Article

Economic Resilience in Post-Pandemic India: Analysing Stock

Volatility and Global Links Using VAR-DCC-GARCH
and Wavelet Approach
Narayana Maharana 1 , Ashok Kumar Panigrahi 2, * , Suman Kalyan Chaudhury 3 , Minal Uprety 4 ,
Pratibha Barik 5 and Pushparaj Kulkarni 6

1 Department of Management Studies, Gayatri Vidya Parishad College of Engineering,

Visakhapatnam 530048, Andhra Pradesh, India; [Link]@[Link]
2 Department of Technology Management, NMIMS University, Dhule 425405, Maharashtra, India
3 Department of Business Administration, Berhampur University, Berhampur 760007, Odisha, India;
sumankchaudhury72@[Link]
4 Prestige Institute of Management and Research, Indore 452010, Madhya Pradesh, India;
minaluprety2022@[Link]
5 Department of Management Studies, The ICFAI University, Raipur 492001, Chhattisgarh, India;
[Link]@[Link]
6 Department of Management, Dr. Ambedkar Institute of Management Studies and Research,
Nagpur 440010, Maharashtra, India; pushparajkk@[Link]
* Correspondence: [Link]@[Link]

Abstract: This study explores the resilience of the Indian stock market in the face of global
shocks in the post-pandemic era, focusing on its volatility dynamics and interconnections
with international indices. Through a combination of Vector Autoregression (VAR), DCC-
GARCH, and wavelet analysis, we analysed the time-varying relationships between the
National Stock Exchange (NSE) of India and major global indices, including those from the
U.S., Europe, Asia-Pacific, Hong Kong and Japan. Time series data of the selected indices
have been collected for the period 1 January 2021 to 30 September 2024. Results reveal
Academic Editor: Svetlozar that while the NSE demonstrates resilience through rapid adjustments following shocks,
(Zari) Rachev it remains vulnerable to substantial spillover effects from markets such as the S&P 500
Received: 20 November 2024 and European indices. Wavelet coherence analysis identifies periods of high correlation,
Revised: 1 January 2025 particularly during major economic events, indicating that regional and global factors
Accepted: 2 January 2025 can periodically compromise market stability. Moreover, the DCC-GARCH results show
Published: 6 January 2025
a persistent but fluctuating correlation with specific markets, reflecting a connected and
Citation: Maharana, N., Panigrahi, A. adaptive nature of the Indian market that is influenced by regional dynamics. This study
K., Chaudhury, S. K., Uprety, M., Barik,
emphasises the importance of strategic risk management. It highlights critical periods
P., & Kulkarni, P. (2025). Economic
and indices that policymakers and investors should monitor closely to understand the
Resilience in Post-Pandemic India:
Analysing Stock Volatility and Global
economic resilience of the Indian financial market better. Further research could explore
Links Using VAR-DCC-GARCH and sector-specific impacts and the role of macroeconomic factors in shaping market responses.
Wavelet Approach. Journal of Risk and
Financial Management, 18(1), 18. Keywords: volatility spillover; VAR; DCC-GARCH; global indices; economic shocks;
[Link] Diebold–Yilmaz spillover index
jrfm18010018

Copyright: © 2025 by the authors.

Licensee MDPI, Basel, Switzerland.
This article is an open access article 1. Introduction
distributed under the terms and
The resilience of financial markets, particularly in emerging economies like India, has
conditions of the Creative Commons
Attribution (CC BY) license
garnered significant attention in the wake of the COVID-19 pandemic (Hasan et al., 2022;
([Link] Indrawati et al., 2020; Ray, 2023; Tiwary et al., 2022). As global financial systems faced
licenses/by/4.0/). unprecedented challenges, understanding how individual markets respond to international

J. Risk Financial Manag. 2025, 18, 18 [Link]

J. Risk Financial Manag. 2025, 18, 18 2 of 24

shocks became imperative. This research investigates whether the Indian stock market
exhibits resilience compared to its global counterparts in the post-pandemic era, utilising
advanced econometric models, namely VAR-BEKK-GARCH and wavelet analysis. Focus-
ing on the interactions between the Indian market and various foreign indices, this study
seeks to identify the nature and extent of spillover effects, contributing valuable insights to
financial stability and risk management.
The research problem centres on verifying the ability of the Indian stock market to
withstand external shocks and its interdependence with international markets. Over the
past two decades, the study of return and volatility spillovers across stock market indices
has become a prominent area of research, driven by both their practical implications and
the inherently volatile nature of financial markets, which fluctuate over time (Bonga-Bonga
& Phume, 2022; Booth et al., 1997; Mukherjee & Mishra, 2010; Yarovaya et al., 2016). The
increasing globalisation of financial markets and rapid technological advancements have
led to a deeper integration of emerging markets into the global economy, adding complex-
ity to the interactions between markets. This integration has significant implications for
portfolio management, as volatility spillovers can diminish the diversification benefits in
emerging markets, complicating the management of international portfolios. Addition-
ally, global crises, such as the Global Financial Crisis (GFC), the European Debt Crisis
(EDC), trade tensions, the COVID-19 pandemic, and geopolitical conflicts, have spurred
heightened academic interest in the contagion and interconnectedness of stock markets
across different periods: before, during, and after these disruptions (Bhowmik & Wang,
2020; Dhingra et al., 2024; Maharana et al., 2024). While previous studies have explored the
resilience of financial markets during crises, limited research has specifically addressed the
post-pandemic recovery phase and its implications for the Indian market (Maharana et al.,
2024; Tiwary et al., 2022). This study aims to fill this gap by applying a multifaceted ana-
lytical framework incorporating time-series econometrics and wavelet transforms. Doing
so will provide a better understanding of market dynamics, helping investors and policy-
makers assess the potential vulnerabilities and strengths of the Indian financial system in a
rapidly changing global environment.
This research addresses the need for robust financial frameworks in emerging
economies, where the repercussions of global shocks can be particularly pronounced
in recent times. Understanding the resilience of the Indian economy in a period of
political stability, increased global reach, and bilateral relations not only aids investors in
making better decisions but also equips policymakers with the necessary tools to enhance
regulatory frameworks and safeguard against future crises. As the global economy
continues to evolve, insights from this study will contribute to the ongoing discourse on
financial stability and economic resilience, ultimately promoting sustainable growth in
the Indian context.

2. Literature Review
The mechanisms of international information transmission between markets, evident
through both returns and volatility, hold significant theoretical and practical importance.
Volatility spillovers occur when fluctuations in one market incite similar volatility in others,
which becomes especially pronounced during market turmoil, reducing the advantages
of international portfolio diversification for investors. This effect has been intensified by
recent technological advancements, which have improved domestic investors’ access to
global information and accelerated information flow between markets. Examining return
and volatility spillovers across stock markets in various geographical regions is crucial,
enhancing our understanding of international financial interconnectedness.
J. Risk Financial Manag. 2025, 18, 18 3 of 24

The resilience of financial markets, particularly in the context of global economic

disruptions, has been a topic of increasing scholarly interest in recent years (He, 2001; Jin
& An, 2016; H. Liu et al., 2022; Maharana et al., 2024; Mishra et al., 2022). Resilience is
often defined as the ability of a market to absorb shocks and recover from disturbances
while maintaining its fundamental functions (Choptiany et al., 2021). Research has shown
that emerging markets, like India, face unique challenges and vulnerabilities compared to
developed markets, particularly during crises such as the COVID-19 pandemic (Arfaoui
& Yousaf, 2022; Chaudhary et al., 2020; Malik et al., 2022; Thangamuthu et al., 2022).
Several studies have highlighted the importance of understanding these dynamics to
formulate effective risk management strategies (Chaudhary et al., 2020; Maharana et al.,
2024; Thangamuthu et al., 2022).
A significant body of literature has explored the concept of market resilience through
various analytical frameworks. For instance, the application of econometric models such as
Vector Autoregression (VAR) and Generalised Autoregressive Conditional Heteroskedastic-
ity (GARCH) has become commonplace in assessing the interdependencies and volatility
spillovers between markets (Arfaoui & Yousaf, 2022; Karolyi, 1995; Maharana et al., 2024;
Singhal & Ghosh, 2016; Yadav et al., 2023). VAR models allow for examining the dynamic
relationships among multiple time series, making it possible to understand how shocks in
one market can influence another. GARCH models, on the other hand, provide insights
into the volatility clustering phenomenon often observed in financial time series data. The
combination of VAR and GARCH frameworks, particularly the BEKK-GARCH specifica-
tion, has proven effective in capturing the complexities of multivariate time series data and
elucidating the spillover effects between different markets (Karolyi, 1995; Maharana et al.,
2024; Singhal & Ghosh, 2016).
In recent years, the application of wavelet analysis has emerged as a powerful tool
for analysing the time-frequency characteristics of financial data (Armah et al., 2022;
D. Liu et al., 2023; Rhif et al., 2019; Ye et al., 2020). Unlike traditional time series meth-
ods, wavelet transforms enable researchers to examine how relationships between financial
markets evolve over different time scales (Armah et al., 2022). Studies such as those by
Baruník and Křehlík (2018) demonstrate that wavelet coherence can reveal significant
insights into the dynamic correlations between stock markets during periods of crisis. This
method is particularly relevant in the context of the COVID-19 pandemic, as it identifies
time-varying dependencies that static models may not capture. By integrating wavelet
analysis with GARCH models, researchers can attain a more comprehensive understanding
of market resilience and the intricate web of interactions between emerging and developed
economies (Sifuzzaman et al., 2009; Wang, 2021).
The COVID-19 pandemic has served as a catalyst for a renewed examination of
financial market resilience, with numerous studies focusing on its impacts. For example,
research by Y. Liu et al. (2022) has shown that the pandemic-induced market volatility
affected emerging markets more severely than developed ones. This disparity can be
attributed to factors such as lower liquidity, heightened investor sentiment, and greater
reliance on foreign investments. Additionally, studies have indicated that markets in
developing countries often exhibit higher sensitivity to global economic shocks due to
their interconnectedness with developed markets (Jin & An, 2016; Maharana et al., 2024;
Mishra et al., 2022). Similarly, India’s post-pandemic financial market volatility has shown
both resilience and challenges (Maharana et al., 2024). While the Indian market experienced
significant volatility, it has managed to recover and adapt, supported by robust policy
measures and economic reforms.
On the other hand, global markets have also faced volatility but have benefited from a
more synchronised monetary policy response and stronger financial safety nets (Adrian,
J. Risk Financial Manag. 2025, 18, 18 4 of 24

