Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

A Study on the Spill Over Effects on Nifty 50

Returns: Evidence from Stock Market
Performances of Major Asian Counterparts of India
Anugya Nagpal1; Krishna MC2
1Student, 2Head of the Department,
School of Business and Management (SBM),
CHRIST (Deemed to be University), Bangalore, Karnataka

Abstract:- This study investigates the spillover effects of market information among the major Asian markets has
major Asian stock market performances on the returns of become a much-researched topic.
the Nifty 50, India's benchmark index. Employing
advanced econometric techniques, we analyze the The Indian stock market, embodied by the majestic
dynamic relationships between the Nifty 50 and key Asian Nifty 50 index, stands tall as a beacon of economic dynamism
counterparts, considering both short-term and long-term in Asia. Yet, its fortunes are not solely etched within its own
horizons. Our research delves into return spillovers borders. Like threads woven into a tapestry, the Nifty 50's
aiming to comprehensively assess the interconnectedness performance is intricately linked to the flow of its Asian
and transmission of market movements across the region. counterparts. This intricate dance of interconnectedness,
This study utilizes an extensive dataset covering Nifty 50 where market movements in one region ripple across others,
returns from April 1, 2013, to March 31, 2023, along with is the domain of return spillovers.
meticulously documented returns from stock market
indexes linked to major strategic alliances in India. By A. Global Financial Markets:
applying advanced multivariate time series analysis Today, the world of finance has created a complex and
techniques, encompassing Vector Autoregression (VAR), interconnected system known as global financial markets.
Granger causality tests, and impulse response functions, This market connects individuals, institutions, and economies
we model the intricate dynamics interweaving these across the globe, facilitating the exchange of financial assets
indexes with the Nifty 50. The research endeavors to and instruments like stocks, bonds, and currencies. These
answer fundamental questions, including assessing short- markets operate electronically, 24/7, with transactions
term and long-term effects resulting from major Asian flowing across different time zones and regulatory
counterparts of India on Nifty returns, as well as frameworks. The interconnectedness of global markets
exploring noticeable patterns that indicate the direction promotes economic growth, diversification, and access to
of causality between these counterparts and Nifty returns. capital, but also comes with risks and complexities. Events in
The outcomes of this study carry substantial implications one market can significantly affect others, causing volatility
for decision-makers. Investors can make more informed and spillover effects. Understanding the dynamics of global
decisions, businesses planning strategic partnerships can financial markets is crucial for navigating the complex world
refine their strategies, and policymakers can formulate of finance and making informed decisions in our increasingly
economic and financial regulations that accurately reflect interconnected world.
the complexities of these dynamics. By unveiling the
ripple effects of these counterparts on the Nifty 50, this B. Spill Over Effect:
research offers valuable insights into the evolving In the context of the stock market, a spillover effect
dynamics of India's financial markets and their refers to the phenomenon where movements in one market
integration into the global economy. cause similar or related movements in another market. It's like
ripples spreading across a pond when a stone is thrown in.
Keywords:- Nifty 50, Asian Stock Markets, Spillover Effects,
Return Spillovers, Econometrics, Interconnectedness,  Here's How it Works:
Investment Strategies.
 Let us suppose there are two markets – A and B.
I. INTRODUCTION  Market A experiences an event: This could be anything
that significantly impacts its prices, like positive news
The increasing regionalization of economic activities about a major company, rising interest rates, or political
and the liberalization of financial markets since the late 1980s uncertainty.
resulted in regional economic integrations 1 around the  Impact on Market A: Depending on the event, prices in
world. Due to the increasing interdependence of major Market A might rise (positive spillover) or fall (negative
financial markets all over the world, the transmission of stock spillover) and finally, Spillover to Market B: If markets A

IJISRT24APR148 www.ijisrt.com 85
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

and B are somehow connected, the movement in Market Habiba (2021), and Joshi (2011). However, there are
A can influence prices in Market B. This can happen conflicting views as well, like (Nath & Verma, 2003), that
through - Investor reactions: Investors active in both reveal a surprising lack of long-term equilibrium among the
markets might adjust their holdings based on their major South Asian stock markets.
understanding of the event in Market A and its potential
implications for Market B and Economic linkages: Trade, D. Scope of the Study:
investment, or financial connections between the two This study delves into the complex world of return
economies can make them sensitive to each other's spillovers, specifically focusing on their impact on India's
performance. Nifty 50 index. It aims to comprehensively analyze how
fluctuations and trends in the stock markets of major Asian
C. Return Spillover Effect: economies influence the returns generated by the Nifty 50.
Return spillovers capture how the returns, or the profits
or losses, generated in one market influence the returns in E. Objectives of the Research:
another. This goes beyond mere correlation, revealing the The study on the spillover effects on Nifty 50 returns
causal relationships that bind these markets together. When with a focus on the stock market performances of major Asian
there are changes in the returns of a particular market or asset, counterparts of India aims to achieve several key objectives.
these changes can affect or spill over to other related markets Firstly, the primary goal is to comprehensively analyze and
or assets. Return spillovers are a common phenomenon in understand the dynamics of spillover effects from the major
interconnected and global financial markets, and they can Asian stock markets to the Nifty 50 index. This involves
have significant implications for investors, portfolio investigating the extent to which fluctuations and trends in the
management, and risk assessment. stock markets of countries such as China, Japan, South Korea,
and others impact the returns of Nifty 50.
 Cross Market Return Spillovers:
This type of spillover occurs between different financial Secondly, the study seeks to identify the factors and
markets. For example, if there is a sudden drop in stock prices mechanisms that drive these spillover effects. This involves a
in one country, it may lead to spillover effects on stock detailed examination of macroeconomic indicators, financial
markets in other countries due to increased policies, geopolitical events, and other relevant factors that
interconnectedness and global economic linkages. It can be may influence the interconnectedness of the markets.
driven by various factors, including economic events, Understanding the underlying drivers is crucial for investors,
geopolitical developments, changes in interest rates, and policymakers, and market participants to make informed
shifts in investor sentiment. Financial crises, policy decisions, decisions in the context of the globalized financial landscape.
and unexpected shocks can amplify the intensity of return
spillovers. Furthermore, the research aims to assess the temporal
dimension of spillover effects, examining whether these
There are several reasons to research return spillover effects are persistent or transitory. This temporal analysis is
effects. Apart from a range of domestic influences, the essential for developing effective risk management strategies
volatility of significant foreign trading partners stands out as and for providing insights into potential windows of
a crucial factor affecting the volatility of stock returns in a opportunity for investment.
domestic market. Research on return spillovers in stock
markets is vital for managing risks, constructing diversified Additionally, the study strives to explore the
portfolios, understanding global economic linkages, implications of spillover effects on portfolio diversification
formulating effective policies, assessing market efficiency, strategies for investors. By gaining insights into the
improving forecasting models, understanding investor correlations and co-movements between Nifty 50 and its
behavior, and promoting financial stability. Asian counterparts, the research aims to provide practical
guidance for investors seeking to optimize their portfolios and
Researchers, including Gębka (2005), Jeon & Von manage risk effectively across different markets.
Furstenberg (1990), Eun & Shim (1989), etc, have examined
return and volatility spillover effects across the globe. The The rest of the paper is organised in the following
past research revealed substantial interdependence among sequence: Section 2, relevant literature review concerning the
various stock markets, suggesting that the price movements spillover effects. Section 3 covers the data description and
in one market impacts other markets and research also various statistical tools and techniques used. Section 4 has the
suggest that emerging markets within the same region results of the study and discussions. Section 5 has the major
influence each other more than markets in different regions. findings of the study and its conclusion. Section 6 gives the
Additionally, studies by researchers such as Kumar & scope for further research in this area of study.
Mukhopadhyay (2007), Kotha Kumar Kiran (2002), and
Yang (2003) incorporate the role of the US and say that the F. Limitations of the Study:
US has a significant impact on most of the economies around
the world. Further, various studies have been undertaken to  External Factors: Unforeseen global events or significant
measure the interconnectedness among the Asian economies, changes in international markets beyond Asia could
which also confers with emerging markets of the region potentially impact the results, even if not the primary
influencing each other, including Kedarnath & R K (2008), focus of the study.

