国际主要股票市场指数以及GDP的比较研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
  • 英文题名:Comparative Study on Main International Stock Markets' Indices and GDP
  • 作者:韩广哲
  • 论文级别:硕士
  • 学科专业名称:数量经济学
  • 学位年度:2004
  • 导师:陈守东
  • 学科代码:020209
  • 学位授予单位:吉林大学
  • 论文提交日期:2004-05-01
摘要
本文运用Granger因果关系检验法、GARCH模型、协整分析和向量误差修正模型(VECM),全面考察美国、英国、日本和中国香港四个国家和地区的GDP之间、主要股票市场之间的相互影响关系。
    本项研究试图建立各国股票市场指数之间、各国GDP之间的协整关系。考察四个股票市场是否能够整合,是否存在长期的共同趋势;各国GDP能否形成一个系统,其长期发展是否具有稳定的关系。并在此基础上建立ECM模型,比较股票市场的协整关系对各个股票市场收益率、GDP的协整关系对各国GDP增长率的影响,各自的调整系数是否显著。从GDP和股票市场角度出发,综合研究美国、英国、日本和中国香港之间的经济联系。
    本文除了第一章“引言”外大致可以分为以下几个部分:
    1.理论基础和指标选择
    证券市场与宏观经济密切相关,尤其是股票市场被称为国民经济的“晴雨表”,是公认的国民经济的信号系统之一,是宏观经济分析中的重要先导指标。国内生产总值能全面、确切地反映一国经济发展的规模、速度、结构和水平,多数国家都采用该指标来说明本国经济发展的进程和进行国际经济比较。
    我们选取美国、英国、日本和中国香港四个国家和地区的主要股票市场指数:美国的道·琼斯工业平均指数(DJIA),英国的金融时报指数(FTSE100),香港的恒生成分股指数(HSI),日本的日经225指数(NIKKEI225)。选择了从1991年到2003年的日度和季度指数。分别进行取对数和对数差分处理,得到对数股指指数序列和股指收益率序列。
    从国际证券市场角度来看,主要股票市场指数呈现出越来越明显的共同运动趋势。由于经济全球化的程度较深,主要发达国家的股票市场具有显著的联动特征。
    选取从1991年到2003年的美国、英国、日本和中国香港四个国家和地区的季度GDP数据。介绍并比较进行GDP国际比较研究时,现行的汇率法和购买力评价法的优缺点。我们选择汇率法,使用季度汇率对英国、日本和中国香港的季度GDP数据进行转换,使得所有的GDP数据都是统一的美元度量单位。同样进行取对数和对数差分处理,得
    
    
    到对数GDP序列和GDP收益率序列。
    伴随着经济全球一体化趋势的发展,美国、英国、日本和中国香港四个国家和地区的经济联系越来越密切,观察各国家和地区季度、年度GDP增长率的时间路径,比较各自的走势和特征。他们的GDP增长路径不尽相同,但存在着“同步”性,即存在着同涨同跌的现象。
    正是各国家和地区的股票市场和GDP之间的这些特征使得我们的研究变得有意义,考察是否存在长期均衡关系以及可能的相异动态调整。
    2.简要介绍本文使用的检验方法和模型
    本文主要使用Granger因果关系检验方法、一元GARCH(p,q)模型、二元GARCH(1,1)模型、协整概念、VAR模型和VECM模型。
    这一部分引入了Granger因果关系检验方法的概念及其应用价值,Granger给出这一定义的原因是如果一个事件Y是另一个事件X的原因,则事件Y可以领先于事件X。注意,“ Granger-引起”这种表达方式并不意味着是的效果或结果。Granger 因果关系只是度量前趋(事件发生的先后次序)及信息的内容。
    介绍了基本的GARCH模型及用途,GARCH模型有许多变形, GARCH类模型特别适合用于金融时间序列数据的波动性和相关性进行建模,特别是用于描述股票市场收益率序列显著存在着的尖峰、厚尾、有偏、波动聚类和长记忆性。需要指出的是,二元GARCH(1,1)模型所得到的相关性是指两个序列的波动之间的相关性,这与两个序列间的相关性意义不同。
    协整理论是处理非平稳时间序列间协整关系的有效方法。它所解决的是某些单整序列的关系问题。介绍单整和协整的概念,协整概念的提出对于用非平稳变量建立经济计量模型,以及检验这些变量之间的长期均衡关系非常重要。
    具有协整关系的非平稳变量可以用来建立误差修正模型。介绍了向量自回归(VAR)理论和向量误差修正模型(VECM)。对于非平稳变量,误差修正模型改进了时间序列模型只考虑用平稳变量建立模型,却忽视了原非平稳变量信息的弱点,以及经典经济计量模型忽视伪回归的问题。误差修正模型提供了结合上述两种模型的优点并克服其缺点的途径,把长期关系和短期动态特征结合在一个模型中。
    