2020). The Indian market’s recovery has been uneven, with sectors like agriculture and
manufacturing showing resilience. In contrast, others, such as retail and services, have
gradually bounced back (Tamhane, 2020). The Indian stock market, as one of the largest in
the emerging market space, provides a unique case study for analysing these dynamics,
particularly as it navigates the recovery phase post-pandemic.
Moreover, the literature on financial market integration portrayed the significance
of understanding cross-border interactions in the context of resilience. For instance, Eun
and Resnick (1984) established that financial markets are increasingly interconnected, with
information flows and capital movements influencing market behaviour (Giudici et al.,
2020; Raddant & Kenett, 2021). Recent studies have built on this foundation, highlighting
the importance of analysing not only the direct relationships between markets but also the
spillover effects of macroeconomic shocks (Aggarwal & Jha, 2023; Mohanasundaram et al.,
2024; Raddant & Kenett, 2021).
Research on volatility spillover between global financial markets has highlighted the
increasing interconnectedness and complex dynamics among various asset classes and
regions, especially during times of crisis. Jebabli et al. (2022) examined data from MSCI
World, Emerging, and European stock markets, revealing that the COVID-19 pandemic
caused significant volatility spillover, with a pattern distinct from that observed during the
2008 financial crisis. Similarly, Khan (2024) and Li (2021) explored the volatility transmission
between developed and emerging markets, finding that developed markets primarily
drive volatility spillover to emerging markets, underscoring the dominant influence of
mature economies on the stability of developing ones. Shahzad et al. (2021), focusing on
China’s stock market across various sectors, observed that the negative impact of volatility
spillovers exceeded the positive effects during the COVID-19 pandemic, suggesting a
heightened need for investor caution. Erdoğan et al. (2020) studied the period between
2013 and 2019 to assess volatility transmission from the Islamic stock market index to
foreign exchange rates in India, Turkey, and Malaysia, finding a significant spillover from
the Turkish Islamic index to exchange rates, while other nations exhibited limited effects.
Further studies on regional volatility interactions have also provided valuable in-
sights for investment strategies. Using the DCC-GARCH technique, Zhong and Liu (2021)
examined the volatility spillover between Chinese and Southeast Asian stock markets, con-
cluding that portfolio diversification across these countries could reduce risk. Sarwar et al.
(2020) investigated the relationship betwen oil market volatility and stock market indexes
in India, Pakistan, and China, finding that volatility consistently spills from the oil mar-
ket to stock markets in these regions, limiting the effectiveness of oil assets as tools for
diversification in these economies. Together, these studies underscore the importance of
understanding cross-market spillovers in asset-specific and broader regional contexts, as
they carry significant implications for investors and policymakers aiming to mitigate risks
and design resilient investment portfolios.
Research on volatility in financial markets frequently references the GARCH family
of models to capture the persistence of volatility shocks. In the past decade, many such
studies have focussed on the interdependencies using various indices of groups of nations,
including the influence of oil prices, exchange rates, etc. Kishor and Singh (2014) explore
the relationship between stock return volatility in BRICS economies and external influences,
mainly focusing on the 2008 financial crisis and its effects from 2007 to 2013. They observed
that, with the exceptions of Brazil and China, the stock markets of BRICS countries are
significantly influenced by U.S. market movements, highlighting substantial differences
in volatility among these economies. Similarly, Tripathy (2022) addresses this subject
by examining the stock markets of Brazil, Russia, India, China, and South Africa (BRICS)
through advanced econometric modelling, including the GARCH, APARCH, ARFIMA, and
J. Risk Financial Manag. 2025, 18, 18 5 of 24

FIGARCH frameworks. The results reveal significant volatility persistence, as evidenced by

the GARCH model. At the same time, APARCH findings indicate leverage effects, meaning
adverse shocks impact volatility more than positive ones. Additionally, ARFIMA and
FIGARCH models confirm long-range dependence in returns and volatility, challenging the
Efficient Market Hypothesis (EMH) by suggesting that market behaviour in these countries
may be somewhat predictable over time.
While numerous studies have explored volatility spillovers and market interdependen-
cies, especially in the context of global crises like the 2008 financial crash and the COVID-19
pandemic, there remains a critical gap in understanding the resilience of the Indian stock
market in the post-COVID era relative to major global indices. Existing research often fo-
cuses on either emerging markets broadly or developed economies individually. Likewise,
many researchers have considered different groups of countries, such as BRICS, G7, G20,
META, etc., to verify their market interdependency of volatility in return and time depen-
dency. Yet few studies specifically address how the Indian stock market, as a prominent
emerging market, responds to shocks compared to key global indices such as NSE, AAXJ,
STOXX, GSPC, FTSE, N225, and HSI. This study addresses this gap by employing advanced
econometric techniques, including VAR, multivariate GARCH, and wavelet analysis, to
provide a detailed assessment of cross-market dependencies and resilience. By focusing on
the unique dynamics of the Indian stock market’s interactions with global counterparts,
this research aims to contribute to the literature on emerging market resilience and inform
policymakers and investors about the robustness of the Indian market in a post-pandemic
global landscape.

3. Data and Methodology

3.1. Data
Studying the resilience of Indian stock indices in the post-COVID era, particularly
amidst ongoing geopolitical tensions such as the Russia–Ukraine conflict and instability
in the Middle East, is highly justifiable as it reflects the complex interplay between global
events and market dynamics. These conflicts have profound implications for global supply
chains, energy prices, and investor sentiment, creating uncertainty that can significantly
affect emerging markets like India. By examining the Indian stock market in this context,
we can gain insights into how domestic equities respond to external shocks and geopolitical
risks, revealing the underlying strengths and vulnerabilities of the Indian economy. Addi-
tionally, understanding this resilience is vital for policymakers and investors seeking to
navigate the intricacies of a rapidly changing global landscape, thereby enhancing strategic
decision-making and risk management in an increasingly interconnected world. This study
contributes to academic discourse and provides practical implications for stakeholders
concerned about financial stability and growth in turbulent times.
In selecting the Nifty 50, MSCI Asia ex-Japan Index, STOXX Europe 600, S&P 500, FTSE
100, Nikkei 225, and Hang Seng Index as per the details given in Table 1, the objective is to
provide a comprehensive analysis of global financial market resilience in the post-COVID
era. Each index represents vital economic regions and diverse market characteristics,
capturing a broad performance spectrum across developed and emerging markets. The
Nifty 50 serves as a benchmark for the Indian market, and the MSCI Asia ex-Japan Index
allows for a focused examination of regional trends in Asia, reflecting the dynamics of
major economies in the area. The STOXX Europe 600 and FTSE 100 represent the European
market landscape, encompassing large-cap companies from various sectors. At the same
time, the S&P 500, Nikkei 225, and Hang Seng Index provide critical perspectives from the
United States, Japan, and Hong Kong, respectively. We have not included the ACWI (All
Country World Index) and EEM (Emerging Markets) like indices since they highly correlate
J. Risk Financial Manag. 2025, 18, 18 6 of 24

with GPSC and AAXJ, respectively, to avoid model-building issues. By analysing these
indices together, we try to uncover the interconnectedness and spillover effects within and
across markets, enhancing our understanding of the global financial landscape in the wake
of the pandemic.

Table 1. Indices used for the study.

Index Name Region Ticker Code

Nifty 50 India NSE
MSCI Asia ex-Japan Index Asia-Pacific AAXJ
STOXX Europe 600 Europe STOXX
S&P 500 USA GSPC
FTSE 100 United Kingdom FTSE
Nikkei 225 Japan N225
Hang Seng Index Hong Kong HSI

The selection of the study period, from 1 January 2021 to 30 September 2024, focuses on
the post-pandemic era, a crucial phase in global economic recovery. It can be observed from
Figure 1 that there was a steep fall in the stock market indices during COVID-19, and almost
all indices had recovered entirely from this blood bath by the first quarter of 2021. From
April 2021, the world witnessed the initial recovery phase from the COVID-19 pandemic as
vaccination efforts ramped up and economies gradually reopened. This period captures
the effects of various fiscal and monetary policies implemented globally to mitigate the
pandemic’s impact. Moreover, it coincides with significant global events such as supply
chain disruptions, inflationary pressures, the Russia–Ukraine war, and ongoing geopolitical
tensions in the Middle East. These factors make this period ideal for assessing the resilience
of the Indian stock market to external shocks, providing insights into how it has adapted to
a volatile post-pandemic global environment. The end of September 2024 marks a suitable
cutoff to include recent developments and capture mid-term economic responses to these
global shocks.

