| 624 | 42 | 109 |
| 下载次数 | 被引频次 | 阅读次数 |
本文选择1994年1月至2014年11月的人民币、美元、英镑、日元、欧元和港币等6种货币实际有效汇率的月度数据,首先采用AR-GARCH-t过程对收益率进行过滤,然后运用规则藤Copula函数对标准化残差序列进行建模,探讨人民币"第一次汇改"前后6种汇率之间的波动溢出效应,研究汇率之间的尾部相依和联动现象。研究发现:"第一次汇改"前后,人民币与其他5种货币实际有效汇率之间的相依结构发生了变化,且联动中的主导货币也由美元变为人民币,但仍可用同一类型的规则藤Copula结构来描述;人民币与其他货币之间都存在对称的或非对称的尾部相依,其中人民币与日元之间存在对称的负尾部相依,而与欧元之间存在负的上尾部相依。"第一次汇改"后,人民币与美元实际有效汇率之间正的尾部相依程度有所增加,且相依性最大,港币与美元之间正的尾部相依性有较大幅度的下降。此外,人民币与日元之间负的尾部相依关系也有较大幅度的下降。
Abstract：To analyze the volatility spillover effects,tailed dependence and comovements of the real effective exchange rates between RMB and foreign currencies,this paper firstly use the AR-GARCH-t process to filter the monthly data of the real effective exchange rates of six currencies from January 1994 to November 2014,then models the volatility of exchange rates employing the regular vine copula framework to analyze the differences of dependences before and after the first reform of RMB exchange rate. The empirical results are as follows. Firstly,the dependences of the real effective exchange rates have changed after the first reform,and RMB displays the leading effects of co-movements. However,the dependence structures can be captured by the same regular vine copula framework. Secondly, symmetric or asymmetric tailed dependences display in the real effective exchange rates between RMB and foreign currencies. There exist symmetric negative tailed dependence between RMB and Japanese Yen and negative upper tailed dependence between RMB and Euro.Thirdly,it increases for the positive tailed dependence between RMB and US dollar,while it decreases for the negative tailed dependence between Hong Kong dollar and US dollar. Furthermore,the negative tailed dependence also declines for the pair of RMB and Japanese Yen.
[1]徐国祥,杨振建.人民币分别与发达市场和新兴市场货币汇率波动传导效应研究——基于多元BEKK-MGARCH模型的波动传导测试[J].金融研究,2013(6):46-59.
[2]张欣,崔日明.基于非对称随机波动模型的人民币汇率波动特征研究[J].国际金融研究,2013(1):28-37.
[3]王晓辉,张卫国,庄亮亮,等.基于多元分析的人民币汇率波动率预测[J].数理统计与管理,2014,33(3):467-477.
[4]鲁万波,焦鹏.基于模糊GJR-GARCH模型的波动率估计[J].数理统计与管理,2014,33(3):559-570.
[5]Sklar A.Fonctions de repartitionàn dimensions et leurs marges[J].Publication de l‘Institut de Statistique de l’Universitéde Paris,1959(8):229-231.
[6]Embrechts P.Copulas:a personal view[J].Journal of Risk and Insurance,1999,76(3):639-650.
[7]Embrechts P,Mc Neil A,Straumann,D.Correlation:pitfalls and alternatives[J].Risk,1999,12(5):11-21.
[8]Bedford T,Cooke R M.Probability density decomposition for conditionally dependent random variables modeled by vines[J].Annals of Mathematics and Artificial Intelligence,2001,32(1-4):245-268.
[9]Bedford T,Cooke R M.Vines-a new graphical model for dependent random variables[J].Annals of Statistics,2002,30(4):1031-1068.
[10]Czado C,Aas K.Pair-copula constructions-even more flexible than copulas[R].Working Paper,2013.
[11]Allen D E,Ashraf M A,Mc Aleer M,et al.Financial dependence analysis:applications of vine copulae[R].Working Paper,2013.
[12]Low R K Y,Faff R,Aas K.Mean-variance optimization still works!a Bayesian methodology with vine copulas[R].Working Paper,2013.
[13]Low R K Y,Alcock J,Faff R,et al.Canonical vine copulas in the context of modern portfolio management:are they worth it?[J].Journal of Banking&Finance,2013,37(8):3085-3099.
[14]So M K P,Yeung C Y T.Vine-copula GARCH model with dynamic conditional dependence[J].Computational Statistics and Data Analysis,2014,76:655-671.
[15]高江.藤Copula模型与多资产投资组合VaR预测[J].数理统计与管理,2013,32(2):247-258.
[16]陈清平,程希骏.一个基于pair-copula法构建高维相依结构的研究[J].数理统计与管理,2013,32(2):232-239.
[17]张国富,杜子平.基于R藤copula的深圳股票市场系统风险分析[J].金融经济学研究,2014,29(3):76-87.
[18]张国富,杜子平,张俊.基于混合C藤Copula的我国一篮子货币汇率相依结构研究[J].数学的实践与认识,2014,44(11):74-84.
[19]马锋,魏宇,黄登仕.基于vine copula方法的股市组合动态VaR测度及预测模型研究[J].系统工程理论与实践,2015,35(1):26-36.
[20]Morales-Napoles O.Bayesian belief nets and vines in aviation safety and other applications[D].Ph.D.thesis,Technische Universiteit Delft,2008.
[21]Dimann J.Statistical inference for regular vines and application[D].Diplomarbeit,Center of Mathematical Sciences,Munich University of Technology,Garching bei Munchen,2010.
[22]Dimann J,Brechmann E C,Czado C,et al.Selecting and estimating regular vine copulae and application to financial returns[D].Computational Statistics and Data Analysis,2013,59(1):52-69.
[23]White H.Estimation,inference and specification analysis[M].Econometric Society Mono-graphs No.22,Cambridge University Press,Cambridge,U.K.,1994.
[24]Akaike H.Information theory and an extension of the likelihood ratio principle[C].In:Petrov,B.N.(Ed.),Proceedings of the Second International Symposium of Information Theory.Akademiai Kiado,Budapest,1973:257-281.
1其他条件相依关系的分析类似,且不是文章分析的重点,此处不作过多阐述。
基本信息:
DOI：10.19343/j.cnki.11-1302/c.2015.05.006
中图分类号:F224;F832.6
引用信息:
[1]胡根华.人民币与国外主要货币的尾部相依和联动[J].统计研究,2015,32(05):40-46.DOI:10.19343/j.cnki.11-1302/c.2015.05.006.
基金信息:
2011年国家自然科学基金面上项目“基于藤Copula GARCH与时就Levy过程的多重货币期权定价的蒙特卡罗模拟方法研究”(71171168);; 2014年西南财经大学中央高校基本科研业务费专项资金项目“基于混频数据的人民币汇市套期保值策略与资产最优配置”(JBK1407165);; 国家留学基金(201406980031)的资助
2015-05-15
2015-05-15