基于双变量EARJI-EGARCH的时变收益关联研究——来自东亚地区股市跳跃的分析

doi:10.16381/j.cnki.issn1003-207x.2015.03.011

中国管理科学 ›› 2015, Vol. 23 ›› Issue (3): 90-96.doi: 10.16381/j.cnki.issn1003-207x.2015.03.011

基于双变量EARJI-EGARCH的时变收益关联研究——来自东亚地区股市跳跃的分析

彭伟

华中科技大学经济学院, 湖北武汉 430074

收稿日期:2012-10-08 修回日期:2013-06-23 出版日期:2015-03-20 发布日期:2015-03-18
作者简介:彭伟(1983-),男(汉族),江西乐安人,华中科技大学经济学院博士生,研究方向:风险管理,证券投资.
基金资助:
国家自然科学基金资助项目(71171056)

The Study of Time-Varying Return Correlations Based on Bivariate EARJI-EGARCH

PENG Wei

School of Economics, Huazhong University of Science and Technology, Wuhan 430074, China

Received:2012-10-08 Revised:2013-06-23 Online:2015-03-20 Published:2015-03-18

摘要/Abstract

摘要： 本文改进了双变量EARJI-EGARCH模型,并对东亚地区的中国上证指数,日本日经指数和韩国综合KS指数的跳跃和双边时变收益关联的影响进行了研究。结果表明,东亚地区股市的时变关联持续性非常高,东亚地区单个市场跳跃对时变关联影响较小,市场同时发生跳跃对市场时变关联的影响取决于跳跃的方向。当市场都发生正向的跳跃时,上证和日经指数的时变收益增量最多,当市场都发生负向跳跃时,上证和韩国KS指数的时变收益减少最多。表明在东亚地区股市同向跳跃发生时,中国和日本股市相互关联较大。且同时跳跃对时变关联的影响将远远超过了单个市场跳跃对时变关联的影响,当市场发生反向的跳跃时,也超过了单个市场跳跃的影响,但不及同向跳跃的影响,且上证和日经指数时变收益增加最多,而日经和KS指数时变收益减少的最多,表明在股市反向跳跃时同样是中国和日本股市比日本和韩国股市之间的相互关联大。

关键词: EARJI-EGARCH, 双变量, 时变收益, 跳跃

Abstract: A bivariate EARJI-EGARCH is improved for study the jumps impact on time-varying return correlations between Shanghai composite index, Japan Nikkei index and Korea KS index. The results show the persistence of correlation in east asian is very high. The outcomes show that individual jumps have small effects on time-varying correlation, the effects of simultaneous jumps depend on the jump signs. The same sign jumps have bigger effects on time-varying correlation than individual jumps,the time-varying return between China and Japan increases most. When the opposite jumps happen, the time-varying return between China and Korea decreases most. It shows that when the same jumps happen, the correlation between Japan and Japan is stronger than the correlation between Japan and Korea.Simultaneous jumps have stronger effects than individual jumps.When reverse jumps happen,they have stronger effect than individual jumps,but weaker than simultaneous jumps.The time-varying return between China and Japan increases most,but Nikkei-KS decreases most.It shows that when reverse jumps happen, the correlation between Japan and China is stronger than the correlation between Japan and Korea.

Key words: EARJI-EGARCH, bivariate, time-varying, jump

中图分类号:

F830.91

彭伟. 基于双变量EARJI-EGARCH的时变收益关联研究——来自东亚地区股市跳跃的分析[J]. 中国管理科学, 2015, 23(3): 90-96.

PENG Wei. The Study of Time-Varying Return Correlations Based on Bivariate EARJI-EGARCH[J]. Chinese Journal of Management Science, 2015, 23(3): 90-96.

参考文献

[1] Kennedy J S, Coleman T F. Calibration and hedging under jump diffusion[J]. Review of Derivatives Research,2006,9(1):1-35.

[2] Lee K, Song S. Insiders' hedging in a jump diffusion model[J]. Quantitative Finance,2007,7(5): 537-545.

[3] Cheng W H. Overestimation in the traditional GARCH model during jump periods[J].Economics Bulletin,2008,3(68):1-20.

[4] Sheu H J: A full jump switching level GARCH model for short-term interest rate[J]. Applied Financial Economics,2012,22(6):479-489.

[5] 谈正达,胡海鸥. 短期利率跳跃-扩散模型的非参数门限估计 [J].中国管理科学,2012,20(1):8-15.