3.2. Method
VAR (Vector Autoregression) Model: Using the Augmented Dickey–Fuller (ADF) test,
we verified the stationarity of the return series. Then, we verified the Akaike information
criterion (AIC) or Schwarz Bayesian Criterion (SBC) to determine the optimal lag length
for the VAR model. The next step is to fit a VAR model using the selected lag length. The
VAR model can be represented as:

Yt = c + A1 Y{t−1} + A2 Y{t−2} + . . . + A p Y{t− p} + ϵt

where Yt is the vector of returns, ccc is a vector of constants, Ai are the coefficient matrices,
and ϵt is the vector of error terms.
Impulse Response Functions (IRFs): Analyse how shocks to one index affect others
over time using IRFs, which can be computed after estimating the VAR model.
Diebold–Yilmaz Spillover Index: The Diebold–Yilmaz spillover index method quan-
tifies the extent of interconnectedness and volatility spillovers across financial markets
(Diebold & Yilmaz, 2009). It begins with estimating a Vector Autoregressive (VAR) model
for the returns of the selected indices, capturing their dynamic relationships. The next
step involves calculating the Forecast Error Variance Decomposition (FEVD), which parti-
tions each variable’s total forecast error variance (index) into contributions from shocks
to itself and other indices. The Diebold–Yilmaz spillover index is then computed using
these variance decompositions, measuring the proportion of the forecast error variance of
J. Risk Financial Manag. 2025, 18, 18 7 of 24

one index attributable to shocks in other indices. The index aggregates these cross-market
contributions to reflect the total spillover effect within the system, providing a quantitative
assessment of how market shocks propagate across different indices. The Diebold–Yilmaz
spillover index is estimated using the following equations:

∑i ̸= j σij2
Total Spillover =
∑in=1 σii2
J. Risk Financial Manag. 2025, 18, x FOR PEER 2REVIEW 7 of 26
where σij is the forecast error variance attributable to shocks from variable ‘j’ to variable ‘i’,
and ‘n’ is the number of variables.
AAXJ FTSE
110 9,000

100 8,000
90 7,000
80
6,000
70
5,000
60

50 4,000
I II III IV I II III IV I II III IV I II III IV I II III I II III IV I II III IV I II III IV I II III IV I II III
2020 2021 2022 2023 2024 2020 2021 2022 2023 2024
HSI N225
44,000
32,000
40,000
28,000
36,000
24,000 32,000
28,000
20,000
24,000
16,000 20,000
16,000
12,000 I II III IV I II III IV I II III IV I II III IV I II III
I II III IV I II III IV I II III IV I II III IV I II III
2020 2021 2022 2023 2024
2020 2021 2022 2023 2024
STOXX GSPC
550 6,000

500
5,000
450

400 4,000

350
3,000
300
2,000
250 I II III IV I II III IV I II III IV I II III IV I II III
I II III IV I II III IV I II III IV I II III IV I II III
2020 2021 2022 2023 2024
2020 2021 2022 2023 2024
NSE
30,000

25,000

20,000

15,000

10,000

5,000
I II III IV I II III IV I II III IV I II III IV I II III
2020 2021 2022 2023 2024

[Link]
Figure Trendofofindices
indicesfrom
from the
the day
day when
when COVID-19
COVID-19was
wasdeclared
declaredasasa aglobal pandemic.
global pandemic.

3.2. Method
VAR (Vector Autoregression) Model: Using the Augmented Dickey–Fuller (ADF)
test, we verified the stationarity of the return series. Then, we verified the Akaike infor-
mation criterion (AIC) or Schwarz Bayesian Criterion (SBC) to determine the optimal lag
length for the VAR model. The next step is to fit a VAR model using the selected lag length.
J. Risk Financial Manag. 2025, 18, 18 8 of 24

The Univariate GARCH Estimation: For each time series (index), estimate a univariate
GARCH model. A common choice is the GARCH (1,1) model, which can be expressed as:

R t = µ + ϵt

where ϵt = σt zt and zt ∼ N (0, 1) (standard normal distribution).

Suppose the results of the GARCH (1,1) model diagnostics for autocorrelation are not
satisfied; it requires further adjustments of leg structure or the adoption of complex models
like BEKK-GARCH (Bollerslev, 1986; Hafner et al., 2022; Tsay, 2010).
The GARCH (1,1) model for the conditional variance σt2 is given by:

p q
σt2 = α0 + ∑ αi ϵt2−i + ∑ β j σt2− j
i =1 j =1

In this framework, Rt is the return at time t, µ is the mean return, ϵt is the innovation
or shock at time t, zt is a standard normal variable, σt is the conditional variance, and
α0 , αi , β j are parameters that need to be estimated. The first step is to fit a univariate
GARCH model for each asset’s returns to capture their volatility dynamics. Use Maximum
Likelihood Estimation (MLE) to estimate the parameters ω, α, and β for each univariate
GARCH model.
DCC-GARCH Model: The Dynamic Conditional Correlation Generalised Autore-
gressive Conditional Heteroskedasticity (DCC-GARCH) model is a powerful econometric
technique for analysing time-varying correlations between multiple financial time series.
This model extends the standard GARCH approach by allowing the conditional correla-
tions between assets to vary over time, capturing dynamic relationships more flexibly. The
DCC-GARCH model operates in two steps: first, univariate GARCH models are fitted to
each series to estimate conditional variances; then, a dynamic correlation matrix can be cal-
culated using standardised residuals from these GARCH models. This two-step approach
helps identify how correlations evolve in response to market events, which is crucial for un-
derstanding volatility spillovers and portfolio risk management. The DCC-GARCH model
is prevalent for financial market analysis because it captures the co-movement of assets in
a dynamic and time-sensitive manner, making it helpful in assessing interconnected risks
and market dependencies (Engle, 2002). The DCC model is specified as follows:
′
Conditional Correlation: Qt = (1 − α − β) Q + α ẑt−1 zt−1 + β Qt−1 .
In this equation, Qt is the conditional correlation matrix, Q is the unconditional
correlation matrix of the residuals, while α and β are parameters that control the weights
of the previous correlations and residuals, respectively, with α, β ≥ 0 and α + β < 1. The
DCC model effectively captures how correlations change over time based on the lagged
information from the standardised residuals.
Wavelet Coherence (WCOH): WCOH complements the analyses by quantifying the
local correlation between the Indian stock market and selected global indices over time
and frequency. This method helps assess how the strength of the relationship between the
Indian market and global indices varies during different market conditions (Grinsted et al.,
2004; Torrence & Compo, 1998).
The mathematical formulation of WCOH is as follows:

| XWT ( a, b)|2
WCOH ( a, b) =
|W1 ( a, b)|2 |W2 ( a, b)|2

where W 1 and W 2 are the wavelet transforms of the individual time series. The WCOH
provides insights into the strength and significance of the correlation between the series at
various scales and time points.
J. Risk Financial Manag. 2025, 18, 18 9 of 24

4. Observations
4.1. Descriptive Statistics
It can be noted from Table 2 that the means return range widely, with N225 (12.7030)
and NSE (12.4723) showing the highest average returns, while AAXJ has a slight negative
mean (−0.0102), suggesting a slight downward trend. The median values vary, with several
indices like AAXJ, HSI, and STOXX at zero, indicating a high occurrence of neutral or zero
returns. Notably, the maximum and minimum values for N225 and NSE reveal extreme
fluctuations, with N225 reaching a peak of 3217.0410 and a low of −4451.2793, signifying
high volatility. Standard deviations confirm this volatility, with N225 and NSE exhibiting
substantial variability (400.5728 and 161.6786, respectively). Skewness values suggest
that most distributions are slightly left-skewed, except for AAXJ and HSI, which show
mild right-skewness, implying asymmetry and occasional more significant positive or
negative returns. The high kurtosis values, especially for N225 (23.5536) and NSE (10.5541),
suggest heavy-tailed distributions, indicating more frequent extreme returns than a normal
distribution. The significant Jarque–Bera statistics confirm that none of the indices returns
follow a normal distribution, primarily due to their skewed and leptokurtic nature.

Table 2. Descriptive statistics using the daily return data (N = 975).

AAXJ FTSE GSPC HSI N225 NSE STOXX

Mean −0.0102 1.9080 2.0329 −6.7680 12.7030 12.4723 0.1311
Median 0.0000 2.8999 1.0801 0.0000 0.8301 6.6992 0.3100
Maximum 6.3300 282.5000 207.8000 1672.4199 3217.0410 735.8496 19.4400
Minimum −2.9300 −292.6001 −177.7202 −1129.6602 −4451.2793 −1379.4004 −20.3300
Std. Dev. 0.9091 59.2137 44.1972 315.2880 400.5728 161.6786 3.9330
Skewness 0.2876 −0.4683 −0.3000 0.2458 −1.1234 −0.7832 −0.5158
Kurtosis 6.0496 6.3379 4.4828 4.9666 23.5536 10.5541 5.8549
Jarque–Bera 391.2647 * 488.2601 * 103.9430 * 166.9356 * 17367.0813 * 2417.9006 * 374.3457 *
* Indicates significance level at p-values less than 0.01.

Table 3 presents the Augmented Dickey–Fuller (ADF) and Phillips–Perron (PP) tests
for stationarity, revealing consistent results across the variables. At the level (original form),
none of the indices (except FTSE in both ADF and PP tests) are stationary, as indicated
by high p-values (greater than 0.05). This suggests the presence of a unit root, implying
non-stationarity in most of the indices at their levels. However, when differenced once, all
variables become stationary, evidenced by highly significant p-values (0.000) in both ADF
and PP tests, meaning they reject the null hypothesis of a unit root at the first difference.

Table 3. Unit root tests.

