Time-varying Parameter Vector Autoregression Research Articles

Understanding the spillover effects of ethanol production and energy prices on African food markets: A time-varying approach

Amidst recent global uncertainty caused by events such as the COVID-19 pandemic and wars, African countries are finding it even more challenging than before to achieve food security. This study utilizes the time-varying parameter vector autoregression (TVP-VAR)–based extended joint connectedness model to analyze the impact of external factors, such as U.S. ethanol production, grain speculation, international energy prices, international food prices, and international corn prices, on domestic food prices in four African countries (Ethiopia, Ghana, South Africa, and Tanzania). The key results of the study can be summarized as follows: (1) The production of ethanol in the United States has an influence on the food prices in all four sample countries, with the extent of this impact differing from one nation to another. Notably, the effects of ethanol production were particularly pronounced until the years 2011–2012. (2) In Ethiopia and Tanzania, the domestic food market shows only a slight impact from speculative activities, whereas in Ghana and South Africa, these activities have a notable effect. (3) International energy prices play a significant role in shaping the domestic food prices across all four countries.

Do macroprudential policies reduce risk spillovers between energy markets?: Evidence from time-frequency domain and mixed-frequency methods

Preventing volatility spillovers between energy markets is essential for maintaining financial stability. Macroprudential policies play an invaluable tool in financial risk monitoring and help to reduce the incidence of systemic risk. However, the effectiveness of macroprudential policies on risk spreads in the energy system is still unclear. This article applies the TVP-VAR (time-varying parameter vector autoregression) spillover methods to capture the risk connectedness between energy markets in the time and frequency domains, and constructs an asymmetric GARCH-MIDAS-MPP model to investigate the influence of macroprudential policies on volatility overflows of the energy system. The results suggest that there are strong risk links between global energy markets and long-term risk resonances play a dominant role. Time-varying risk overflows occur throughout the energy sector, and market turbulence amplifies these risk communications. Whether on a time or frequency horizon, the oil market represents the largest emitter of fluctuation transmissions, while the fuel oil market stands out as the biggest recipient of risk diffusion. We do not observe that macroprudential policies can significantly reduce the average and long-run risk premiums of the energy system. Conversely, our results reveal that macroprudential policies intensify short- and medium-term risk spreads between global energy markets. This paper provides some insight into energy market risk contagion, which is conducive to the improvement of macroprudential policies for energy market risk management.

Volatility spillovers and carbon price in the Nordic wholesale electricity markets

This paper investigates price volatility and spillovers in the Nordic electricity wholesale markets. We use the Time-Varying Parameter Vector Autoregressive (TVP-VAR), Rolling Window-based VAR (RW-VAR), and high dimensional VAR with common factors (VAR-CF) methods and analyze the integration dynamics among these markets and impact of carbon prices on volatility spillovers. We use 107,352 hourly price data from January 2010 to March 2022. The novelty of this research is four-fold. First, we adopt a connectedness approach to explore volatility interactions among the four Nordic markets, contributing to the scarce literature on volatility in this market. Second, we segment the Norwegian market into southern and northern regions, revealing differences in volatility spillover patterns. Third, we investigate the effect of carbon prices on volatility spillovers and market dynamics. Last, we show significant contribution of covariances to interdependence among markets. We find significant connectedness between the Nordic markets, with an average Total Connectedness Index of between 50% (with a system of variance) and 90% (with a system of both variance and covariance). Sweden is the sole net volatility spillover transmitter, while Denmark experiences the largest shocks from the system. We further find that carbon prices exert a 5% significant impact on the volatility spillover index.