IJISRT24APR148 www.ijisrt.com 86
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

 Market Complexity: Financial markets are inherently types of spillovers were significant, with intra-regional
complex systems with a multitude of interacting factors. linkages being stronger. This suggests that emerging markets
The study might not be able to capture every single within the same region influence each other more than
influence on return spillovers. markets in different regions, even after accounting for the
 Generalizability: The findings of the study might be impact of the global market. Jeon & Von Furstenberg (1990)
specific to the chosen time frame and the Asian markets A study using daily stock price data from major global
included. Applying the results to broader contexts or exchanges (Tokyo, Frankfurt, London, New York) revealed a
future scenarios might require further research. significant shift in interconnectedness and leadership among
these markets after the 1987 stock market crash. Yu & Hassan
G. Problem Statement: (2008) employing advanced EGARCH-M models and
To investigate the short run and long run return spillover multivariate AR-GARCH models, this study sheds light on
effects of major Asian Counterparts on Nifty 50 returns in the intricate relationships between MENA and world stock
India, using advanced multivariate time series analysis markets. The results point to sizeable and predominantly
techniques. positive volatility spillovers, signifying substantial
transmission of volatility fluctuations between
 Research Questions: regions. Interestingly, each market tends to contribute more
to its own volatility than it receives from others, despite the
 What is the magnitude and direction of the impact of significant overall interdependence. Eun & Shim (1989)
short-term shocks in major Asian markets on the employed a sophisticated statistical technique (VAR) to
immediate performance of Nifty 50 in India? analyze the intricate web of connections between nine major
 What are the long-term trends and patterns in return stock markets. Their findings revealed substantial
spillover effects between major Asian counterparts and interdependence among these markets, meaning that price
the Nifty 50 in India? movements in one market can rapidly impact others. This
suggests that investors should consider the broader
H. Research Hypothesis: international context when making investment decisions, as
local markets may be influenced by global trends.
 Null Hypothesis: There is an insignificant impact of Asian
counterparts’ Indices performance on the Indian Nifty 50 (Ratanapakorn & Sharma, 2002) examines the pre- and
return/ Returns. post-Asian crisis relationships between stock markets in
 Alternate Hypothesis: There is a significant impact of different regions (US, Europe, Asia, etc.). Before the
Asian counterparts’ Indices performance on the Indian crisis, no long-term connections were found, but during the
Nifty 50 return/Returns crisis, a single long-term relationship and more short-term
causal links emerged. Notably, only European markets
II. LITERATURE REVIEW directly influenced the US during the crisis, while others did
so indirectly through Europe.
Research on stock market integration and information
spillover is extensive, exploring various aspects. Some B. Spillovers from US Markets:
studies focus solely on return spillover, while others delve Utilizing high-frequency intra-day data, Kumar &
deeper into both return and volatility spillovers, Mukhopadhyay (2007) investigated the dynamic connections
encompassing the full picture of price movements across between India's NSE Nifty and the US NASDAQ Composite.
markets. Beyond simply detecting interdependence, research Their study identified significant one-way volatility spillover
has examined the influence of specific events like crises and from NASDAQ to Nifty, meaning Nifty's overnight volatility
liberalization on cross-border information flow. Additionally, fluctuations mainly stem from daytime movements in the US
while most studies analyze the spillover itself, some market. On average, NASDAQ shocks contribute roughly
investigate the underlying factors driving it, seeking to 9.5% to Nifty's overnight volatility, while Nifty's influence
understand the "why" behind market interconnectedness. on NASDAQ is negligible.
This diverse body of research offers valuable insights into the
complex web of relationships between national equity A similar study can be seen- Kotha Kumar Kiran (2002)
markets. reveals a strong US influence on the Indian stock market. US
daytime returns (both NASDAQ and S&P 500) Granger
It can also be seen that researchers have covered this cause the Nifty's movement, and both markets' daytime
interconnectedness among Asian economies and other returns significantly impact Nifty overnight
economies around the world as well. returns. Notably, volatility spillover is unidirectional, with
NASDAQ shocks influencing Nifty overnight volatility
A. Return and Volatility Spillover Effects Across the Globe: (9.5% impact) far more than Nifty's daytime volatility
Gębka (2005) examined return and volatility spillover affecting NASDAQ (0.5% impact). However, incorporating
across emerging markets in Central and Eastern Europe, Latin NASDAQ day trading information only improved forecasts
America, and South-East Asia. Their analysis separated the of Nifty overnight return levels, not its volatility. Then, Yang
influence of regional factors (intra-regional) from global (2003) analyzes long-term & short-term connections between
factors (inter-regional) on these spillovers. Interestingly, both US, Japan, & 10 Asian markets before, during, & after the
1997-98 crisis to assess its impact on stock market