Augmented Dickey–Fuller Test (ADF) Phillips–Perron Test (PP)

Level At First Difference Level At First Difference
Variables t-Statistic Prob. t-Statistic Prob. t-Statistic Prob. t-Statistic Prob.
AAXJ −0.9892 0.944 −33.1635 0.000 −0.8426 0.960 −33.1860 0.000
FTSE −4.2177 0.004 −32.3240 0.000 −4.1083 0.006 −32.4989 0.000
GSPC −1.2474 0.899 −31.0539 0.000 −1.1450 0.920 −31.0933 0.000
HSI −1.7887 0.710 −14.4577 0.000 −1.7048 0.749 −30.5488 0.000
N225 −2.1363 0.524 −31.9512 0.000 −2.0807 0.555 −31.9512 0.000
NSE −1.2831 0.891 −32.1889 0.000 −1.1496 0.919 −32.2478 0.000
STOXX −2.3116 0.427 −19.5721 0.000 −2.2092 0.483 −31.3784 0.000
 The correlation matrix in Figure 2 shows varying degrees of association
J. Risk Financial Manag. 2025, 18, 18 10 of 24
indices. All the correlation values are positive and significant at p-values less
The strength of correlation between two variables indicated with a relatively d
of the
Thegreen colour
correlation for positive
matrix in Figure 2correlation
shows varying and orange
degrees colour for
of association negative
among the corre
indices. All the correlation values are positive and significant at p-values
STOXX index strongly correlates with FTSE (0.851) and GSPC (0.516), indica less than 0.01. The
strength of correlation between two variables indicated with a relatively darker shed of the
positive association with these markets, likely reflecting regional economic co
green colour for positive correlation and orange colour for negative correlation. The STOXX
AAXJ is moderately
index strongly correlates correlated withand
with FTSE (0.851) GSPCGSPC (0.646)
(0.516),and STOXX
indicating (0.494),
a high positivesuggesti
what moves
association withwith
these these global
markets, likelyindices.
reflecting FTSE
regionaland NSE also
economic exhibit AAXJ
connections. moderate c
is moderately correlated with GSPC (0.646) and STOXX (0.494),
with each other (0.382) and STOXX, reflecting potential interdependencies. Nsuggesting it somewhat
moves with these global indices. FTSE and NSE also exhibit moderate correlations with
ever, has generally low correlations with the other indices, indicating weake
each other (0.382) and STOXX, reflecting potential interdependencies. N225, however, has
ment with
generally low global markets,
correlations with thepossibly dueindicating
other indices, to regional weaker market dynamics
co-movement with uniqu
While specific
global markets, indices
possibly duelike STOXX
to regional anddynamics
market FTSE showuniquestrong
to [Link],
While specific othe
indices like STOXX and FTSE show strong relationships,
larly N225, have more isolated movement patterns. In contrast, others, particularly N225,
NSEhaveshows a
more isolated movement patterns. In contrast, NSE shows a moderate correlation with the
correlation with the other global indices.
other global indices.

Figure 2. Inter indices bi-variate correlation matrix.

Figure 2. Inter indices bi-variate correlation matrix.
Figures 3 and 4 illustrate the trend of the daily closing prices and log differentiated
returns of the selected global indices for the post-pandemic period. FTSE and NSE show a
rising trend, whereas AAXJ and HIS show a declining trend in the post-pandemic period.
On the other hand, STOXX, N225, and GSPC recorded growth after the 4th quarter of 2022.

4.2. The VAR Model

The VAR results in Table 4 offer insights into the dynamic relationships among the
indices. Based on the VAR lag selection criteria in Table 5, lag two is chosen for interpre-
tation according to the AIC. However, both lags are considered in the analysis, as the SC
and HQ criteria recommend selecting lag 1. Notably, the lagged values of AAXJ exhibit
a strong positive influence on HSI, with AAXJ(−1) showing a highly significant effect on
HSI (11.2685), implying that past values of AAXJ have a substantial influence on HSI. Simi-
larly, GSPC(−1) strongly impacts multiple indices, including FTSE (5.0360), N225 (7.7516),
NSE (5.1035), and STOXX (7.2433), suggesting that U.S. market movements significantly
affect these indices, particularly N225. FTSE(−1) shows a negative and significant effect
on N225, indicating that FTSE declines could negatively impact N225. NSE(−1) is also
influential, with adverse and significant effects on HSI and NSE, highlighting internal
J. Risk Financial Manag. 2025, 18, 18 Figures 3 and 4 illustrate the trend of the daily closing prices and log differentiated
11 of 24
returns of the selected global indices for the post-pandemic period. FTSE and NSE show
a rising trend, whereas AAXJ and HIS show a declining trend in the post-pandemic pe-
riod. On the within
momentum other hand, STOXX,
the NSE index.N225, and−GSPC
STOXX( recorded
1) influences growth
N225 after pointing
(5.3139), the 4th quarter
to the
of 2022.
interdependence between European and Japanese markets.

AAXJ FTSE
110 8,500
100 8,000
90
7,500
80
7,000
70
60 6,500

50 6,000
I II III IV I II III IV I II III IV I II III I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

HSI N225
32,000 44,000

28,000 40,000

24,000 36,000

20,000 32,000

16,000 28,000

12,000 24,000
I II III IV I II III IV I II III IV I II III I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

STOXX GSPC
560 6,000

520 5,500

480 5,000

440 4,500

400 4,000

360 3,500
I II III IV I II III IV I II III IV I II III I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

NSE
28,000

24,000

20,000

16,000

12,000
I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024

Figure 3. Trend
Trend of
of the
the selected
selected indices
indices (post-pandemic).
(post-pandemic).
J. Risk Financial Manag. 2025, 18, 18
x FOR PEER REVIEW 1212of
of 26
24

Log Differenced AAXJ Log Differenced FTSE

0.100 0.04
0.075 0.02
0.050
0.00
0.025
-0.02
0.000
-0.025 -0.04

-0.050 -0.06
I II III IV I II III IV I II III IV I II III I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

Log Differenced HSI Log Differenced N225

0.12 0.10

0.08 0.05

0.04 0.00

0.00 -0.05

-0.04 -0.10

-0.08 -0.15
I II III IV I II III IV I II III IV I II III I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

Log Differenced STOXX Log Differenced GSPC

0.06 0.06
0.04 0.04
0.02 0.02
0.00 0.00
-0.02 -0.02
-0.04 -0.04
-0.06 -0.06
I II III IV I II III IV I II III IV I II III I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

Log Differenced NSE

0.06
0.04
0.02
0.00
-0.02
-0.04
-0.06
-0.08
I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024

Figure
Figure 4.
4. Daily
Daily return
return plot
plot of
of the
the selected
selected indices
indices (post-pandemic).
(post-pandemic).
J. Risk Financial Manag. 2025, 18, 18 13 of 24

Table 4. VAR model.

AAXJ FTSE GSPC HSI N225 NSE STOXX

AAXJ(−1) Coeff. −0.03829 0.050133 0.007312 0.756044 0.080821 0.09667 0.006091
SE 0.059321 0.038345 0.050617 0.067094 0.053885 0.041468 0.041139
t [−0.64551] [1.30739] [0.14445] [11.2685] [1.49987] [2.33120] [0.14806]
AAXJ(−2) Coeff. 0.140704 0.042043 0.093127 0.306489 0.040286 0.099995 0.05417
SE 0.059262 0.038307 0.050566 0.067026 0.053831 0.041426 0.041098
t [2.37429] [1.09753] [1.84168] [4.57267] [0.74838] [2.41379] [1.31807]
FTSE(−1) Coeff. −0.05274 0.01693 −0.06601 0.117186 −0.24365 −0.004 0.08628
SE 0.094431 0.061041 0.080576 0.106804 0.085778 0.066011 0.065488
t [−0.55851] [0.27736] [−0.81920] [1.09721] [−2.84044] [−0.06057] [1.31750]
FTSE(−2) Coeff. 0.007491 0.010076 0.02965 0.069441 0.155993 −0.03754 0.013907
SE 0.094077 0.060812 0.080274 0.106404 0.085456 0.065764 0.065243
t [0.07962] [0.16569] [0.36937] [0.65262] [1.82541] [−0.57078] [0.21315]
GSPC(−1) Coeff. −0.05052 0.188798 −0.02646 −0.15976 0.408374 0.206909 0.291335
SE 0.057997 0.03749 0.049488 0.065596 0.052683 0.040543 0.040221
t [−0.87105] [5.03601] [−0.53477] [−2.43547] [7.75158] [5.10350] [7.24331]
GSPC(−2) Coeff. −0.12129 0.033102 −0.12018 0.015827 0.134225 0.021069 0.025325
SE 0.061161 0.039535 0.052187 0.069175 0.055557 0.042754 0.042415
t [−1.98306] [0.83728] [−2.30284] [0.22879] [2.41601] [0.49278] [0.59708]
HSI(−1) Coeff. −0.02553 −0.01537 0.005573 −0.3616 −0.02266 −0.07224 −0.01666
SE 0.039257 0.025376 0.033497 0.044401 0.03566 0.027442 0.027225
t [−0.65037] [−0.60577] [0.16637] [−8.14387] [−0.63544] [−2.63235] [−0.61192]
HSI(−2) Coeff. −0.09796 −0.03484 −0.08114 −0.15405 0.017166 −0.04676 −0.06288
SE 0.035181 0.022741 0.030019 0.039791 0.031957 0.024593 0.024398
t [−2.78445] [−1.53212] [−2.70292] [−3.87154] [0.53714] [−1.90126] [−2.57710]
N225(−1) Coeff. 0.054537 0.006983 −0.00284 −0.0294 −0.17047 −0.01053 0.001618
SE 0.037685 0.02436 0.032155 0.042622 0.034231 0.026343 0.026134
t [1.44718] [0.28667] [−0.08842] [−0.68973] [−4.97997] [−0.39986] [0.06192]
N225(−2) Coeff. 0.062819 −0.01293 0.036381 0.041528 −0.01689 0.007454 −0.00115
SE 0.035114 0.022698 0.029962 0.039715 0.031896 0.024546 0.024352
t [1.78898] [−0.56964] [1.21425] [1.04564] [−0.52964] [0.30369] [−0.04704]
NSE(−1) Coeff. −0.11548 −0.02573 −0.06922 −0.23541 −0.09876 −0.1104 −0.02223
SE 0.051561 0.033329 0.043996 0.058317 0.046836 0.036043 0.035758
t [−2.23974] [−0.77197] [−1.57326] [−4.03680] [−2.10869] [−3.06304] [−0.62160]
NSE(−2) Coeff. −0.09604 −0.05979 −0.08803 −0.12817 −0.01354 −0.04698 −0.05673
SE 0.051135 0.033054 0.043632 0.057834 0.046449 0.035745 0.035462
t [−1.87820] [−1.80902] [−2.01748] [−2.21614] [−0.29159] [−1.31437] [−1.59985]
STOXX(−1) Coeff. 0.160792 −0.19343 0.123431 0.130812 0.469441 0.051938 −0.25588
SE 0.097254 0.062865 0.082984 0.109997 0.088342 0.067984 0.067446
t [1.65332] [−3.07691] [1.48740] [1.18924] [5.31391] [0.76397] [−3.79389]
STOXX(−2) Coeff. 0.040734 −0.02765 0.074089 0.064007 −0.18667 0.023602 −0.03722
SE 0.097879 0.063269 0.083518 0.110704 0.08891 0.068421 0.067879
t [0.41617] [−0.43702] [0.88711] [0.57819] [−2.09955] [0.34495] [−0.54834]
C Coeff. −5.65 × 10−5 0.000243 0.000539 −0.00013 0.000245 0.000605 0.000228
SE 0.000393 0.000254 0.000335 0.000444 0.000357 0.000274 0.000272
t [−0.14381] [0.95566] [1.60964] [−0.29931] [0.68612] [2.20585] [0.83836]
Source: Authors own interpretation.