Dynamic connectedness among market volatilities: a perspective of COVID-19 and Russia-Ukraine conflict

Purpose This paper aims to investigate the dynamic volatility connectedness among 13 G20 countries by using the volatility indices. Design/methodology/approach The connectedness approach based on the time-varying parameter vector autoregression model has been used to investigate the linkage. The period of study is from 1 January 2014 to 20 April 2023. Findings This analysis revealed that volatility connectedness among the countries during COVID-19 and Russia–Ukraine conflict had increased significantly. Furthermore, analysis has indicated that investors had not anticipated the World Health Organization announcement of COVID-19 as a global pandemic. Contrarily, investors had anticipated the Russian invasion of Ukraine, evident in a significant rise in volatility before and after the invasion. In addition, the transmission of volatility is from developed to developing countries. Developed countries are NET volatility transmitters, whereas developing countries are NET volatility receivers. Finally, the ordinary least square regression result suggests that the volatility connectedness index is informative of stock market dynamics. Originality/value The connectedness approach has been widely used to estimate the dynamic connectedness among market indices, cryptocurrencies, sectoral indices, enegy commodities and metals. To the best of the authors’ knowledge, none of the previous studies have directly used the volatility indices to measure the volatility connectedness. Hence, this study is the first of its kind that has used volatility indices to measure the volatility connectedness among the countries.

Dynamic connectedness, portfolio performance, and hedging effectiveness of the hydrogen economy, renewable energy, equity, and commodity markets: Insights from the COVID-19 pandemic and the Russia-Ukraine war

This study employs a Time-Varying Parameter Vector Auto Regressive (TVP-VAR) connectedness approach to investigate the dynamic interconnections, portfolio performance, and hedging effectiveness across hydrogen economy, renewable energy markets, equities, and energy commodities amidst the backdrop of the COVID-19 pandemic and the Russia-Ukraine conflict. Our findings reveal a consistent level of average connectedness during both black swan events, with dynamic connectedness reaching its peak during the COVID-19 crisis. While some assets (hydrogen economy index, renewable, solar and clean technology index) persistently function as net transmitters, the others (geothermal index, crude oil, natural gas, biofuel, and gold) consistently act as net receivers. We also find that the role of equity indices (wind energy, fuel cell, FTSE_100, and S&P 500) as net transmitters or receivers changes over time. The network plot results show that the hydrogen economy typically functions as shock transmitters for equity market indices and commodities. Portfolio analysis underscores the superior risk-adjusted performance of the minimum variance (connectedness) portfolio during the COVID-19 crisis in comparison to the Russia-Ukraine conflict. Furthermore, our examination of effective hedge and portfolio strategies demonstrates that managed collateralized portfolio weights of hydrogen economy and renewable energy assets (equities) in the minimum variance portfolio increase (decrease) from 7% to 12% (53%–41%) during the COVID-19 crisis, and subsequently decline (rise) further to 6% (53%) amidst the Russia-Ukraine conflict. These findings suggest a preference for hydrogen economy and renewable energy assets as hedging instruments in health-related financial crises over crises precipitated by military conflicts.

Carbon Market Efficiency and Economic Policy Uncertainty: Evidence from a TVP-VAR Model

This paper examines the dynamic linkages among economic policy uncertainty (EPU), the green bond market, the carbon market, and the macroeconomy using the time-varying parameter vector autoregressive (TVP-VAR) model with monthly data spanning from January 2016 to December 2021. Additionally, it assesses the robustness and accuracy of the empirical results through the Bayesian vector autoregressive (BVAR) model. The findings indicate that EPU negatively affects the green bond market in the short term but has a positive impact in the medium and long term. Conversely, EPU has a positive impact on the carbon market in the short term but a negative impact in the medium and long term. Furthermore, the green bond market negatively influences the carbon market in both the short and medium to long term. These results suggest that emerging markets, such as the green bond and carbon markets, are influenced by EPU. The adverse impact of the green bond market on the carbon market, however, contributes to expediting China’s attainment of its low-carbon objectives. Appropriate economic policies can play a vital role in accelerating the transition to a low-carbon economy. The study also reveals that the US-China trade war has expedited the development of green capital markets in China, despite its impact on the green economic transition in the country. These findings provide insights for the government and investors to formulate suitable strategies for risk mitigation.