IJISRT24APR148 www.ijisrt.com 87
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

integration. We also have Morana & Beltratti (2008) that interdependence changes over time. Furthermore, Fan
reveals stronger integration between the US and European introduces novel causality tests suitable for analyzing
markets compared to Japan. This is attributed to Japan's integrated and cointegrated systems.
economic stagnation and weak fundamentals in the
1990s, which seemingly led to more independent market There are studies that takes the Asian Financial crisis
behavior. into consideration as well as it was one of the major events
occurred in Asia like (Jang & Sul, 2002) analyzed the
Tan (2001) which says ESEA deregulation (1988-2000) changes in the co-movement among the stock markets of the
led to increased stock market integration, measured by co- countries which have undergone the Asian Financial crisis
movement in daily returns. Geweke's measure and VAR directly and the neighboring Asian countries using time series
analysis confirm, but US and Japan's influence remain test as co-integration and the granger causality test. Some
balanced. Post-crisis, interdependence strengthens researchers also represent the pre and post Asian financial
significantly. crisis conditions like- (Sheng & Tu, 2000) used multivariate
cointegration and error correction test found that prior to the
Some studies can be seen that shows no or significantly Asian financial crisis, stock markets in the Asia-Pacific
low influence of US like - (Ng, 2000) Moving beyond region were largely independent. However, the crisis
traditional global focus, this study reveals substantial triggered a fundamental shift, leading to the formation of
regional volatility spillovers from Japan to Pacific-Basin long-term linkages between national indices, as evidenced by
markets, independent of the US influence. A dedicated model cointegration analysis.
identifies local, regional, and global contributions to each
market's volatility, and interestingly, regional factors play a However, there are some conflicting views as well like
significant role. A significant study can be (Hsiao,2005) the study (Nath Mukherjee & Mishra, 2005) analyzed daily
which employed a combination of pairwise and vector data from 1996 to 2004 and found that, except for a few Asian
autoregression (VAR) models to rigorously test the causal countries, most markets studied weren't statistically
relationships between various economic indicators. Their integrated with India in the long run, suggesting limited long-
findings suggest that, while overall economic activity in the term interdependence. However, short-term relationships
US may not directly drive individual Asian economies, were detected, indicating potential diversification
financial shocks emanating from the US stock market can opportunities for international investors. The goal was to
have significant spillover effects on regional markets. This assess potential diversification benefits for foreign investors
highlights the importance of considering both real and in the Indian market. We also have (Nath & Verma, 2003)
financial linkages when assessing the interconnectedness of - Contrary to extensive research on developed markets, this
global economies. study reveals a surprising lack of long-term equilibrium
among the major South Asian stock markets. Despite
C. Spillovers among Asian Economies: analyzing data from India, Singapore, and Taiwan, spanning
Kedarnath & R K (2008) investigated return and nine years, we found no consistent cointegration between
volatility spillover between the Indian stock market and 12 their indices, indicating weak long-term interdependence.
other Asian countries using a GARCH model. They found
significant two-way intraday return spillover between India Finally, (Bessler & Yang, 2011) uncover a fascinating
and almost all the studied markets, indicating strong interplay of influence among major stock markets. Their
information flow and interconnectedness. Employing an research identifies Japan as a bastion of independence, while
EGARCH model, Habiba (2021) examined volatility Canada and France appear more vulnerable to external forces.
spillover across several Asian emerging stock markets. Their The U.S. market emerges as a complex entity, both self-
analysis revealed statistically insignificant volatility driven and receptive to inputs from key players like the U.K.
transmission between China and India, China and Indonesia, and Switzerland. Most importantly, the U.S. stands alone in
China and Pakistan, as well as in the reverse directions (i.e., its lasting impact on the price movements of other major
Pakistan to China, Pakistan to Indonesia, Pakistan to Korea, markets.
and Pakistan to Taiwan) over the specified study period. Joshi
(2011) employed a sophisticated model (GARCH-BEKK) to There is certain research that shows crucial gaps like -
analyze return and volatility spillover across six Asian stock (Pretorius, 2009) While extensive research explores
markets. The study revealed two-way connections between the degree of integration between stock
most markets in terms of returns, shocks, and volatility, markets, understanding the underlying reasons for this
though the magnitude of these linkages was relatively low, interconnectedness remains unexamined. This study delves
suggesting weak integration. Notably, internal volatility into this crucial gap, arguing that comprehending the driving
(within each market) was more pronounced than cross-market forces behind market relationships is even more valuable than
influences. Japan exhibited the highest overall volatility simply confirming their existence.
persistence, while China had the lowest. (Fan, 2003) delves
into the interconnectedness of Asia-Pacific stock markets,
pushing the boundaries of existing research. Their analysis
leverages cutting-edge techniques that handle structural
breaks and volatility (GARCH effects). This allows for not
only confirming cointegration but also quantifying how

IJISRT24APR148 www.ijisrt.com 88
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

III. DATA AND METHODOLOGY 50 returns serve as the Dependent Variable. The data
collected consists of Daily prices spanning the time frame
A. Data and Data Sources:
The research utilizes an extensive dataset covering Nifty The data collection will encompass key stock indicators
50 returns from April 1, 2013, to March 31, 2023, along with like Opening, High, Low, closing prices, along with the
meticulously documented returns from stock market indices volume of shares traded. The adjusted closing price will be
linked to major Asian counterparts of India, where in Nifty considered, which accommodates factors like Stock Splits,
bonuses, ESOPs, etc.

Table 1: Countries and Indices used in the Study

S. No. Countries Stock Index
1 India Nifty 50
2 China Shanghai Composite
3 Hong Kong Hang Seng
4 Japan Nikkie 225
5 South Korea Kospi 200
6 Pakistan Karachi 100
7 Malaysia KLSE Composite
8 Taiwan Taiwan weighted
9 Thailand SET

Table 2: List of Variables

Endogenous Exogenous
Nifty 50 Returns Nifty 50, Hang Seng, Karachi 100, Kospi 200, Nikkie 225, SET, Taiwan weighted, KLSE Composite,
Shanghai Returns

 Type of Research: Secondary normally distributed. However, the data for all the indices as
 Tool: E-views a whole follows a normal distribution.
 Technique: Multi-variate time series analysis – VECM
 Time Period for study: Daily data from 2013 to 2023 Additionally, we will move forward with the Johansen
 Source: Yahoo finance Cointegration test, a statistical test used to determine the
presence and number of cointegrating vectors in a
B. Methodology: multivariate time series system. Cointegration occurs when
As the tests are being conducted for the returns of the two or more non-stationary time series have a long-run
specific indices, the following function will be used to equilibrium and move together so that a linear combination
calculate returns: results in a stationary time series.