Table 5. Leg length selection criteria.

Lag LogL LR FPE AIC SC HQ

0 22,716.97 NA 9.42 × 10−30 −46.9700 −46.9347 −46.9565
1 23,099.45 758.6143 4.72 × 10−30 −47.6597 −47.3773 * −47.5522 *
2 23,165.23 129.5204 4.56 × 10−30 * −47.6943 * −47.1651 −47.4929
3 23,210.64 88.75905 4.60 × 10−30 −47.687 −46.9107 −47.3914
4 23,253.63 83.39746 * 4.66 × 10−30 −47.6745 −46.6513 −47.2850
5 23,285.26 60.90666 4.83 × 10−30 −47.6386 −46.3684 −47.1550
* Indicates lag order selected by the criterion, LR: sequential modified LR test statistic (each test at 5% level); FPE:
Final prediction error; AIC: Akaike information criterion; SC: Schwarz information criterion; HQ: Hannan–Quinn
information criterion.

The impulse response graphs given in Figure 5 illustrate how the National Stock
Exchange (NSE) reacts to unexpected shocks or innovations from eight global indices over
10 days. Each plot provides insight into the NSE’s sensitivity to a one-standard-deviation
innovation originating from a particular international market. Observing these responses
J. Risk Financial Manag. 2025, 18, 18 14 of 24

J. Risk Financial Manag. 2025, 18, x FOR PEERus

helps REVIEW
understand 15 have
the degree and duration of influence that global market events of 26

on the NSE and the stability of these influences over time.

Response to Cholesky One S.D. (d.f. adjusted) Innovations

95% CI using analytic asymptotic S.E.s
Response of NSE to AAXJ Innovation Response of NSE to STOXX Innovation

0.003 0.003

0.002 0.002

0.001 0.001

0.000 0.000

-0.001 -0.001
1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10

Response of NSE to GSPC Innovation Response of NSE to FTSE Innovation

0.003 0.003

0.002 0.002

0.001 0.001

0.000 0.000

-0.001 -0.001
1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10

Response of NSE to N225 Innovation Response of NSE to HSI Innovation

0.003 0.003

0.002 0.002

0.001 0.001

0.000 0.000

-0.001 -0.001
1 2 3 4 5 6 7 8 9 10 1 2 3 4 5 6 7 8 9 10

Figure 5. Impulse
Impulse response
response curves
curves for the
the response
response of
of NSE-India
NSE-India to the
the innovations
innovations of global
global indices.
indices.

In most
The cases,
prompt the immediate
decline also reflects response of the NSE
how rapidly the NSEto a adjusts
shock from a global
to these index
external is
fac-
noticeable
tors, with within the first
the impact one to
fading as three [Link]
the local For instance,
absorbs indices like AAXJ the
and processes (Asianewex-Japan)
infor-
and FTSE
mation. In (UK) appear
contrast, to have
indices likeathesubstantial initialand
N225 (Japan) impact,
STOXX with the response
(Europe) exhibitofathe NSE
smaller
spiking
initial withinindicating
impact, this earlyatimeframe.
more limited This suggests
influence on that
the [Link] NSEGSPC is (S&P
highly responsive
500) also shows to
sudden changes in these indices, possibly due to economic ties, trading
a noticeable impact, though slightly less intense, which reflects the influence of the global patterns, or investor
sentiment
and linked to
U.S. markets onthese regions.
the NSE. The However, after this intervals
shaded confidence initial surge,
around the response
each responsegenerally
line
starts to decline, indicating that while the NSE reacts quickly to foreign
also provide additional insight into the stability of these reactions. Tighter intervals reflect market shocks, this
areaction is often short-lived.
higher confidence level in the measured response. In comparison, wider intervals denote
The prompt decline
more significant uncertainty, also suggesting
reflects howthatrapidly the NSE
the impact of adjusts to these
some indices onexternal
the NSEfactors,
is less
with the impact
consistent or more fading
variableas the
over local
[Link] absorbs and processes the new information.
In contrast,
The Grangerindices like thetests
causality N225in(Japan)
Table 6and STOXX
reveal (Europe)
significant exhibit a smaller
bidirectional influencesinitial
be-
impact,the
tween indicating
NSE and aseveralmore limited influence
international on the
indices. NSE.
AAXJ, FTSE,GSPC (S&Pand
GSPC, 500) also shows
STOXX signifi-a
noticeable
cantly impact,
Granger cause though
the NSEslightly
at theless
1%intense,
level ofwhich reflectsindicating
significance, the influence thatofpast
the values
global
and
of [Link]
these markets on the
help [Link]
predict Themovements.
shaded confidence
However,intervals
HSI and around
N225eachdo notresponse line
show sig-
also provide additional insight into the stability of these reactions.
nificant causality towards the NSE. Conversely, the NSE Granger causes FTSE and N225 Tighter intervals reflect
at the 5% level of significance, suggesting weak predictive power of the NSE over these
indices. The relationship with AAXJ and STOXX is poor, with marginal significance, while
J. Risk Financial Manag. 2025, 18, 18 15 of 24

a higher confidence level in the measured response. In comparison, wider intervals denote
more significant uncertainty, suggesting that the impact of some indices on the NSE is less
consistent or more variable over time.
The Granger causality tests in Table 6 reveal significant bidirectional influences be-
tween the NSE and several international indices. AAXJ, FTSE, GSPC, and STOXX signifi-
cantly Granger cause the NSE at the 1% level of significance, indicating that past values
of these indices help predict NSE movements. However, HSI and N225 do not show sig-
nificant causality towards the NSE. Conversely, the NSE Granger causes FTSE and N225
at the 5% level of significance, suggesting weak predictive power of the NSE over these
indices. The relationship with AAXJ and STOXX is poor, with marginal significance, while
no causality is observed from NSE to GSPC or HSI. It shows a stronger external influence
on the NSE than its influence on global indices, except for selective interactions.

Table 6. VAR Granger causality tests.

Null Hypothesis Leg Observations F-Statistics Sig.

AAXJ does not Granger Cause NSE 2 973 25.474 0.000
FTSE does not Granger Cause NSE 2 973 9.185 0.000
GSPC does not Granger Cause NSE 2 973 56.198 0.000
HSI does not Granger Cause NSE 2 973 0.023 0.977
N225 does not Granger Cause NSE 2 973 0.870 0.419
STOXX does not Granger Cause NSE 2 973 19.389 0.000
NSE does not Granger Cause AAXJ 2 973 2.434 0.088
NSE does not Granger Cause FTSE 2 973 3.080 0.046
NSE does not Granger Cause GSPC 2 973 1.521 0.219
NSE does not Granger Cause HSI 2 973 0.809 0.445
NSE does not Granger Cause N225 2 973 3.806 0.023
NSE does not Granger Cause STOXX 2 973 2.915 0.055

4.3. Diebold–Yilmaz Spillover Index

The Diebold–Yilmaz spillover index illustrates the degree of interconnectedness or
spillover among financial markets or variables over time. Higher values on the graph indi-
cate increased spillover, meaning shocks in one market or variable significantly influence
others, often reflecting periods of heightened volatility or economic uncertainty. Lower
values suggest weaker linkages or more independence between markets, indicating that
each variable or market behaves more independently (Diebold & Yilmaz, 2009, 2023). The
Diebold–Yilmaz spillover index graphs in Figure 6 depict the spillover effect or connected-
ness between the National Stock Exchange of India (NSE) and several prominent global
indices over time, using a 200-day window with a 10-step horizon and a lag of two. In
these graphs, the magnitude of the spillover is reflected in the values on the y-axis, which
typically range from 0 to 20, where higher values indicate a stronger spillover effect and,
therefore, a more significant impact on the NSE.
The Diebold–Yilmaz spillover graphs reveal moderate to significant spillover effects
from the STOXX (Europe), N225 (Nikkei 225), GSPC (S&P 500), and FTSE (UK) indices
to the NSE. The impact from European and Japanese markets peaks around late 2021
and mid-2022, reflecting how specific market events in these regions influenced Indian
market volatility. However, this influence appears to diminish in 2023, indicating a possible
decoupling or enhanced resilience of the NSE to these markets. The GSPC exhibits a strong
spillover, likely due to the influence of U.S. economic factors, while the FTSE shows a
consistent, albeit lower, level of impact, possibly stemming from economic ties between
the UK and India. This diminishing spillover in 2023 suggests reduced volatility in these
markets or a weakening linkage with the NSE.
 Financial Manag.
J. Risk Financial Manag. 2025,
2025, 18,
18, 18
x FOR PEER REVIEW 17
16 of 26
of 24

NSE-AAXJ NSE-STOXX
18 24
16
20
14
12 16
10
12
8
6 8
4
4
2
0 0
IV I II III IV I II III IV I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

NSE-GSPC NSE-FTSE

16 20

14
16
12
10 12
8
8
6
4
4
2
0 0
IV I II III IV I II III IV I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

NSE-N225 NSE-HSI
16 12
14
10
12
10 8

8 6
6
4
4
2 2

0 0
IV I II III IV I II III IV I II III IV I II III IV I II III IV I II III
2021 2022 2023 2024 2021 2022 2023 2024

Figure 6.
Figure 6. Diebold–Yilmaz
Diebold–Yilmaz spillover
spillover index
index (200-day
(200-day window,
window,10
10step
stephorizons,
horizons,22lag).
lag).