Can carbon emission trading markets reduce the risks in traditional energy markets?

As the largest energy consumer in the world, China maintains a tightly interconnected energy market in the international arena. Therefore, it is necessary to explore the interdependence and spillover effects between the carbon emissions trading markets, traditional energy markets in China, and International markets. We explore changes in risk in the Chinese energy market with the introduction of the Chinese carbon market by employing the Vine Copula function to construct a vine structure and analyse the complex interdependence among markets. Moreover, we utilise the Time-Varying Parameter Vector Auto Regression and Diebold-Yilmaz Spillover Index (TVP-VAR-DY) method to examine the dynamic spillover effects of risk across various markets. Empirical analyses reveal a strong interdependence between the carbon emissions trading market and the traditional energy market. The Brent crude oil market occupies a central position within the system and significantly influences other markets. The carbon emissions trading market on the periphery has little impact on the system. Additionally, significant volatility spillover effects—observed between the carbon emissions trading market and traditional energy market systems—are closely correlated with economic conditions and extreme events, demonstrating time-varying characteristics. Furthermore, the Chinese carbon emissions trading market effectively reduces risk spillover in traditional Chinese energy markets from international markets during periods of risk contagion, particularly during times of high volatility, which can offer policymakers a novel path for risk management and provide investors with new avenues for investment hedging strategies.

Volatility Connectedness of MOVE Index and Bond Returns

Research Originality: To the best of our knowledge, this is the first study which measures the impact of the MOVE index on bond yield volatility by comparing its effect on both short-term and long-term. The paper contributes to the existing literature by providing a better understanding of the relationship between maturity and volatility spillover. Research Objectives: This study examines the dynamic volatility connectedness between 2 and 10-year bond yields and the MOVE Index. Furthermore, it is aimed at detecting the transmitter of volatility among variables. Research Methods: Using a data set from 2010 to 2022, the study utilizes a Time-Varying Parameter Vector Autoregression (TVP-VAR) model to analyse the dynamics and relationship between bond yields and the MOVE Index. Empirical Results: The study finds a significant volatility spillover between the MOVE Index and Türkiye's bond yields. Notably, the linkage between the MOVE Index and the 10-year bond rates is stronger than with the 2-year rates. Additionally, the MOVE Index emerges as the primary transmitter of volatility, impacting both bond yields. Implications: This study sheds light on the complexity and dynamics of volatility spread in Türkiye's bond market, providing essential insights for forecasting bond yields and shaping financial policies.JEL Classification: G17, C22, G12How to Cite:Baykut, E., Gökgöz, H. (2024). Volatility Connectedness of MOVE Index and Bond Returns. Etikonomi, 23(1), 27 – 46. https://doi.org/10.15408/etk.v23i1.36131.

Extreme connectedness between cryptocurrencies and non-fungible tokens: portfolio implications

We analyze the connectedness between major cryptocurrencies and nonfungible tokens (NFTs) for different quantiles employing a time-varying parameter vector autoregression approach. We find that lower and upper quantile spillovers are higher than those at the median, meaning that connectedness augments at extremes. For normal, bearish, and bullish markets, Bitcoin Cash, Bitcoin, Ethereum, and Litecoin consistently remain net transmitters, while NFTs receive innovations. However, spillover topology at both extremes becomes simpler—from cryptocurrencies to NFTs. We find no markets useful for mitigating BTC risks, whereas BTC is capable of reducing the risk of other digital assets, which is a valuable insight for market players and investors.