[6] 欧丽莎,袁琛.中国股票价格跳跃实证研究[J].管理科学学报,2011,14(9):60-66.

[7] 唐勇,寇贵明.股票市场微观结构噪声、跳跃、流动性关系分析[J].中国管理科学,2012,20(2):11-19.

[8] 王锦华.基于时间序列极值理论的跳跃风险研究[J].投资研究,2012,31(4):89-100.

[9] Andersen T G, Bollerslev T. A reduced form framework for modeling volatility of speculative prices based on realized variation measures[J]. Journal of Econometrics,2011, 160(1):176-189.

[10] Andersen T G, Bollerslev T, Frederiksen P. Continuous-time models, realized volatilities, and testable distributional implications for daily stock returns[J]. Journal of Applied Econometric,2010,25(2): 233-261.

[11] Yun J. The role of time-varying jump risk premia in pricing stock index options[J]. Journal of Empirical Finance,2011,18(5): 833-846.

[12] 左浩苗,刘振涛.跳跃风险度量及其在风险收益关系检验中的应用[J].金融研究,2011,(10):170-184.

[13] 刘庆富,许友传.国内外非同步期货交易市场之间跳跃溢出行为:基于风险事件的视角[J].系统工程理论与实践,2011,31(4):679-690.

[14] Chan W H. Conditional correlated jump dynamics in foreign exchange[J]. Economic Letters,2004,83(1):23-28.

[15] Asgharian H,Bengtsson C.Jump spillover in international equity markets[J]. Journal of Financial Econometrics,2006,4(2):167-203.

[16] Hellström J, Soultanaeva A. The impact of stock market jumps on time-varying return correlations: Empirical evidence from the Baltic countries[J].Working paper,Ume University,2010.

基于双变量EARJI-EGARCH的时变收益关联研究——来自东亚地区股市跳跃的分析

The Study of Time-Varying Return Correlations Based on Bivariate EARJI-EGARCH

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	陈强, 龚玉婷. 基于近邻截断的跳跃扩散过程波动函数的设定检验[J]. 中国管理科学, 2020, 28(7): 45-56.
[2]	郑尊信, 王华然, 朱福敏. 基于Levy-GARCH模型的上证50ETF市场跳跃行为与波动特征研究[J]. 中国管理科学, 2019, 27(2): 41-52.
[3]	龚旭, 林伯强. 跳跃风险、结构突变与原油期货价格波动预测[J]. 中国管理科学, 2018, 26(11): 11-21.
[4]	刘凤琴, 金瑜. LEVY-LIBOR市场模型的蒙特卡罗模拟参数校准与估计[J]. 中国管理科学, 2018, 26(1): 25-34.
[5]	陈声利, 李一军, 关涛. 基于四次幂差修正HAR模型的股指期货波动率预测[J]. 中国管理科学, 2018, 26(1): 57-71.
[6]	宋亚琼, 王新军. 基于动态估计误差的中国股市波动率建模与预测[J]. 中国管理科学, 2017, 25(9): 19-27.
[7]	巢文, 邹辉文. 基于双指数跳跃扩散模型的长寿债券定价研究[J]. 中国管理科学, 2017, 25(9): 46-52.
[8]	龚旭, 文凤华, 黄创霞, 杨晓光. 下行风险、符号跳跃风险与行业组合资产定价[J]. 中国管理科学, 2017, 25(10): 1-10.
[9]	刘志东, 严冠. 基于半鞅过程的中国股市随机波动、跳跃和微观结构噪声统计特征研究[J]. 中国管理科学, 2016, 24(5): 18-30.
[10]	刘志东, 杨竞一. 基于非参数日内跳跃检验和高频数据的公司信息披露对股市价格波动影响研究[J]. 中国管理科学, 2016, 24(10): 22-34.
[11]	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.
[12]	唐勇, 林欣. 考虑共同跳跃的波动建模:基于高频数据视角[J]. 中国管理科学, 2015, 23(8): 46-53.
[13]	孙洁. 考虑跳跃和隔夜波动的中国股票市场波动率建模与预测[J]. 中国管理科学, 2014, 22(6): 114-124.
[14]	黄苒, 唐齐鸣. 基于可变强度跳跃-GARCH模型的资产价格跳跃行为分析——以中国上市公司股票市场数据为例[J]. 中国管理科学, 2014, 22(6): 1-9.
[15]	罗长青, 朱慧明, 欧阳资生. 跳跃—扩散条件下信用风险相关性度量的变结构Copula模型[J]. 中国管理科学, 2014, 22(3): 1-12.