4.4. The DCC-GARCH

In contrast, Model
the HSI (Hang Seng) demonstrates lower overall spillovers, likely due to
less integration between(1,1)
The DCC-GARCH the Chinese and Indian
model results markets.
in Table However,
7 highlight the AAXJ and
the individual (Asiajoint
ex-
Japan) index
volatility displaysofa seven
dynamics fluctuating but moderate
financial impact, reflecting
indices, including the NSE. the
Theinterconnectedness
model, estimated
of Asian
under markets andnormal
a multivariate their regional dynamics.
distribution The variable
assumption, spillover
captures how eachintensity
index’sfrom
pastthere-
AAXJ suggests that specific regional events may increase NSE volatility, underscoring
turns and volatility affect its current volatility and the time-varying correlations between the
integration of the
these indices. WithIndian market within
a log-likelihood theofbroader
value Asian
23,235.09 andeconomic landscape.
a high average log-likelihood,
the model fits the data well, suggesting that the chosen parameters effectively capture the
4.4. The DCC-GARCH Model
market dynamics and interactions between indices. For each index, the coefficients offer
Theinto
insights DCC-GARCH
their unique(1,1) modelstructures.
volatility results in The
Table 7 highlight
mean thefor
return (μ) individual
the NSE isand joint
positive
volatility dynamics
and statistically of sevenindicating
significant, financial indices, including
that the NSE tendsthe [Link]
to yield The model, estimated
returns on av-
under
erage. The persistence in volatility, shown by high β values across indices (e.g., 0.8228past
a multivariate normal distribution assumption, captures how each index’s for
returns and volatility
NSE, 0.8903 for AAXJ,affect its current
and 0.8804 volatility
for HSI), and that
suggests the time-varying
past volatilitycorrelations between
strongly influences
these
currentindices. Witha acommon
volatility, log-likelihood
trait invalue of 23,235.09
financial [Link] a high average
Significant α values,log-likelihood,
particularly
the model fits the data well, suggesting that the chosen parameters
for indices like the STOXX (0.1512) and FTSE (0.1264), highlight the immediate effectively capture
impactthe
of
market dynamics and interactions between indices. For each index, the coefficients
past shocks on present volatility. This effect is critical in understanding how recent market offer
events can affect ongoing risk levels for each index.
J. Risk Financial Manag. 2025, 18, 18 17 of 24

insights into their unique volatility structures. The mean return (µ) for the NSE is positive
and statistically significant, indicating that the NSE tends to yield positive returns on
average. The persistence in volatility, shown by high β values across indices (e.g., 0.8228 for
NSE, 0.8903 for AAXJ, and 0.8804 for HSI), suggests that past volatility strongly influences
current volatility, a common trait in financial markets. Significant α values, particularly
for indices like the STOXX (0.1512) and FTSE (0.1264), highlight the immediate impact of
past shocks on present volatility. This effect is critical in understanding how recent market
events can affect ongoing risk levels for each index.

Table 7. DCC-GARCH model.

Parameters Estimate SE t-Value Sig. Q (20) Q2 (20)

NSE µ 0.000978 0.000289 3.387790 0.001 27.9520 19.6063
ω 0.000004 0.000010 0.387500 0.698 (0.1105) (0.4828)
α 0.137807 0.043685 3.154590 0.002
β 0.822771 0.080420 10.230940 0.000
AAXJ µ −0.000068 0.000370 −0.182620 0.855 20.1445 16.3681
ω 0.000006 0.000001 4.946620 0.000 (0.4489) (0.6935)
α 0.068840 0.005943 11.583370 0.000
β 0.890296 0.011555 77.049700 0.000
STOXX µ 0.000515 0.000262 1.968750 0.049 14.2735 6.8124
ω 0.000007 0.000001 10.693170 0.000 (0.8164) (0.9973)
α 0.151183 0.023424 6.454180 0.000
β 0.761288 0.028720 26.507560 0.000
GSPC µ 0.000739 0.000273 2.705830 0.007 28.9015 19.3100
ω 0.000002 0.000010 0.158050 0.874 (0.0897) (0.5018)
α 0.072643 0.113097 0.642310 0.521
β 0.912570 0.130162 7.011050 0.000
FTSE µ 0.000361 0.000234 1.543100 0.123 17.3539 9.3280
ω 0.000011 0.000000 55.422260 0.000 (0.6299) (0.9788)
α 0.126431 0.014575 8.674560 0.000
β 0.701930 0.033805 20.764120 0.000
N225 µ 0.000595 0.000361 1.649100 0.099 10.8881 8.5108
ω 0.000042 0.000020 2.091630 0.036 (0.9491) (0.9842)
α 0.153559 0.066948 2.293720 0.022
β 0.559411 0.172610 3.240890 0.001
HSI µ −0.000162 0.000448 −0.361970 0.717 24.7376 16.9049
ω 0.000011 0.000001 13.524990 0.000 (0.0715) (0.6591)
α 0.073925 0.004986 14.825480 0.000
β 0.880359 0.008692 101.281520 0.000
[Joint]dcc α1 0.020206 0.006182 3.268230 0.001
[Joint]dcc β1 0.824140 0.096115 8.574480 0.000

The DCC parameters, dcc α1 and dcc β1 , capture the dynamics of time-varying correla-
tions between the indices. The positive, significant estimates for both dcca1 (0.0202) and
dccb1 (0.8241) suggest that correlations between the indices are both influenced by recent
correlation shocks and exhibit a high level of persistence over time. This interconnectedness
implies that volatility shocks in one market can lead to sustained correlation changes across
others, a sign of volatility spillover where risks and returns are not isolated but are instead
transmitted across global markets. This is particularly evident during turbulent periods,
where persistent correlations may amplify systemic risk. The high β values for each index
indicate strong volatility persistence, meaning that once volatility increases in one index,
it is likely to remain elevated, affecting not only that market but potentially increasing
risk across correlated markets as well. Further, the information criteria values, with a
low Akaike score of −47.557, further support the model’s appropriateness for capturing
these dynamics. These criteria penalise model complexity and suggest that the model
effectively balances fit and simplicity. As such, the residual Q (20) and squared residual
 J. Risk Financial Manag. 2025, 18, 18 18 of 24

diagnostics Q2 (20) show the absence of autocorrelation in the residuals and confirm that
the model has adequately captured higher moments or volatility clustering. Squared resid-
uals typically exhibit autocorrelation if there are unmodeled patterns in the volatility. This
outcome validates the model’s specification, showing that it fits the data well without
leaving unexplained structures in the returns or volatility.
The time-varying correlations between India and other global markets (Asia Pacific,
USA, Europe, UK, Hong Kong, and Japan) estimated using the DCC-GARCH model
presented in Figure 7, reveal significant insights into the dynamic interconnectedness of
India’s financial market. The correlations with Asia Pacific and Hong Kong are relatively
low, typically ranging from 0.15 to 0.35, indicating modest but fluctuating linkages driven
by regional economic events. The correlation with the USA is similarly low, suggesting
distinct economic influences. However, certain global financial events cause brief increases
in co-movement. In contrast, correlations with Europe and the UK are generally higher,
J. Risk Financial Manag. 2025, 18, x FOR PEER REVIEW 19 of 26
often ranging between 0.25 and 0.55, reflecting stronger financial linkages, possibly due to
similar responses to global economic conditions and investment flows. Japan’s correlation
with India shows moderate fluctuations, suggesting limited alignment influenced by unique
volatility.
regionalThis
and outcome
economicvalidates
policies. the model’soccasional
However, specification, showing
alignment thatduring
occurs it fits the data
broader
well without leaving unexplained
Asian economic shifts. structures in the returns or volatility.

Figure 7. Time-varying correlation plot between India and other global indices.
Figure 7. Time-varying correlation plot between India and other global indices.
4.5. Wavelet Coherence
The time-varying
The correlations
wavelet coherence graphbetween
visuallyIndia and
depicts theother global markets
time-varying (Asiabetween
correlation Pacific,
USA,
twoEurope, UK,data
time series Hong Kong,
across and Japan)
different estimated
frequencies, using how
showing the DCC-GARCH model
their relationship pre-
changes
sented in Figure 7, reveal significant insights into the dynamic interconnectedness of
over time. The wavelet coherence graph is superior for analysing time-varying relationships In-
dia’s financial
between twomarket. The correlations
time series with and
across both time Asiafrequency
Pacific and Hong Kong
domains. aretraditional
Unlike relatively
low, typically ranging from 0.15 to 0.35, indicating modest but fluctuating linkages driven
by regional economic events. The correlation with the USA is similarly low, suggesting
distinct economic influences. However, certain global financial events cause brief in-
creases in co-movement. In contrast, correlations with Europe and the UK are generally
J. Risk Financial Manag. 2025, 18, 18 19 of 24