Green Shocks: The Spillover Effects of Green Equity Indices on Global Market Dynamics

This study investigates the impact of green equity indices on global market dynamics using a time-varying parameter vector autoregression (TVP-VAR) model. We uncover a significant shift in the role of the global market, transitioning from a shock transmitter to a shock receiver, as the influence of green finance grows. By directly comparing green equity indices with their corresponding global parent indices, we adopt a global perspective that transcends the limitations of studies focusing on specific regions, such as the USA, China, or Europe. This novel approach minimizes the potential biases in the transmission channels within regional markets, enabling a more comprehensive understanding of the relationship between green finance and global market dynamics. Moreover, by focusing on equity indices we ensure a consistent comparison of financial instruments, avoiding the complexities that arise when comparing different asset classes such as green bonds and conventional equities. For global investors, our results highlight the importance of dynamic and flexible hedging strategies that adapt to the distinct characteristics of green assets and their growing influence on the global market. Risk managers should incorporate these time-varying spillover effects into their models to better assess and mitigate potential risks. Policymakers should consider the growing influence of green finance on the broader market when formulating regulations and incentives to support sustainable investing, as our findings underscore the increasing importance of this sector in shaping market dynamics.

Towards sustainable development: Exploring the spillover effects of green technology innovation on energy markets and economic cycles

With the proposal of sustainable development goals, the world has placed increasing emphasis on energy transition and green, low-carbon initiatives, leading to the emergence of green technology. This article explores the spillover effects among green technology innovation (GTI), oil prices (OP), clean energy (CE), sustainable development (SD), and economic cycles (EC) with the time-varying parameter vector autoregression (TVP-VAR) connectedness method. The empirical results demonstrate that, in static analysis, the short-term connectedness is significantly stronger than that in the long term. SD serves as the main transmitter, while EC acts as the primary receiver. Furthermore, dynamic analysis suggests that spillover effects fluctuate with time and frequency. Finally, the net direction and net pairwise connectedness reveal that GTI is favorable for mitigating OP shocks and accelerating EC in the long term, while it is driven by CE and SD in the short term. The contribution of this paper lies in its incorporation of GTI, energy markets, economic cycles, and SD into a unified framework, and its detailed analysis of the channels of influence. Also, based on a time-frequency domain perspective, the paper dynamically examines the different performances of specific markets in the short or long term. Finally, the paper proposes some policy recommendations, including the strengthening of green technology innovation and the acceleration of energy transition.

COVID-19, the Russia–Ukraine war and the connectedness between the U.S. and Chinese agricultural futures markets

This study focuses on how recent global crises such as the COVID-19 pandemic and the Russia–Ukraine war have affected the relationship between the U.S. and Chinese agricultural futures markets. By applying wavelet coherence analysis (WCA) and time-varying parameter vector autoregression (TVP-VAR), we obtain the following findings. First, both events have changed the correlation and lead–lag comovement between U.S. and Chinese soybean and corn futures returns but have little impact on the comovement between the two cotton futures returns. Second, U.S. agricultural markets transmit more volatility risk to Chinese markets than the risk spillover from the reverse direction. Third, the risk spillover enhancement effect from the war is stronger than that from the pandemic, which is obvious in both the soybean and corn futures markets but not in the cotton market. Our paper has implications for policy makers seeking to stabilize agricultural commodity prices during global crisis episodes and for designing strategies for cross-market hedging of spillover risks among commodity markets for international investors.

The dynamic connectedness between collateralized loan obligations and major asset classes: a TVP-VAR approach and portfolio hedging strategies for investors

AbstractMotivated by the increasing demand for alternative assets that can contribute to reducing portfolio risk, this paper examines the volatility spillovers between collateralized loan obligations (CLOs) and various in-demand investment instruments, including equities, bonds, crude oil, commodities, gold, bitcoin, shipping and real estate. The applied methodology comprehends the time-varying parameter vector autoregressive (TVP-VAR) modification of the classical spillover approach, for the period from January 1, 2012, to August 31, 2023. The empirical findings show moderate levels of dynamic connectedness; albeit several external shocks strengthened the interconnection among the assets. Moreover, we compare the ability of CLOs for hedging, during the overall sample period and multiple subperiods, by estimating hedge ratios and optimal portfolio weights, in order to inform investors about feasible portfolio adjustments. Our results indicate that CLOs constitute an effective hedging tool, irrespective of the period covered, as the short position in their volatility provides high hedging effectiveness for investors holding long positions in the volatility of all the remaining assets.

