﻿ 中美股市股价间联动性分析

# 中美股市股价间联动性分析Dynamics of Integration between Shanghai Stock Market and Stock Market in America

Abstract: As the time went by, the economy has been developing and an increasing number of people begin to focus on investment, which leads to the dynamics of integration among different stock markets. Those problems on stock market become more and more important. In addition to the dynamics of integration between Shenzhen Stock Market and Shanghai Stock Market, the dynamics of inte-gration among international stock market are of great importance. Learnt from knowledge on Ap-plied Econometric Time Series, same order mono may have cointegration effect. If two time series are both stable, we can check whether the two time series have cause-and-effect relationship. This article will focus on the dynamics of integration between Shanghai Stock Market and Stock Market in America, Shanghai Composite Index and National Association of Securities Dealer Automated Quotations are chosen to represent two stock market prices. Then the order of the mono is calcu-lated and the result of cointegration will be judged. After calculating the Daily Yield Rate and proving that they are steady, Granger Causality Test can be used to test whether the Daily Yield Rate of Shanghai Composite Index and National Association of Securities Dealer Automated Quota-tions have cause-and-effect relationship. At last Unit Root Test, Vector Autoregressive Model can be built.

1. 引言

2. 国内外研究现状综述

Tadaaki Komatsubara (2017) [1] 使用Three-Regime STC模型对1995年至2013年东亚地区的上海、香港、韩国及日本的债券交易所进行分析建模，得出在1995年各股市间的联动性还不甚明显，但从1995年到2003年间各股市间联动性上升很快。2003年后股市联动性维持在一定水平。

3. 综合指数协整检验

3.1. 数据选取

3.3. 单整阶数

Table 1. Unit root test for Nasdaq Composite Index in three situations

Table 2. Optimal criteria test for Nasdaq Composite Index

Table 3. Unit root test for Shanghai Composite Index in three situations

Table 4. Optimal criteria test in three situations

Table 5. Unit root test for first-order difference of Nasdaq Composite Index

3.4. 协整检验

4. 格兰杰因果检验

4.1. 数据选取

Table 6. Optimal criterion test for the first-order difference of Nasdaq Composite Index

Table 7. Unit root test for the first-order single sequence of Shanghai Composite Index

Table 8. Optimal criterion test for the first-order difference of Shanghai Composite Index

Table 9. Unit root test for residuals of cointegration equations

4.2. 收益率平稳性检验

4.2.1 . 纳斯达克综合指数每日收益率平稳性检验

4.2.2 . 上海证券综合指数每日收益率平稳性检验

4.3. 格兰杰因果检验

4.4. 格兰杰因果检验原因分析

5. VAR建模

5.1. 建立VAR模型

Table 10. Unit root test for daily yield rate of Nasdaq Composite Index

Table 11. Unit root test for daily yield rate of Shanghai Composite Index

Table 12. Optimal criterion test for daily yield rate of Shanghai Composite Index

Table 13. Granger causality test between daily yield rate of Nasdaq Composite Index and Shanghai Composite Index

Table 14. Granger causality test between daily yield rate of Nasdaq Composite Index and Shanghai Composite Index

Table 15. VAR Model with lagging eight order

Continued

5.2. 外生变量检验

5.3. VAR模型平稳性检验

5.4. 脉冲响应分析

Table 16. Exogenous variable test for daily yield rate of Nasdaq Composite Index

Table 17. Exogenous variable test for daily yield rate of Shanghai Composite Index

Figure 1. Unit root test for VAR Model

Figure 2. Impulse response of Shanghai Composite Index to daily yield rate of Shanghai Composite Index

Figure 3. Impulse response of Nasdaq Composite Index to daily yield rate of Shanghai Composite Index

5.5. 方差分解

Figure 4. Impulse response of Nasdaq Composite Index's daily yield rate to Nasdaq Composite Index's daily yield rate

Figure 5. Impulse response of Shanghai Composite Index’s daily yield rate to Nasdaq Composite Index’s daily yield rate

6. 研究结论

1) 纳斯达克综合指数及上海证券综合指数均为一阶单整序列。

2) 纳斯达克综合指数及上海证券综合指数不存在明显的协整关系，原因可能是因为缺少某些重要的影响因素。

3) 纳斯达克综合指数的每日收益率序列及上海证券综合指数的每日收益率序列均具有平稳性。

4) 在一定程度上，纳斯达克综合指数的每日收益率是造成上海证券综合指数的每日收益率波动的原

Table 18. Variance decomposition of Nasdaq Composite Index’s daily yield rate

Table 19. Variance decomposition of Shanghai Composite Index’s daily yield rate

5) 通过建立VAR模型，并通过相关检验发现最优的滞后阶数为八阶，而建立的VAR模型在一定显著水平下满足平稳性检验，而脉冲响应效益也较为良好。

[1] 李广众, 杨子晖, 杨铠维. 汇率波动性与股市收益率联动性——来自国际样本的经验证据[J]. 金融研究, 2014(7): 16-31.

[2] 何苏燕. 我国沪深股市与债市联动性研究[J]. 山东工商学院学报, 2016, 30(3): 91-96.

[3] 裴延华, 余万林. 基于沪港通前后沪港和沪美股市联动性的比较分析[J]. 武汉金融, 2017(4): 26-29.

[4] 西村友作. 中美两国股票市场联动性研究——基于CCF检验法的新证据[J]. 经济评论, 2009(2): 43-49.

[5] 马千里. 利率变动对沪深港股票市场联动性的影响[J]. 金融论坛, 2015, 20(12): 42-52.

[6] 张兵, 范致镇, 李心丹. 中美股票市场的联动性研究[J]. 经济研究, 2010, 45(11): 141-151.

[7] 郭全毓. 沪、港、深股市的动态相关性研究——基于DCC-GARCH模型[J]. 时代金融, 2017(17): 186-187.

[8] 莫悠, 程锐. 基于向量自回归模型的中美股市联动性分析[J]. 中国集体经济, 2017(25): 40-42.

Top