correlation measures, it reveals how the strength and nature of the relationship evolve over
time at different frequencies, making it particularly effective for identifying non-stationary
or cyclical patterns. By identifying periods of high coherence between different markets,
investors and portfolio managers can recognise when diversification benefits diminish,
prompting a shift towards less correlated assets to mitigate risk. Considering the wavelet
coherence graph presenting strong long-term synchronisation between market A and B
during a particular period, it may be suggested to reduce exposure to market B assets by
increasing investments in regions or asset classes exhibiting lower coherence with market
A. Conversely, during periods of low or fragmented coherence, the investor may diversify
across multiple markets to exploit independent growth trajectories.
The X-axis in the graph represents time, and the Y-axis shows frequency, with short-
term interactions at the bottom and long-term at the top. Colour-coded regions illustrate the
coherence strength (0 to 1), where red or yellow areas indicate high coherence, indicating
strong correlation, and blue signifies low coherence. Arrows in the graph provide additional
insights into the phase relationship. Rightward arrows show the series are in-phase,
leftward indicate out-of-phase, while upward and downward arrows suggest one series
leads the other. The cone of influence outlines the area where interpretations are most
reliable, focusing attention within its bounds. The wavelet coherence graph helps identify
periods of high or low correlation and any lead–lag relationships, revealing dynamic
connections between two time series. Figure 8 shows the wavelet coherence between
the Indian stock market and the other global indices, shedding light on the strength and
dynamics of their interdependencies across different periods and frequencies.
Generally, there are noticeable periods of high coherence (marked in red) between
India and other markets, particularly in the medium- (16–64) to long-term (64–256) periods,
suggesting that external shocks have a significant and sustained impact on the Indian
market. This is evident, especially during 2022 and 2023, where high coherence regions
frequently appear across these indices, indicating that global market trends considerably
influenced the Indian market in the aftermath of the COVID-19 pandemic. For instance,
the coherence between India and the Global, Emerging Markets, and USA indices shows
robust synchronisation, reflecting the effect of heightened economic interconnectivity
and the global response to market disruptions caused by the pandemic and subsequent
recovery phases.
Another notable observation is that the Indian market’s coherence with European, UK,
and Asia Pacific indices reveals a pattern of fluctuating correlation over time, with some
high-coherence areas appearing intermittently in short-term periods (4–16), particularly in
the latter part of 2023. This could suggest that regional-specific events, such as inflation
concerns, policy changes, and geopolitical tensions, also play a role in these correlations,
influencing investor behaviour and market responses. Additionally, the Indian market
shows varying responses to short-term shocks, as evidenced by the scattered low-coherence
(blue) regions. These results indicate that India’s stock market demonstrates a degree of
resilience but remains exposed to global volatility, especially during significant economic
events. This interconnectedness, highlighted by the wavelet coherence across multiple
regions, emphasises the need for investors and policymakers in India to account for both
global and regional market conditions in their decision-making processes.
J. Risk Financial Manag. 2025, 18, x FOR PEER REVIEW 21 of 26
J. Risk Financial Manag. 2025, 18, 18 20 of 24

Figure 8. Wavelet coherence between India and other global indices.

Figure 8. Wavelet coherence between India and other global indices.
5. Implications
5. Implications
The implications of this study are far-reaching for investors, policymakers, and market
The implications
regulators, of this
offering crucial study into
insights are far-reaching
the dynamicsfor investors,
of global policymakers,
financial and mar-
market intercon-
ket regulators,
nectedness. Theoffering
results crucial
indicateinsights
that the into thestock
Indian dynamics
marketofexhibits
global financial market inter-
a high sensitivity to
connectedness.
shocks from majorTheinternational
results indicate that particularly
indices, the Indian stock
during market
periods exhibits a high turmoil
of economic sensitivity
tosuch as the
shocks post-pandemic
from [Link],
major international This information
particularlyis valuable for investors
during periods seekingtur-
of economic
moil such as the post-pandemic recovery. This information is valuable for investorskey
to optimise portfolio strategies by accounting for the volatility spillover effects from seek-
global markets like the U.S., Europe, and Asia, thereby improving risk management
ing to optimise portfolio strategies by accounting for the volatility spillover effects from and
enhancing
key returns. Specifically,
global markets like the U.S.,forEurope,
the portfolio managers,
and Asia, therebyit isimproving
necessary to identify
risk and
management
categorise
and rising
enhancing correlations,
returns. increased
Specifically, forvolatility persistence,
the portfolio managers, or periods of high wavelet
it is necessary to identify
coherence for better risk mitigation strategies. During periods of heightened market inter-
and categorise rising correlations, increased volatility persistence, or periods of high
connectedness, they may reduce exposure to highly correlated assets or diversify into less
wavelet coherence for better risk mitigation strategies. During periods of heightened mar-
volatile regions to safeguard returns. This adaptive strategy, guided by the wavelet-based
ket interconnectedness, they may reduce exposure to highly correlated assets or diversify
insights, allows decision-makers to dynamically rebalance portfolios, optimise returns,
into less volatile regions to safeguard returns. This adaptive strategy, guided by the wave-
let-based insights, allows decision-makers to dynamically rebalance portfolios, optimise
J. Risk Financial Manag. 2025, 18, 18 21 of 24

and strengthen resilience against market shocks by aligning asset allocation with evolving
market interdependencies.
For policymakers, the findings highlight the need for proactive measures to bolster
market resilience against external shocks, such as creating stronger financial infrastructure,
improving regulatory frameworks, and fostering greater economic integration. Addition-
ally, we suggest implication of policies fostering regional cooperation and information-
sharing among emerging economies can help mitigate contagion risks by addressing
cross-border volatility spillovers. Establishing capital buffer requirements that fluctuate
based on wavelet-identified periods of heightened coherence with global markets could
pre-empt market disruptions. Moreover, promoting financial literacy and encouraging
institutional investors to diversify into asset classes less sensitive to global shocks can
reduce overall market fragility. Moreover, the study underscores the importance of dy-
namic, real-time monitoring of market correlations and volatility, enabling timely policy
interventions and more informed decision-making by investors and regulators. Identify-
ing time-varying relationships between markets also stresses the necessity for adaptive
strategies that respond to market fluctuations across different frequencies, ensuring that the
Indian market remains resilient and competitive in a highly interconnected global economy.

6. Conclusions
This study comprehensively analyses the interconnectedness between the Indian
stock market (NSE) and several key global financial indices, using advanced econometric
techniques such as the Diebold–Yilmaz spillover index, DCC-GARCH model, and wavelet
coherence analysis. The findings reveal significant spillover effects, especially from markets
in the U.S., Europe, and Asia, indicating that global events have a lasting impact on the
Indian market. The results highlight the need for enhanced risk management strategies
and adaptive policy measures, as the Indian market is highly responsive to external shocks,
particularly during economic uncertainty. The research also demonstrates the effectiveness
of time-varying methods in capturing the dynamic nature of market interdependencies,
offering valuable insights for investors, regulators, and policymakers in navigating the
complexities of a globally interconnected financial landscape.

7. Limitation and Scope

This study primarily focuses on the volatility spillovers and interdependencies be-
tween financial indices, offering critical insights into market dynamics. However, it does
not explicitly account for broader macroeconomic variables such as fiscal policies, trade
dynamics, monetary interventions, or political stability, which can significantly shape mar-
ket behaviour. While the use of broad market indices is informative, it may mask sectoral
and regional variations that could reveal more focussed patterns of volatility transmission.
This generalisation limits the ability to draw conclusions about the behaviour of specific
industries or geographic segments within the market. Future research can address these
limitations by integrating sector-specific indices, macroeconomic indicators (e.g., inflation
rates, interest rates, and government debt levels), and geopolitical risks to develop a more
comprehensive understanding of market interdependencies. Expanding the dataset to
include indices from economic blocs such as BRICS+, G7, and G20 could yield insights into
cross-regional volatility spillovers and diversification opportunities. Additionally, employ-
ing alternative econometric models like BEKK-GARCH, TVP-VAR, or machine learning
techniques can enhance the accuracy and robustness of the analysis of time-varying cor-
relations. A more focused exploration of causal relationships between markets during
critical economic events, such as financial crises, geopolitical conflicts, and pandemics,
may uncover underlying drivers of market resilience or fragility. Future studies could also
J. Risk Financial Manag. 2025, 18, 18 22 of 24

investigate the role of emerging markets in mitigating global risks, shedding light on their
evolving influence in fostering financial stability and reducing systemic vulnerabilities
across interconnected economies.

Author Contributions: Conceptualisation, N.M. and A.K.P.; methodology, N.M., A.K.P., and S.K.C.;
software, N.M.; validation, N.M., M.U., and P.B.; data curation, N.M., S.K.C., and M.U.; formal
analysis, N.M., A.K.P., M.U., and P.K.; resources, A.K.P., S.K.C., M.U., P.B., and P.K.; writing—original
draft preparation, N.M.; writing—review and editing, A.K.P., S.K.C., M.U., P.B., and P.K.; supervision,
A.K.P., S.K.C., and M.U.; project administration, A.K.P. All authors have read and agreed to the
published version of the manuscript.

Funding: This research received no external funding.

Institutional Review Board Statement: Not applicable.

Informed Consent Statement: Not applicable.

Data Availability Statement: Data used in this study are publicly available and can be easily
downloaded from Blumberg or Yahoo Finance.

Conflicts of Interest: The authors declare no conflicts of interest.

References
Adrian, T. (2020). Global financial stability report: Markets in the time of COVID-19. Available online: [Link]
Publications/GFSR/Issues/2020/04/14/global-financial-stability-report-april-2020#Chapter2%0A[Link]
Publications/GFSR/Issues/2020/04/14/global-financial-stability-report-april-2020 (accessed on 23 June 2024).
Aggarwal, K., & Jha, M. K. (2023). Day-of-the-week effect and volatility in stock returns: Evidence from the Indian stock market.
Managerial Finance, 49(9), 1438–1452. [CrossRef]
Arfaoui, N., & Yousaf, I. (2022). Impact of COVID-19 on volatility spillovers across international markets: Evidence from var asymmetric
bekk garch model. Annals of Financial Economics, 17(1), 2250004. [CrossRef]
Armah, M., Amewu, G., & Bossman, A. (2022). Time-frequency analysis of financial stress and global commodities prices: Insights
from wavelet-based approaches. Cogent Economics and Finance, 10(1), 2114161. [CrossRef]
Baruník, J., & Křehlík, T. (2018). Measuring the frequency dynamics of financial connectedness and systemic risk. Journal of Financial
Econometrics, 16(2), 271–296. [CrossRef]
Bhowmik, R., & Wang, S. (2020). Stock market volatility and return analysis: A systematic literature review. Entropy, 22(5), 522.
[CrossRef]
Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307–327. [CrossRef]
Bonga-Bonga, L., & Phume, M. P. (2022). Return and volatility spillovers between South African and Nigerian equity markets. African
Journal of Economic and Management Studies, 13(2), 205–218. [CrossRef]
Booth, G. G., Martikainen, T., & Tse, Y. (1997). Price and volatility spillovers in Scandinavian stock markets. Journal of Banking and
Finance, 21(6), 811–823. [CrossRef]
Chaudhary, R., Bakhshi, P., & Gupta, H. (2020). Volatility in international stock markets: An empirical study during COVID-19. Journal
of Risk and Financial Management, 13(9), 208. [CrossRef]
Choptiany, J. M. H., Nicoletti, C. K., Van Beck, L., Seekman, V., Henao, L., Buchholz, N., Parker, T., Kothari, R., Ullah, M. H., & O’hara,
C. (2021). The market systems resilience index: A multi-dimensional tool for development practitioners to assess resilience at
multiple levels. Sustainability, 13(20), 11210. [CrossRef]
Dhingra, B., Batra, S., Aggarwal, V., Yadav, M., & Kumar, P. (2024). Stock market volatility: A systematic review. Journal of Modelling in
Management, 19(3), 925–952. [CrossRef]
Diebold, F. X., & Yilmaz, K. (2009). Measuring financial asset return and volatility spillovers, with application to global equity markets.
Economic Journal, 119(534), 158–171. [CrossRef]
Diebold, F. X., & Yilmaz, K. (2023). On the past, present, and future of the Diebold–Yilmaz approach to dynamic network connectedness.
Journal of Econometrics, 234, 115–120. [CrossRef]
Engle, R. (2002). Dynamic conditional correlation: A simple class of multivariate generalized autoregressive conditional heteroskedas-
ticity models. Journal of Business and Economic Statistics, 20(3), 339–350. [CrossRef]
Erdoğan, S., Gedikli, A., & Çevik, E. İ. (2020). Volatility spillover effects between Islamic stock markets and exchange rates: Evidence
from three emerging countries. Borsa Istanbul Review, 20(4), 322–333. [CrossRef]
J. Risk Financial Manag. 2025, 18, 18 23 of 24