The Risk Spillover Effects and Network Connectedness Between Real Estate and Other Sectors in China

Using a high-dimensional time-varying parameter vector autoregression framework, we propose a volatility spillover network to analyze risk contagion direction, path, and intensity under supply-demand relationships when important events break out in the real estate market. We characterize daily return volatility spillovers across firms from January 2010 to April 2022 and find a high correlation among these firms because the real linkage based on industrial chain structure strengthened. Meanwhile, the outbreak of essential events in the real estate market corresponds to several peak values of return volatility. The empirical results show that excessive correlation induces risk contagion across the network, and spillover effects are significant under extreme market conditions, manifesting as cross-industry contagion and intersectoral diffusion. The volatility spillover effects within real estate firms are higher than spillover effects across markets. In addition, the industrial chain structure better explains the mechanism of cross-industry risk contagion, firms located upstream of the real estate industry chain are risk receivers, and those located downstream are risk spillovers. Real estate firms mainly spread risks to financial institutions and firms that provide production goods. Our findings are of constructive significance to the related policies by regulatory authorities and provide multi-angle empirical evidence support for the risk supervision theory of “too connected to fail.”

Dynamic connectedness among the BRICS markets and the recent pandemic: an application of TVP-VAR approach

PurposeThis study analyses the impact of the Covid-19 on stock market performance of BRICS nations together. BRICS countries comprise almost 30% of the global GDP and around 50% of the world’s economic growth. As BRICS nations have gained the attraction as financial investment destinations, their financial markets have apparently been as potential opportunities for foreign portfolio investors. While there is extensive research on the impact of the Covid-19 pandemic on individual economies and global financial markets, this paper is among the first to systematically investigate the dynamic connectedness of these emerging economies during the pandemic using the Time-Varying Parameter Vector Autoregressions (TVP-VAR) approach.Design/methodology/approachWe categorise our data into two distinct periods: the pre-Covid period spanning from January 1, 2018, to March 10, 2020, and the Covid crisis period extending from March 11, 2020, to June 4, 2021. To achieve our research objectives, we employ the Time-Varying Parameter Vector Autoregressions (TVP-VAR) approach to assess dynamic connectedness.FindingsOur findings reveal that among the BRICS nations, Brazil and South Africa serve as net transmitters of shocks, while China and India act as net receivers of shocks during the Covid crisis. However, the total connectedness index (TCI) has exhibited a notable increase throughout this crisis period. This paper makes several notable contributions to the academic literature by offering a unique focus on BRICS economies during the Covid-19 pandemic, providing practical insights for stakeholders, emphasising the importance of risk management and investment strategy, exploring diversification implications and introducing advanced methodology for analysing interconnected financial markets.Research limitations/implicationsThe results have important implications for the investors, the hedge funds, portfolio managers and the policymakers in BRICS stock markets. The investors, investment houses, portfolio managers and policymakers can develop investment strategies and policies in the light of the findings of this study to cope up the future pandemic crisis.Originality/valueThis study is one of its kind that examines the dynamic connectedness of BRICS with recently developed TVP-VAR approach across pandemic crisis.

Stock-oil comovements through fear, uncertainty, and expectations: Evidence from conditional comoments

This paper investigates the role of sentiment as a potential driver of the novel stock-oil (represented by the S&P 500 and West Texas Intermediate futures) dynamics in the aftermath of the 2008 global financial crisis (GFC). We study the impact of both sentiment shocks and fluctuations, on the stock-oil time-varying conditional comoments, using the time-varying parameter vector autoregression (TVP-VAR), and the nonlinear autoregressive distributed lag (NARDL), respectively. The findings show that the increasing (asymmetric) effect of sentiments, accounts for the novel post-GFC stock-oil dynamics. As a result, a proactive regulatory framework is needed to shield oil futures against the ever-increasing speculation and financialization.