 Equation 1: Logarithmic Returns  Test for Stationarity:

However, using a unit root test, we must make variables
𝑨𝒅𝒋𝒖𝒔𝒕𝒆𝒅 𝑪𝒍𝒐𝒔𝒆𝒕 stationary for time series analysis. Stationary Data means the
𝑹𝒕 = 𝒍𝒐𝒈 ( ) ∗ 𝟏𝟎𝟎 statistical characteristics like mean, variance, autocorrelation,
𝑨𝒅𝒋𝒖𝒔𝒕𝒆𝒅 𝑪𝒍𝒐𝒔𝒆𝒕−𝟏 etc, do not change over time. Meanwhile, non-stationary data
makes it difficult to model and predict future values as new
The Rt shows the logarithmic returns for a specific index trends or patterns evolve with time.
for any given period.
 Hypothesis:
 The Jarque-Bera Test:
As the data collected is secondary, the statistical
 H0: There is a non-stationarity or Unit root problem in the
properties of the data must be checked to ensure that it follows
data.
a normal distribution. For the same, Skewness, Kurtosis, and
 Ha: There is a stationarity in the data.
Jarque-Bera will be conducted.
 Johansen Cointegration Test to Check Long-Term
 Hypothesis: Relationships:
Cointegration testing is used in time series analysis to
 H0: The data collected is normally distributed
identify whether a long-term relationship exists between two
 Ha: The data collected is not normally distributed or more time series variables, particularly in modeling and
analyzing the relationships between variables that may have
First, this test will be done for individual indices. The a common stochastic trend.
alternate hypothesis will be accepted when the p-value of the
test is greater than 0.05 or 5%, concluding that the data is not

IJISRT24APR148 www.ijisrt.com 89
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

Cointegration is particularly relevant when variables are the order p - 1 on the differences of the variables and an error-
expected to move together in the long run, even if they may correction term derived from the known (estimated)
deviate from each other in the short term. cointegrating relationship. This model establishes a short-
term relationship between the stock prices while correcting
 Hypothesis: for the deviation from the long-term co-movement of prices.
VECM incorporates the concept of an error correction term,
 H0: There are no cointegrating factors among the which captures the short-term dynamics and adjustments
variables. toward the long-term equilibrium. The error correction term
 Ha: There are cointegrating factors among the variables. helps to model how deviations from the long-term
equilibrium are corrected in the short run.
 The Vector Error Correction Model for Multivariate Time
Series Analysis:  Granger Causality Test
Further, the Vector Error Correction Model (VECM) is After this, we proceed with the Granger Causality test,
done. The Vector Error Correction Model (VECM) is which is designed to assess whether past values of one
commonly used in time series analysis to model the variable help predict future values of another variable. It does
relationship between multiple cointegrated time series. not imply a true causal relationship in the traditional sense,
but rather a predictive relationship. If one variable Granger
 Hypothesis: causes another, it suggests that the first variable contains
information that is useful for predicting the second variable's
 Ho: Exogenous variable does not influence Endogenous future values.
variables.
 Ha: Exogenous variables do influence Endogenous  Hypothesis:
variables.
 H0: X does not Granger cause Y
The general form of a VECM is given by:  Ha: X does Granger cause Y

 Equation 1: Vector Error Correction Model Finally, we conclude with the Impulse Response
Functions that provide insights into how a variable reacts to a
∆𝒀𝒕 = 𝜶 + 𝜷𝟏 ∆𝒀𝒕−𝟏 + 𝜷𝟐 ∆𝒀𝒕−𝟐 + ⋯ + 𝜷𝒑 ∆𝒀𝒕−𝒑 + 𝝉𝑫𝒕 + 𝜺𝒕 one-unit shock in another variable, allowing researchers to
analyze the short-term and long-term effects of shocks in a
It is a cointegrated VAR model. This idea of the Vector dynamic system.
Error Correction Model (VECM) consists of a VAR model of

IV. RESULTS AND DISCUSSIONS

A. Descriptive Statistics:
Table 3: Descriptive Statistics for Selected Indices
KLSE
HANGSENG KARACHI KOSPI 200 NIFTY 50 NIKKE 225 SET SHANGHAI TAIWAN
COMPOSITE
Mean -0.0000565 0.0001008 -0.0000691 0.0000852 0.0004410 0.0003330 0.0000162 0.0001500 0.0002760
Median 0.0003000 0.0000000 0.0000255 0.0004910 0.0006360 0.0007230 0.0003270 0.0005010 0.0006610
Maximum 2.3296240 0.1789180 0.0662630 0.0875480 0.0840030 0.0773140 0.0765310 0.0849470 0.0617260
Minimum -2.3253660 -0.2133230 -0.0540470 -0.0797800 -0.1390380 -0.0825290 -0.1142820 -0.0887320 -0.0652060
Std. Dev. 0.0938030 0.0244540 0.0069030 0.0104170 0.0108990 0.0130660 0.0098510 0.1325700 0.0095310
Skewness 0.0002670 0.0107700 -0.1317070 -0.0807410 -1.2234360 -0.2525490 -1.3564140 -0.9705850 -0.5595700
Kurtosis 594.1043000 8.0648210 11.2750400 9.2448690 20.4658000 7.3375860 21.7735500 10.8765200 8.1494700
Jarque-Bera 35901299.00 2635.83 7043.07 4009.76 31959.49 1959.42 36970.01 6761.74 2851.71
Probability 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00
Sum -0.1394420 2.4849430 -0.1704380 0.2099990 1.0877810 0.8207120 0.0399870 0.3698490 0.6808620
Sum Sq. Dev. 21.6896400 1.4740270 0.1174590 0.2928010 0.2928010 0.4208530 0.2392140 0.4332190 0.2239220
Observations 2466 2466 2466 2466 2466 2466 2466 2466 2466