    协整向量和误差修正系数可以通过协整检验和极大似然估计得出。
    3. 模型检验以及估计结果的实证分析
    这是本文最核心的部分。
    首先,通过单位根检验确定各个对数序列以及收益率序列的单整性。检验结果表明,对数序列是一阶单整的,相应的收益率序列都是平稳的。
    其次,使用Granger因果关系检验对日度股票指数进行检验,Granger因果关系检验的检验结果对滞后阶数的选取十分敏感。对各对数指数序列建立ARIMA(p,1,q)模型,也即相应的收益率序列的ARMA(p,q)模型,在模型结构节俭的条件下,参照模型的Akaike信息准则(AIC)、Schwarz准则(SC)进行,通过实际的建立模型,我们选择p=q=5,这样的滞后阶数可以很好的描述这四个指数。因此在Granger因果关系检验中,滞后阶数选择为5。
    从Granger因果关系检验的结果来看,主要股票市场之间存在着显著的Granger因果关系,无论是对数指数序列还是收益率序列,道指对其他股票市场指数?
Through Granger Causality Method, GARCH models, Cointegration analysis and Vector Error Correction Model (VECM), we research the relationship among USA GDP(Gross Domestic Product), UK GDP, Japan GDP and Hongkong GDP and the relationship among their Stock markets.
    This study intends to find the Cointegration relations among the international stock indices、GDP. We want to find out whether the four stock markets can be integrated and have the same long-term trend. We also want to find out whether USA GDP, UK GDP, Japan GDP and Hongkong GDP can make themselves a system and have a stable relationship in the long-term development. Then we set up ECM on the foregoing basis to study how Cointegration relation of stock markets affects every stock market’s yield and how Cointegration relation of GDP affects every country or region’s GDP growth, and to observe if the coefficient of Cointegration is significant. We comprehensively research the economic relationship among USA, UK, Japan and Hongkong from the point of view of GDP and stock market.
    With the exception of the first chapter, which is an introduction of this paper, the paper consists of four sections: theory basis and index choice, the model system and test method, the empirical study and results.
    1. theory basis and index choice
    Securities business is in close contact with macroeconomic. Especially, stock market is usually considered as the “weatherglass” of a country’s economics and is acknowledged as one of beaconages of a country, and it is an important forecasting sign or symptom in macroeconomic analysis. Since GDP can reflect the exact scale、growth、structure and level of a country economy, most countries choose it to show the course of economic development and to compare with each other.
    We select four indices : USA DJIA, UK FTSE100, Japan NIKKEI225 and Hongkong HSI. The sample is daily index and quarterly index from 1991 to 2003. And we deal with the series by the algorithm of ln(x) and
    
    
    dln(x), then we have the natural logarithm series and difference of natural logarithm series(the stock index’s yield series).
    From the point of view of international securities business, the stock market indices show the same movement trend more and more obviously. Because of the economic globalization, major stock markets in developed countries show evident characteristic of co-movement.
    We have already got the quarterly data of GDP from 1991 to 2003. There are two means for us to convert different GDP denoted in its own currency, exchange rate and PPP. We choose quarterly exchange rate to convert UK quarterly GDP, Japan quarterly GDP and Hongkong quarterly GDP to the uniformed measurement units of USD.
     As economic globalization goes, the relationships among countries are more and more close. By observing the quarterly and annual GDP growth, though there are some difference in the course of growth, but the characteristic of “simultaneity” does exist, which means that GDP rise or fall simultaneously.
    These characteristics and differences among stock markets and GDP are meaningful in the research of long-term Cointegration relation and possible different short-term adjustment.
    2. Introduction to the model system and test method
    This paper chiefly uses the Granger Causality Method, univariate GARCH(p,q) model, bivariate GARCH(1,1) model, Cointegration concept and Vector Error Correction Model (VECM).
    Granger Causality Method points out that if event Y is the cause of event X, then event Y can precede event X. The expression of “x Granger-caused y” doesn’t means that y is the effect or result of x. Granger causality measures precedence and information content but does not by itself indicate causality in the more common use of the term.
    The class of GARCH models is suited to measure the volatility and correlation of financial time series. Especially, it can perfect measure the “fat tail、volatility cluster and long memory”. The correlation that bivariate
    
    
    GARCH(1,1) model returns is the relationship of volatilities between two serie
引文
[1] 陈守东、韩广哲、荆伟.主要股票市场指数与我国股票市场指数间的协整分析[J].数量经济技术经济研究,2003,5:126-127.
    [2] 俞世典、陈守东.主要股票指数的联动分析[J].统计研究,2001,8:42-46.
    [3] (美)詹姆斯 D.汉密尔顿著,靳云汇等译.时间序列分析[M].北京:中国社会科学出版社,1999:358-359.
    [4] (美)威廉 H.格林著,靳云汇主审.经济计量分析[M].北京:中国社会科学出版社,1998:615-630.
    [5] 董文泉、高铁梅等.经济周期波动的分析与预测方法[M].吉林:吉林大学出版社,1998:483-518.
    [6] 王春峰.金融市场风险管理[M].天津:天津大学出版社,2001:134-144.
    [7] 张晓峒.计量经济分析[M].北京:经济科学出版社,2000:214-229.
    [8] Bollerslev T. Generalized Autoregressive Conditional Heteroscedasticity[J].Journal of Econometrics ,1986,31:307-327.
    [9] C.A.Sims. Money,Income,and Causality[J].American Economic Review ,1972,62:540-552.
    [10]C.W.J.Granger. Investigating Causal Relations by Econometric Models and Cross-Spectral Methods[J]. Econometrica ,1969,37:424-438
    [11]Engle Robert F. Autoregressive Conditional Heteroscedasticity With Estimate of the Variance of United Kingdom Inflation[J].Econometrica , 1982 ,50:987-1008.
    [12]Engle Robert F., and C.W.J.Granger .Co-Integration and Error Correction: Representation, Estimation,and Testing[J]. Econometrica ,1987,55:251-76.
    [13]Engle Robert F. and K.Kroner. Multivariate Simultaneous Generalized ARCH[J]. Econometric Theory ,1993,11:122-150.
    
    [14]Granger,C.W.J. Co-Integrated Variables and Error-Correcting Models[J].Unpublished University of California, San Diego, Discussion Paper,1983:83-13.
    [15]Jeon,B.N., and Von Furstenberg ,G.M. Growing international co-movement in stock price indexes[J].Quarterly Review of Economics and Business ,1990, 30:15-30.
    [16]Nelson ,C. Conditional Heteroskedasticity in Asset Return: A New Approach[J].Econometrica ,1991,59:347-370.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700