox package for estimating and forecasting various ARCH models[J]. Journal of Economic Surveys, 2002,(16):447-485.
[2] Laurent, S., Perters, J. P.. G@RCH 4.0, estimating and forecasting ARCH models[J].Timberlake Consultants, 2005.
[3] Ricardo, A.. The Estimation of Market VaR Using GARCH Models and a Heavy Tail Dis-tributions. Working Paper Series, 2006.
[4] 宋鹏燕, 刘琼荪. 基于幂率型分布的动态VaR模型及实证研究[J]. 中国管理科学, 2008, 16: 251-254.
[5] 李成, 马国校. VaR模型在我国银行业同业拆借市场中的应用研究[J]. 金融研究, 2007, (5): 62-77.
[6] Engle, R. E.. Autoregressive conditional heteroskedasticity with estimation of the variance of UK inflation[J]. Econometrics, 1982, 50: 987-1008.
[7] Bollerslev, T.. Generalized autoregressive conditional heteroskedasticity[J]. Journal of Econometrics, 1986, 31: 307-327.
[8] Bailliie, R. T., Bollerslev, T., Mikkelsen, H.. Fractional integrated generalized autoregressive conditional heteroskedasticity[J]. Journal of Econometrics, 1996, 74: 3-30.
[9] Tse, Y. K.. The conditional heteroscedasticity of Yen-dollar exchange rate[J]. Journal of Applied Econometrics, 1998, 13: 49-55.
[10] 张世英, 樊智. 协整理论与波动模型[M]. 北京: 清华大学出版社, 2004.
[11] 张卫国, 胡彦梅, 陈建忠. 中国股市收益及波动的ARFIMA-FIGARCH模型研究[J]. 南方经济, 2006, (3): 108-112.
[12] 曹广喜. 我国股市收益的双长记忆性检验——基于VaR估计的ARFIMA-HYGARCH-skt模型[J]. 数理统计与管理, 2009, (1): 167-174.
[13] 殷炼乾, 邵锡栋. 中国金融市场波动率模型预测能力比较研究[J]. 预测, 2009, 28(5): 20-26.
[14] 郑振龙, 黄薏舟. 波动率预测:GARCH模型与隐含波动率[J]. 数量经济技术经济研究, 2010, (1): 140-150.
[15] 徐正国, 张世英. 调整"已实现"波动率与GARCH及SV模型对波动的预测能力的比较研究[J]. 系统工程, 2004, 25(8): 60-63.
[16] 巍宇. 中国股票市场的最优波动率预测模型研究——基于沪深300指数高频数据的实证分析[J]. 管理学报, 2010, 7(6): 936-942.
[17] 巍宇. 沪深300股指期货的波动率预测模型研究[J]. 管理科学学报, 2010, 13(2): 66-76.
[18] Hansen, P. R., Lunde, A.. Consistent ranking of volatility models[J]. Journal of Econometrics, 2006, 131(2): 97-121.
[19] 张永东, 毕秋香. 上海股市波动性预测模型的实证比较[J]. 管理工程学报, 2003, 15(2): 16-19.
[20] Granger, C. W. J.. Long memory relationships and the aggregation of bynamic models [J]. Journal of Econometrics, 1980, 14: 227-238.
[21] Hosking, J. R. M.. Fractional differencing [J]. Biometrika, 1981, 68: 165-176.
[22] Davidson, J.. Moment and memory properties of linear conditional heteroscedasticity models, and a new model[J]. Journal of Business & Economic Statistics, 2004, 22: 16-29.
[23] Tang, T. L., Shieh, S. J.. Long-memory in stock index futures markets: A value-at-risk approach[J]. Physica A, 2006, 366: 437-448.
[24] Kupiec, P.H.. Techniques for verifying the accuracy of risk measurement models[J]. Journal of Derivatives, 1995,(3): 73-84.
[25] 曹广喜, 姚奕. 沪深股市动态溢出效应与动态相关性的实证研究——基于长记忆VAR-BEKK(DCC)-MVGARCH(1,1)模型[J]. 系统工程, 2008, (5): 47-54.
[26] Lamoureux, C. G., William, D. L.. Forecasting stock return variance: Toward an understanding of stochastic impied volatilities[J]. Review of Financial Studies, 1993, 5: 293-326.
[27] Hamilton, J. D.. Time Series Analysis[M]. Princeton University Press, 1994.