Here, we see the p-value for Jarque Bera of all variables same point, which is the peak of the curve. A normal
is less than 0.05 and therefore, the null hypothesis of the test distribution, often called a "bell curve," has thin tails at the
is rejected which tells us that the data is not normally ends, meaning extreme events (very high positive or negative
distributed. returns) are unlikely. In contrast, stock returns exhibit fatter
tails. This signifies a higher probability of both large gains
In a normal distribution, the mean, median, and mode and significant losses than a normal distribution would
all coincide. As the curve is symmetrical with a single peak predict.
at the center, the average (mean), the middlemost value
(median), and the most frequent value (mode) all fall at the

IJISRT24APR148 www.ijisrt.com 90
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

Stock returns often exhibit skewness. Skewness Further, all variables except Hangseng and Karachi have
describes how a distribution of data deviates from symmetry. negative skewness. Skewness tells how symmetrical the data
It tells you whether the data leans more towards one side (left is, and negative and positive skewness refer to the direction
or right) compared to a normal distribution. They may be of the asymmetry. Positive skewness indicates that the data is
positively skewed, where there are more frequent small gains clustered on the left side with a longer tail stretching out
with a few exceptional large gains. Alternatively, they might towards the right side of the distribution. This means there are
be negatively skewed, with a concentration of small losses more frequent lower values and a few higher outliers.
and the occasional major crash. Whereas negative skewness indicates that the data is clustered
on the right side with a longer tail stretching out towards the
left side of the distribution. This means there are more
frequently higher values and a few lower outliers.

B. Unit Root Tests:

Table 4: Unit Root Test

t-Statistic P-Value
Nifty 50 -17.67580 0.0000
Hang Seng -27.36607 0.0000
Karachi 100 -29.5751 0.0000
KLSE Composite -32.87299 0.0000
Kospi 200 -32.99415 0.0000
Nikkie 225 -33.57275 0.0000
SET -50.54347 0.0001
Shanghai -47.58169 0.0001
Taiwan Weighted -49.18060 0.0001

A unit root test is a statistical tool used to analyze time series against the alternative hypothesis of stationarity. The
series data, specifically to see if the data has a unit root. A test involves regressing the variable on its lagged values and
unit root basically means that the past value of the series examining the significance of the coefficient on the lagged
strongly influences the present value. If there's a unit root, an variable. If the test statistic is sufficiently negative, and the p-
increase today tends to lead to another increase tomorrow, value is below a chosen significance level, the null hypothesis
and a decrease today tends to lead to another decrease of a unit root is rejected, indicating that the time series is
tomorrow, with the changes just following the trend set by the likely stationary.
previous value. The key takeaway is that a unit root makes
the data non-stationary. This means the statistical properties If the p-value is less than 0.05, then the null hypothesis
of the data (like mean and variance) can change over time, is rejected. Here the p-value for all the variables is less than
making it difficult to analyze trends or forecast future values 0.05, so the null hypothesis is rejected, and it can be said that
using standard methods. The most employed unit root test is the data is stationary. Stationary data is the data for which the
the Augmented Dickey-Fuller (ADF) test. The ADF test statistical properties do not change with time, and it can be
assesses the null hypothesis that a unit root is present in a time easier to predict and model.

C. The Johansen Cointegration Test:

Table 5: The Johanse3n Cointegration Test

Data trend: None None Linear Linear Quadratic
Test type No Intercept No Trend Intercept No Trend Intercept No Trend Intercept Intercept Trend
Trend
Trace 9 9 9 9 9
Max-Eig 9 9 9 9 9

Information Criteria by Rank and Model

Data trend: None None Linear Linear Quadratic
Rank or No Intercept No Trend Intercept No Trend Intercept No Trend Intercept Intercept Trend
No. of Ces Trend
Akaike Information Criteria by Rank (Rows) and Model (Columns)
0 -49.34454 -49.34454 -49.33723 -49.33723 -49.32992
1 -49.77232 -49.77169 -49.76520 -49.76446 -49.75797
2 -50.03887 -50.03751 -50.03183 -50.03031 -50.02463
3 -50.28166 -50.27968 -50.27481 -50.27247 -50.26760

IJISRT24APR148 www.ijisrt.com 91
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

4 -50.46444 -50.46165 -50.45759 -50.45450 -50.45045

5 -50.62899 -50.62557 -50.62232 -50.61893 -50.61568
6 -50.78823 -50.78556 -50.78312 -50.77914 -50.77670
7 -50.93545 -50.93223 -50.93061 -50.92581 -50.92419
8 -51.07697 -51.07295 -51.07214 -51.06654 -51.06572
9 -51.17346* -51.16949 -51.16949 -51.16327 -51.16327

Data Trend specifies whether a constant term, a linear We use Akaike Information Criteria by Rank (Rows)
trend, or a quadratic trend is included in the model, Test Type and Model (Columns). This criterion is used to compare
shows two options: "No Intercept" and "Intercept". These different models and select the one that best fits the data. The
refer to whether a constant term is included in the star mark comes at 9 which tells there are 9 lag values and No
cointegration regression equation and Trace and Max-Eig are intercept No Trend model.
two test statistics used in the Johansen test to assess the null
hypothesis that there are no cointegrating relationships.

Table 6: Unrestricted Cointegration Rank Test (Trace)

Hypothesized No. of CE(s) Eigenvalue T-Statistic 0.05 Critical Value Probability
None* 0.205076 2810.267 54.96577 0.0000
At Most 1* 0.156052 2248. 48.87720 0.0000
At Most 2* 0.136566 2810.267 42.77219 0.0000
At Most 3* 0.126697 2810.267 36.63019 0.0000
At Most 4* 0.117355 2810.267 30.43961 0.0000
At Most 5* 0.103229 2810.267 24.15921 0.0000
At Most 6* 0.089582 2810.267 17.79730 0.0000
At Most 7* 0.083289 2810.267 11.22480 0.0000
At Most 8* 0.051467 2810.267 4.129906 0.0000

Cointegration is a statistical concept that helps us rejected and the cointegration test indicates that there are 9
understand the long-term relationship between two or more cointegrating equations at 0.05 level.
time series variables. In simple terms, if two variables are
cointegrated, it means they tend to move together over the So, Cointegration exists which means there is a long run
long run, even though they might show short-term relationship among these variables.
fluctuations.
If cointegration exists, we proceed with the Vector Error
Cointegration helps us uncover long-term stable Correction Model. Cointegration tests identify the long-term
relationships between non-stationary time series variables. relationships, and VECMs allow us to explore the short-run
These variables might exhibit trends or fluctuations over dynamics within these systems. It offers a unique advantage
time, but cointegration indicates they're bound together in the by combining short-run and long-run dynamics in a single
long run. The null hypothesis is that there are no cointegrating framework. They capture the immediate impacts of changes
factors among the variables. The decision criteria being if in one variable on another (short-run) while simultaneously
Trace Statistic > Critical value, then Reject Ho. accounting for the tendency to revert to the long-run
equilibrium relationships allowing a richer understanding of
Here, the Trace statistic value is greater than the critical how variables interact and influence each other.
value for all the variables. So therefore, the null hypothesis is

