This document presents a study on analyzing the integration of major global stock market indices. The study aims to identify interdependencies among 10 stock market indices from Asia, Europe, and America. The objectives are to determine the co-integration among indices using Granger causality tests. Methodologies used include collecting daily index data from 2001-2020, calculating returns, performing normality tests, correlation analysis, unit root tests, co-integration tests, and Granger causality tests. The results could help portfolio managers and investors design diversification strategies by understanding how policies interconnected global stock markets.
ENGLISH 7_Q4_LESSON 2_ Employing a Variety of Strategies for Effective Interp...
Global Stock Indices Integration Study
1. PRESENTED BY:
Rishav Raj Singh
(334/2019)
A STUDY OF INTEGRATION OF MAJOR
GLOBAL STOCK MARKET INDICES
UNDER GUIDANCE OF:
Dr. Gautam Negi
2. INTRODUCTION
Diversification has always been important in portfolio creation and
diversification using global stock markets is one of the way to do so
Diversification among different economies benefits if one understands the
interlinkages of different markets through their indices
This study is to identify the interrelationship among the stock indices across
the globe, to help understand how policy makers, portfolio managers and
investors design their strategies
3. OBJECTIVES
To identify the
interdependency among ten
stock market indices spread
across Asia, Europe and
America.
To determine causality among
the indices by Granger
Causality.
4. LITERATURE REVIEW
The Paper discusses the 10 Indices over the world and how they are so co-integrated that there exists a
cascading effect among themselves and how diversification advantage can be sensitive towards the co-
integration of the international indices which can help to build better investment and portfolio strategies.
HEMENDRA GUPTA, “INTEGRATION OF STOCK MARKET - EVIDENCE FROM
INDIA AND MAJOR GLOBAL INDICES”, INTERNATIONAL JOURNAL OF
FINANCIAL MANAGEMENT (JANUARY 2019)
5. P. SHRIKANT, K. APARNA, “GLOBAL STOCK MARKET INTEGRATION - A STUDY
OF SELECT WORLD MAJOR STOCK MARKETS”, INTERNATIONAL REFEREED
RESEARCH JOURNAL (JANUARY 2012)
The paper discusses how Globalization has helped the Indian economy to reduce the risk as it has
integrated with the other nations with the advancement of time and technology. Their will exist an arbitrage
opportunity if two nations are involved in the trade among themselves and their country’s index are not co-
integrated.
AROURI MOHAMED, FREDJ JAWADI, “STOCK MARKET INTEGRATION IN EMERGING
COUNTRIES: FURTHER EVIDENCE FROM THE PHILIPPINES AND MEXICO”,
RESEARCHGATE ARTICLE (JANUARY 2019)
This article investigates the stock market integration hypothesis of two emerging countries (the Philippines
and Mexico) into the world capital market over the last three decades. It concludes that both stock markets
are nonlinearly integrated into the world market. Furthermore, it shows that the stock market integration
process is nonlinear, asymmetric and time varying.
7. DATA COLLECTION
S.NO INDEX STOCK EXCHANGE COUNTRY REGION
1 NYSE Composite New York Stock Exchange USA
North America
2 NASDAQ New York Stock Exchange USA
3 TSX Composite Toronto Stock Exchange Canada
4 Nikkei 225 Tokyo Stock Exchange Japan
Asia
5 SSE Composite Shanghai Stock Exchange China
6 Hang Seng Hong Kong Stock Exchange China
7 Nifty 50 National Stock Exchange India
8 DAX Frankfurt Stock Exchange Germany
Europe
9 FTSE 100 London Stock Exchange United Kingdom
10 CAC Paris Stock Exchange France
Note: The data has been collected for the period of January 2001 to December 2020.
8. AVERAGE DAILY RETURNS
The daily logarithmic returns were calculated
using the following formula:
Rt = ln
𝑷𝒕
𝑷𝒕−𝟏
where, Rt is the logarithmic daily return at time t and
Pt and Pt-1 are the closing index values for two
consecutive days
It was observed from analysis that all stocks
except CAC give positive average daily returns,
with Nifty 50 giving maximum returns and CAC
giving minimum returns
S.NO INDEX
AVG DAILY
RETURNS
1 NYSE Composite 0.01818%
2 NASDAQ 0.03952%
3 TSX Composite 0.01662%
4 Nikkei 225 0.01704%
5 SSE Composite 0.01171%
6 Hang Seng 0.01416%
7 Nifty 50 0.05808% (max.)
8 DAX 0.01878%
9 FTSE 100 0.00142%
10 CAC 40 -0.00093% (min.)
9. JARQUE-BERA TEST
It is performed to find out whether there is normality in the time series data or not.
It is a test for the goodness-of-fit for the data to check whether the data has a skewness and
kurtosis value matching that of a normal distribution.
The formula for JB test is given below:
JB =
𝒏−𝒌+𝟏
𝟔
𝑺𝟐 +
𝟏
𝟒
𝑪 − 𝟑 𝟐
where,
n = no. of observations, k = no. of variables, S = skewness, C = kurtosis
Ho: S = 0 and C = 0
Ha: Data is non-normally distributed
10. CORRELATION MATRIX
A correlation matrix is a table
showing correlation coefficie
nts between variables
The variables represent the
different market indices and
the table shows the
correlation between these
indices
A correlation matrix is used
to summarize data, as an
input into a more advanced
analysis, and as a diagnostic
for advanced analyses.
11. UNIT ROOT – AUGMENTED DICKEY FULLER TEST
ADF Test helps to identify the unit problem in the series or the stationarity of the data
Stationarity in time series implies that mean, variance and covariance remain constant with the change in
time
If the series is non-stationary, then the study can be done only for a particular time period and cannot be
generalized for other time periods
The null hypothesis states that,
Ho: There exists a Unit Root (data is not stationary)
The alternate hypothesis states that,
Ha: There exists no Unit Root in the data
12. CO-INTEGRATION TEST
The co-integration test checks that even though each index has its own individual trend, how
are the different indices linked together by some relationship
To check co-integration, the Johnson Co-Integration Test has been performed
Johnson Co-Integration Test requires that the series is non-stationary at level and stationary
at first level
Null Hypothesis:
Ho: There do not exist any co-integrating equations among different indices
Alternate Hypothesis:
Ha: There exists a co-integrating equation among different indices
13. GRANGER CAUSALITY TEST
The Granger Causality Test has been used in the analysis to test the relationship between various
stock indices and to establish the relationship that the return of one market can help in
forecasting in returns in another market.
The 2 equations have the following null hypothesis:
Ho: x does not granger cause y
Ho: y does not granger cause x
Depending upon the above hypothesis, there are 3
outcomes:
Univariate Causality, if only in one equation the
hypothesis is rejected
Bivariate Causality, if in both the equation Null
hypothesis is rejected
No Causality, if hypothesis is not rejected in any case
14. BENEFIT OF THE STUDY
The purpose of this study is to check how the interdependency among the stock markets
around the world work using the correlation of returns among different indices and testing
the results through Granger Causality
The study would help in exploring options for portfolio diversification through investing in
different stock markets across the globe
Portfolio diversification would work best in cases where the interdependency among the
stock markets is low