Giudici, P., Sarlin, P., & Spelta, A. (2020). The interconnected nature of financial systems: Direct and common exposures. Journal of
Banking and Finance, 112, 105149. [CrossRef]
Grinsted, A., Moore, J. C., & Jevrejeva, S. (2004). Application of the cross wavelet transform and wavelet coherence to geophysical time
series. Nonlinear Processes in Geophysics, 11(5/6), 561–566. [CrossRef]
Hafner, C. M., Herwartz, H., & Maxand, S. (2022). Identification of structural multivariate GARCH models. Journal of Econometrics,
227(1), 212–227. [CrossRef]
Hasan, M. B., Rashid, M. M., Shafiullah, M., & Sarker, T. (2022). How resilient are Islamic financial markets during the COVID-19
pandemic? Pacific Basin Finance Journal, 74, 101817. [CrossRef]
He, L. T. (2001). Time variation paths of international transmission of stock volatility—US vs. Hong Kong and South Korea. Global
Finance Journal, 12(1), 79–93. [CrossRef]
Indrawati, S. M., Diop, N., Ikhsan, M., & Kacaribu, F. (2020). Enhancing resilience to turbulent global financial markets: An Indonesian
experience. Economics and Finance in Indonesia, 66(1), 47. [CrossRef]
Jebabli, I., Kouaissah, N., & Arouri, M. (2022). Volatility spillovers between stock and energy markets during crises: A comparative
assessment between the 2008 global financial crisis and the COVID-19 pandemic crisis. Finance Research Letters, 46(1), 102363.
[CrossRef]
Jin, X., & An, X. (2016). Global financial crisis and emerging stock market contagion: A volatility impulse response function approach.
Research in International Business and Finance, 36(1), 179–195. [CrossRef]
Karolyi, G. A. (1995). A multivariate GARCH model of international transmissions of stock returns and volatility: The case of the
United States and Canada. Journal of Business and Economic Statistics, 13(1), 11–25. [CrossRef]
Khan, I. (2024). An analysis of stock markets integration and dynamics of volatility spillover in emerging nations. Journal of Economic
and Administrative Sciences. ahead of print. [CrossRef]
Kishor, N., & Singh, R. P. (2014). Stock return volatility effect: Study of BRICS. Transnational Corporations Review, 6(4), 406–418.
[CrossRef]
Li, W. (2021). COVID-19 and asymmetric volatility spillovers across global stock markets. North American Journal of Economics and
Finance, 58(1), 101474. [CrossRef]
Liu, D., Sun, W., Xu, L., & Zhang, X. (2023). Time-frequency relationship between economic policy uncertainty and financial cycle in
China: Evidence from wavelet analysis. Pacific Basin Finance Journal, 77, 101915. [CrossRef]
Eun, C. S., & Resnick, B. G. (1984). Estimating the correlation structure of international share prices. The Journal of Finance, 39(5),
1311–1324. [CrossRef]
Liu, H., Saleem, M. M., Al-Faryan, M. A. S., Khan, I., & Zafar, M. W. (2022). Impact of governance and globalization on natural resources
volatility: The role of financial development in the Middle East North Africa countries. Resources Policy, 78, 102881. [CrossRef]
Liu, Y., Wei, Y., Wang, Q., & Liu, Y. (2022). International stock market risk contagion during the COVID-19 pandemic. Finance Research
Letters, 45, 102145. [CrossRef]
Maharana, N., Panigrahi, A. K., & Chaudhury, S. K. (2024). Volatility persistence and spillover effects of Indian market in the global
economy: A pre-and post-pandemic analysis using VAR-BEKK-GARCH model. Journal of Risk and Financial Management,
17(7), 294. [CrossRef]
Malik, K., Sharma, S., & Kaur, M. (2022). Measuring contagion during COVID-19 through volatility spillovers of BRIC countries using
diagonal BEKK approach. Journal of Economic Studies, 49(2), 227–242. [CrossRef]
Mishra, A. K., Agrawal, S., & Patwa, J. A. (2022). Return and volatility spillover between India and leading Asian and global equity
markets: An empirical analysis. Journal of Economics, Finance and Administrative Science, 27(54), 294–312. [CrossRef]
Mohanasundaram, T., Rizwana, M., Sathyanarayana, S., & Singh, P. (2024). Structural change, information asymmetry and volatility in
Indian stock market: Evidence from pre-and-post-COVID-19 outbreak. Afro-Asian Journal of Finance and Accounting, 14(3), 412–431.
[CrossRef]
Mukherjee, K. nath, & Mishra, R. K. (2010). Stock market integration and volatility spillover: India and its major Asian counterparts.
Research in International Business and Finance, 24(2), 235–251. [CrossRef]
Raddant, M., & Kenett, D. Y. (2021). Interconnectedness in the global financial market. Journal of International Money and Finance, 110,
102280. [CrossRef]
Ray, I. (2023). Economic resilience during COVID-19 in South-Asia. Splint International Journal of Professionals, 10(1), 62–70. [CrossRef]
Rhif, M., Ben Abbes, A., Farah, I. R., Martínez, B., & Sang, Y. (2019). Wavelet transform application for/in non-stationary time-series
analysis: A review. Applied Sciences, 9(7), 1345. [CrossRef]
Sarwar, S., Tiwari, A. K., & Tingqiu, C. (2020). Analyzing volatility spillovers between oil market and Asian stock markets. Resources
Policy, 66(1), 101608. [CrossRef]
Shahzad, S. J. H., Naeem, M. A., Peng, Z., & Bouri, E. (2021). Asymmetric volatility spillover among Chinese sectors during COVID-19.
International Review of Financial Analysis, 75, 101754. [CrossRef] [PubMed]
J. Risk Financial Manag. 2025, 18, 18 24 of 24

Sifuzzaman, M., Islam, M. R., & Ali, M. Z. (2009). Application of wavelet transform and its advantages compared to fourier transform.
Journal of Physical Sciences, 13, 121–134.
Singhal, S., & Ghosh, S. (2016). Returns and volatility linkages between international crude oil price, metal and other stock indices in
India: Evidence from VAR-DCC-GARCH models. Resources Policy, 50, 276–288. [CrossRef]
Tamhane, T. (2020). India’s post—COVID-19 economic recovery: The M & A imperative. Available online: [Link]
media/McKinsey/Business%20Functions/M%20and%20A/Our%20insights/Indias%20post%20COVID%2019%20economic%
20recovery%20The%20M%20and%20A%20imperative/Indias-post-COVID-19-economic-recovery-The-M-and-A-imperative
-[Link]?form=MG0AV3 (accessed on 18 August 2024).
Thangamuthu, M., Maheshwari, S., & Naik, D. R. (2022). Volatility spillover effects during pre-and-post COVID-19 outbreak on Indian
market from the USA, China, Japan, Germany, and Australia. Journal of Risk and Financial Management, 15(9), 378. [CrossRef]
Tiwary, D., Pandey, M., & Agarwal, P. (2022). Remodelling post-COVID 19 resilience of emerging market microenterprises. Journal of
Information and Optimization Sciences, 43(6), 1475–1486. [CrossRef]
Torrence, C., & Compo, G. P. (1998). A practical guide to wavelet analysis. Bulletin of the American Meteorological Society, 79(1), 61–78.
[CrossRef]
Tripathy, N. (2022). Long memory and volatility persistence across BRICS stock markets. Research in International Business and Finance,
63, 101782. [CrossRef]
Tsay, R. S. (2010). Analysis of financial time series. John Wiley & Sons. [CrossRef]
Wang, J. (2021). Application of wavelet transform image processing technology in financial stock analysis. Journal of Intelligent and
Fuzzy Systems, 40(2), 2017–2027. [CrossRef]
Yadav, N., Singh, A. B., & Tandon, P. (2023). Volatility spillover effects between Indian stock market and global stock markets: A
DCC-GARCH model. FIIB Business Review, 23197145221141186. [CrossRef]
Yarovaya, L., Brzeszczyński, J., & Lau, C. K. M. (2016). Intra-and inter-regional return and volatility spillovers across emerging and
developed markets: Evidence from stock indices and stock index futures. International Review of Financial Analysis, 43(1), 96–114.
[CrossRef]
Ye, Z., Hu, C., He, L., Ouyang, G., & Wen, F. (2020). The dynamic time-frequency relationship between international oil prices and
investor sentiment in china: A wavelet coherence analysis. Energy Journal, 41(5), 251–270. [CrossRef]
Zhong, Y., & Liu, J. (2021). Correlations and volatility spillovers between China and Southeast Asian stock markets. The Quarterly
Review of Economics and Finance, 81, 57–69. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.