D. Vector Error Correction Model:

Table 7: Vector error Correction Estimates
Vector Error Correction Estimates
Cointegrating Eq: Coefficient T-Stat
NIFTY (-1) -1.0000
HANG_SENG (-1) -122.2281* -24.1955
KARACHI_100(-1) -1.029133 -0.2503
KLSE_COMPOSITE (-1) 29.51170 1.71723
KOSPI_200(-1) 40.37238* 2.82220
NIKKIE_225(-1) 38.17963* 3.85138
SET (-1) 0.434041 0.03769
SHANGHAI (-1) 5.053087 0.57993
TAIWAN_WEIGHTED (-1) 20.17730 0.28757

IJISRT24APR148 www.ijisrt.com 92
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

This table talks about the long-term relationship of the Moreover, Kospi 200 most significantly impacts Nifty
variables with Nifty 50. A variable has a significant impact 50 positively in the long run.
on the Endogenous variable if the T-Stat value lies between –
1.96 to 1.96. Here, only HangSeng, Kospi 200 and Nikkie 225
have significant impact on Nifty 50 returns.

Table 8: Error Correction Model

Error Correction D(NIFTY)
CointEq1 Coefficient 0.00082
T-stat 3.30556
D (NIFTY (-1)) Coefficient -0.89444
T-stat -43.1692
D (NIFTY (-2)) Coefficient -0.82449
T-stat -29.8440
D (NIFTY (-3)) Coefficient -0.71561
T-stat -22.3440
D (NIFTY (-4)) Coefficient -0.61225
T-stat -17.8867
D (NIFTY (-5)) Coefficient -0.45224
T-stat -12.8199
D (NIFTY (-6)) Coefficient -0.45731
T-stat -13.3971
D (NIFTY (-7)) Coefficient -0.29388
T-stat -9.17861
D (NIFTY (-8)) Coefficient -0.21696
T-stat -7.85657
D (NIFTY (-9)) Coefficient -0.11358
T-stat -5.46181
D (HANG_SENG (-1)) Coefficient 0.099997
T-stat 3.44987
D (HANG_SENG (-2)) Coefficient 0.09154
T-stat 3.40865
D (HANG_SENG (-3)) Coefficient 0.07937
T-stat 3.28953
D (HANG_SENG (-4)) Coefficient 0.06488
T-stat 3.09322
D (HANG_SENG (-5)) Coefficient 0.05109
T-stat 2.91634
D (HANG_SENG (-6)) Coefficient 0.03858
T-stat 2.78148
D (HANG_SENG (-7)) Coefficient 0.02661
T-stat 2.62542
D (HANG_SENG (-8)) Coefficient 0.01451
T-stat 2.23793
D (HANG_SENG (-9)) Coefficient 0.00788
T-stat 2.53500
D (KLSE_COMPOSITE (-1)) Coefficient -0.0828
T-stat -2.57468
D (KLSE_COMPOSITE (-2)) Coefficient -0.10647
T-stat -2.51212
D (KLSE_COMPOSITE (-3)) Coefficient -0.13531
T-stat -2.85358
D (KLSE_COMPOSITE (-4)) Coefficient -0.09815
T-stat -1.96832
D (KOSPI_200 (-6)) Coefficient 0.088596
T-stat 2.58262
D (KOSPI (-7)) Coefficient 0.097194
T-stat 2.98875

IJISRT24APR148 www.ijisrt.com 93
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

D (KOSPI (-8)) Coefficient 0.096272

T-stat 3.34476
D (KOSPI (-9)) Coefficient 0.080645
T-stat 3.8054
D (NIKKIE_225 (-4)) Coefficient 0.08151
T-stat 2.99998
D (NIKKIE_225 (-5)) Coefficient 0.08447
T-stat 3.03814
D (SET (-1)) Coefficient -0.04796
T-stat -2.16547
D (SET (-4)) Coefficient 0.085962
T-stat 2.3586
D (SET (-5)) Coefficient 0.131013
T-stat 3.48822
D (SET (-6)) Coefficient 0.085683
T-stat 2.34514
D (SET (-7)) Coefficient 0.087485
T-stat 2.53819

The second table of the VECM model talks about the shows how Nifty 50 is impacted due to the lagged values of
short-term relation of these variables with Nifty 50. This these following variables.

 The Following is the Equation:

d(NIFTY)-
d(NIFTY(-1)), d(NIFTY(-2)), d(NIFTY(-3)), d(NIFTY(-4)), d(NIFTY(-5)), d(NIFTY(-6)), d(NIFTY(-7)), d(NIFTY(-8)),
d(NIFTY(-9)), d(HANG_SENG(-1)), d(HANG_SENG(-2)), d(HANG_SENG(-3)), d(HANG_SENG(-4)), d(HANG_SENG(-5)),
d(HANG_SENG(-6)), d(HANG_SENG(-7)), d(HANG_SENG(-8)), d(HANG_SENG(-9)), d(KLSE_COMPOSITE(-1)),
d(KLSE_COMPOSITE(-2)), d(KLSE_COMPOSITE(-3)), d(KOSPI_200(-6)), d(KOSPI_200(-7)), d(KOSPI_200(-8)),
d(KOSPI_200(-9)), d(NIKKIE_225(-4)), d(NIKKIE_225(-5)), d(SET(-1)), d(SET(-4)), d(SET(-5)), d(SET(-6)), d(SET(-7))..

E. Granger Causality Test: values of another variable. If one variable Granger causes
Further, the predictive relationship of the variables was another, it suggests that the first variable contains information
seen using the Granger Causality test which is designed to that is useful for predicting the second variable's future
assess whether past values of one variable help predict future values.

Table 9: Granger Causality Test

P value
Nifty does not Granger cause Hang Seng 3.00E-05
Nifty does not Granger cause KLSE Composite 1.00E-11
Kospi 200 does not Granger cause Nifty 4.00E-24
Nifty does not Granger cause Kospi 200 5.00E-08
Nifty does not Granger cause Nikkie 225 4.00E-10
SET does not Granger cause Nifty 3.00E-08
Taiwan Weighted does not Granger cause Nifty 1.00E-08
Nikkie 225 does not Granger cause KLSE Composite 2.00E-16

The p value for these variables is less than 0.05 and V. FINDINGS AND CONCLUSIONS
therefore, null hypothesis is rejected. It can be said that Nifty
can be significant in predicting the future values of Hang First, it was found that Hangseng and Karachi 100 had
Seng, KLSE Composite, Kospi 200 and Nikkie 225. Also, the positive skewness which means that the returns of these two
future values of Nifty are affected by the previous values of indices are less than the average returns and the distribution
Kospi 200, SET and Taiwan weighted. is skewed towards the right meaning the mass of the
distribution is concentrated on the left side. However, all the
Here also, South Korea emerges out as the most other variables had negative skewness meaning the returns of
significant market for India. The indices for both these these indices are higher than the average returns.
markets are interdependent.

IJISRT24APR148 www.ijisrt.com 94
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

It was also found that co-integration exists among these was co-organized in March 2022 by the Embassy of India in
variables. It means that there is a long-term relationship Seoul.
meaning the variables tend to move together over the long
run, even though they might show short-term fluctuations. PM Narendra Modi paid a State Visit to ROK from 21-
After this, Vector Error Correction Model was employed in 22 February 2019 and unveiled a bust of Mahatma Gandhi at
which the error correction term helps to model how the prestigious Yonsei University. Foreign Ministers held
deviations from the long-term equilibrium are corrected in the discussions on political contacts, trade & investments,
short run. Long run and short run spillover is observed from defense, S&T, energy, space, semiconductors, emerging
VECM. technologies, and cultural exchanges during their bilateral
meeting on 07 April 2023 in New Delhi.
In the long run, the Kospi 200 and Nikkie 225
significantly impact the Nifty 50, where the Kospi 200 is the Bilateral trade in 2022 reached record levels of US$ 27.8
most significant, i.e., a positive impact of 40%. billion. India’s import volume is US$ 18.8 billion, while the
export volume is US$ 9 billion. India’s exports to Korea are
The predictive relationship was also seen by employing mineral fuels/oil distillates (mainly naphtha), cereals, iron,
the Granger Causality test and assessing whether past values and steel. On the other hand, Korea’s main export items are
of one variable help predict future values of another. It was automobile parts, telecommunication equipment, hot rolled
again found that the Kospi 200 and Nikkie 225 help predict iron products, petroleum refined products, base lubricating
the future values of the Nifty 50, and the Nifty 50 also helps oils, mechanical appliances, electrical machinery & parts, and
predict the future values of the Kospi 200 and Nikkie 225. iron and steel products.

An impulse response function was also employed that India and ROK defense relations have strengthened in
provides insights into how a variable reacts to a one-unit recent years. The Defense Ministers of ROK and India have
shock in another variable, allowing researchers to analyze the been interacting regularly since 2015. A Roadmap for
short-term and long-term effects of shocks in a dynamic Defense Industries Cooperation was signed between the two
system. The most prominent responses are to innovations in countries in September 2019. In recent exchanges, two ROK
the KOSPI 200, the KLSE Composite, Nikkie 225, and the naval ships visited Chennai port in October 2022. Two Indian
Hang Seng. naval ships INS Shivalik and INS Kamora visited Busan
Naval Base in November 2022.
It was confirmed that the model is stable using the AR
roots graph, as all the data points lie within or at the circle's  Bilateral trade between two countries can have a
boundary. significant impact on their respective stock market
indices:
Therefore, by applying Multivariate time series analysis
techniques with the index price data over a period from April  Increased bilateral trade can boost the revenues and
2013 to March 2023, an effort has been made to investigate profits of companies involved in export and import
the stock market integration and return spillover among India activities, positively impacting their stock prices.
and 8 other Asian markets. Conversely, trade tensions or disruptions may adversely
affect corporate earnings and stock prices.
The most significant markets for India are South Korea  It also contributes to overall economic growth, and
and Japan according to this research as it has a long run Positive economic indicators can favor stock market
relation as well as can be crucial for predicting future values indices.
of Nifty 50.  Bilateral trade relations can influence investor sentiment.
Positive trade agreements or partnerships developments
Here are a few additional insights as to why South Korea may boost investor confidence, leading to increased
is significant market for the performance of Nifty 50. investment in the stock market. Trade activities can
influence exchange rates. An increase in bilateral trade
 Bilateral Relation between India and South Korea may impact the value of the currencies involved. Currency
Both countries formed a “Strategic Partnership” in the movements, in turn, can affect the competitiveness of
year 2010, which was elevated to a “Special Strategic exports and imports, influencing the stock prices of
Partnership” in the year 2015 during the State Visit of Prime companies engaged in international trade.
Minister Narendra Modi to Seoul. There are political
relations, defense, cultural and economic relations, and VI. RECOMMENDATIONS
bilateral trade.
If overseas investors are drawn to the KOSPI 200's
India played an essential role in the Korean peninsula notable influence on the Nifty 50, it would be wise for them
after Korea's independence in 1945. In June 2020, PM to learn about the connection between these indices prior to
Narendra Modi gave a video message during an event to making any investing choices. It is still essential to diversify
commemorate the 70th anniversary of the Korean War. An the assets across a range of asset classes and geographies in
exhibition to celebrate India’s contribution to the Korean War order to reduce the risk of linked swings. It is advisable to
closely watch geopolitical developments and global

IJISRT24APR148 www.ijisrt.com 95
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

economic data to assess possible effects on the markets in [12]. Jeon, B. N., & Von Furstenberg, G. M. (1990).
South Korea and India. Depending on risk tolerance and legal Growing international co-movement in stock price
restrictions, it may be advantageous to consider derivatives indexes. Quarterly Review of Economics and
for hedging. The key to negotiating the complexities of Business, 30, 15+.
investing in indices impacted by outside events is to be https://link.gale.com/apps/doc/A9615039/AONE?u=
abreast of market movements, seek advice from financial anon~5ed58f9c&sid=googleScholar&xid=36820f14
experts knowledgeable in both markets and keep an eye on [13]. Kotha, K. K., Mukhopadhyay, C., Kiran Kumar, K., &
the big picture. In the end, comprehensive research from the Mukhopadyay, C. (n.d.). Equity Market Interlinkages:
investor’s end is crucial. Transmission of Volatility :: A Case of Us & India
EQUITY MARKET INTERLINKAGES ::
REFERENCES TRANSMISSION OF VOLATILITY A CASE OF
US AND INDIA.
[1]. Bessler, D. A., & Yang, J. (n.d.). The structure of https://www.researchgate.net/publication/249962073
interdependence in international stock markets. [14]. Merton, R. C. (1980). NBER WORKING PAPER
[2]. Eun, C. S., & Shim, S. (1989). EunShim1989. The SERIES ON ESTIMATING THE EXPECTED
Journal of Financial and Quantitative Analysis , 24(2), RETURN ON THE MARKET: AN
241–256. EXPLORATORY INVESTIGATION ON
[3]. Fan, W. (2003). An Empirical Study of Cointegration ESTIMATING THE EXPECTED RETURN ON THE
and Causality in the Asia-Pacific Stock Markets. MARKET: An Exploratory Inv~stigation.
[4]. Gębka, B., Frankfurt, V., & Serwa, D. (n.d.). Intra-and [15]. Morana, C., & Beltratti, A. (2008). Comovements in
Inter-regional Spillovers between Emerging Capital international stock markets. Journal of International
Markets around the World *. Financial Markets, Institutions and Money, 18(1), 31–
[5]. Habiba, U. E., Peilong, S., Hamid, K., & Shahzad, F. 45.
(2021). Stock Returns and Asymmetric Volatility https://doi.org/https://doi.org/10.1016/j.intfin.2006.05
Spillover Dynamics Between Asian Emerging .001
Markets. Global Business Review, 22(5), 1131–1145. [16]. Nath, G. C., & Verma, S. (2003). Study of Common
https://doi.org/10.1177/0972150919838433 Stochastic Trend and Co-Integration in the Emerging
[6]. HamaoMasulisNg1990. (n.d.). Markets A Case Study of India, Singapore and
[7]. Hsiao, F. S., Hsiao, M.-C. W., Yamashita, A., Hsiao, Taiwan.
S., of Economics, P., Hsiao Professor of Economics, [17]. nath Mukherjee, K., & Mishra, R. K. (n.d.). Stock
M.-C. W., Yamashita Professor of Economics, A., Market Interlinkages: A Study of Indian and World
Fukakusa, T., & Hsiao, M. W. (n.d.). DISCUSSION Equity Markets.
PAPERS IN ECONOMICS The Impact of the US [18]. Ng, A. (2000). Volatility spillover effects from Japan
Economy on the Asia-Pacific Region: Does it Matter? and the US to the Pacific–Basin. Journal of
The Impact of the US Economy on the Asia-Pacific International Money and Finance, 19(2), 207–233.
Region:-Does it Matter? The Impact of the US https://doi.org/https://doi.org/10.1016/S0261-
Economy on the Asia-Pacific Region: Does It Matter? 5606(00)00006-1
In Forthcoming in Journal of Asian Economics (Vol. [19]. Pretorius, E. (n.d.). Economic determinants of
14, Issue 2). emerging stock market interdependence.
[8]. Joshi, P. (2011). Return and volatility spillovers [20]. Ratanapakorn, O., & Sharma, S. C. (2002).
among Asian stock markets. SAGE Open, 1(1), 1–8. Interrelationships among regional stock indices.
https://doi.org/10.1177/2158244011413474 Review of Financial Economics, 11(2), 91–108.
[9]. Kedarnath, M., & R K, M. (2008). Munich Personal https://doi.org/https://doi.org/10.1016/S1059-
RePEc Archive Stock Market Integration and 0560(02)00103-X
Volatility Spillover:India and its Major Asian [21]. Sheng, H.-C., & Tu, A. H. (2000). A study of
Counterparts:44 UTC Stock Market Integration and cointegration and variance decomposition among
Volatility Spillover: India and its Major Asian national equity indices before and during the period of
Counterparts Stock Market Integration and Volatility the Asian financial crisis. Journal of Multinational
Spillover: India and its Major Asian Counterparts. Financial Management, 10(3), 345–365.
https://mpra.ub.uni-muenchen.de/12788/ https://doi.org/https://doi.org/10.1016/S1042-
[10]. Kumar, K., & Mukhopadhyay, C. (2007). Volatility 444X(00)00034-7
Spillovers from the US to Indian Stock Market: A [22]. Tan, K. B., Tse, Y. K., & Tse, Y. K. (2001). The
Comparison of GARCH Models. www.nasdaq.com. Integration of the East and South-East Asian Equity
[11]. ang, H., & Sul, W. (2002). The Asian financial crisis Markets The Integration of the East and South-East
and the co-movement of Asian stock markets. Journal Asian Equity Markets Citation Citation The
of Asian Economics, 13(1), 94–104. Integration of the East and South-East Asian Equity
https://doi.org/10.1016/S1049-0078(01)00115-4 Markets. In The Integration of the East and South-East
Asian Equity Markets.
https://ink.library.smu.edu.sg/soe_research/702

IJISRT24APR148 www.ijisrt.com 96
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

[23]. Yang, J., Kolari, J. W., & Min, I. (2003). Stock market [24]. Yu, J.-S., & Hassan, M. K. (2008). Global and
integration and financial crises: the case of Asia. regional integration of the Middle East and North
Applied Financial Economics, 13(7), 477–486. African (MENA) stock markets. The Quarterly
Review of Economics and Finance, 48(3), 482–504.

APPENDIX

TREND ANALYSIS

IJISRT24APR148 www.ijisrt.com 97
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

UNIT ROOT TESTS

IJISRT24APR148 www.ijisrt.com 98
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

IJISRT24APR148 www.ijisrt.com 99
Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

JOHANSON COINTEGRATION TEST

IJISRT24APR148 www.ijisrt.com 100

Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

VECTOR ERROR CORRECTION MODEL

IJISRT24APR148 www.ijisrt.com 101

Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

IJISRT24APR148 www.ijisrt.com 102

Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

IJISRT24APR148 www.ijisrt.com 103

Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

IJISRT24APR148 www.ijisrt.com 104

Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

GRANGER CAUSALITY TEST

IJISRT24APR148 www.ijisrt.com 105

Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

IJISRT24APR148 www.ijisrt.com 106

Volume 9, Issue 4, April – 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24APR148

IMPULSE RESPONSE FUNCTION

IJISRT24APR148 www.ijisrt.com 107