The Risk Transfer among Exchange Rates, Energy Commodities, and Agricultural Commodity Prices in SADC Countries

This paper investigates the risk transfer between exchange rates, energy commodities, and agricultural commodity prices in SADC nations from July 29, 2007, to December 18, 2022. The Time-varying parameter Vector Autoregression connectivity technique is specifically used. The total connectivity index for the specific network of energy commodities, currency rates, and agricultural commodities is 24.39%. The energy commodities index (crude oil and heating oil) and the ZAR were the largest shock transmitters, according to averaged dynamic connectedness. In contrast, two SADC currency markets (MWK and MZN), natural gas, and corn were net shock recipients. Furthermore, overall connection indices were shown to change dramatically with high sensitivity to crisis events, particularly the 2007/2008 crisis and the COVID-19 pandemic. As indicated by net directional connection, most energy commodities, as well as the Rand and the Pula, were persistent net transmitters over time. This is especially noteworthy given oil's direct impact on agricultural commodities. The findings of this paper are useful for policymakers who are attempting to maximize public benefit. Policymakers charged with developing policies for economically vulnerable segments of the population should use these findings to examine the potential impact of changes in energy prices on food and currency markets.

Time-varying Connectedness Between ESG Stocks and BRVM Traditional Stocks

Periods of crisis prompt investors to look out for means of making returns even in uncertain market conditions. Investors are using stocks selected on an environmental, social, and governance (ESG) basis to mitigate the unavoidable risks of investing in assets during these times of pandemic and war. In an integrated global financial system, we sought to explore the connectedness, if any, between the returns on the Bourse Régionale des Valeurs Mobilières (BRVM) and ESG-based stocks. Using a time-varying parameter vector autoregression (TVP-VAR) to analyze daily returns from 12 March 2013 to 4 April 2022, we find categorically that ESG-based stocks and BRVM stocks are connected, with ESG-based stocks dominating the network connectedness. Furthermore, using dynamic connectedness correlations from dynamic conditional correlation generalized autoregressive conditional heteroscedasticity (DCC-GARCH), we show that ESG stocks could be used as a safe haven or weak hedge for BRVM stocks in times of crisis. We test for the robustness of our findings using quantile causality. The causality test further shows that ESG-based stocks cause movements in BRVM stocks mostly at the lower quantiles—enhancing the findings of dominancy from the TVP-VAR estimates and offer diversification and safe haven benefits from the DCC-GARCH in extreme conditions. The implication of these findings for investors is that they could benefit from using ESG-based stocks in their portfolios, particularly in times of crisis. JEL Codes: G01, G11

Spillover effects from partisan conflict and trade & immigration policy uncertainty to US travel and leisure stocks: a time-frequency analysis

ABSTRACT This study uses the time-varying parameter vector autoregression (TVP-VAR) based connectedness approach to explore the effects of partisan conflict, trade policy uncertainty, and immigration policy uncertainty on the return and volatility of travel and leisure stocks in the US markets. The empirical results show that partisan conflict has the strongest spillover; the trade and immigration policy uncertainties are the spillover transmitters; travel and leisure stocks are the main receivers. In the time-domain, the spillover effect is time-varying, which increases significantly in times of crisis, especially during the COVID-19 and the Russia–Ukraine Conflict. In the frequency-domain, long-term spillover is more significant than short-term spillover. Compared with returns, volatility is more sensitive to uncertainties and has a much more complex spillover path. Among travel and leisure stocks, airline stocks are most vulnerable to uncertainty shocks, whereas gambling stocks are more rigid than other stocks. Our results have important implications for investment decisions, policy-making, and coping with risks arising from uncertainty.

Return and volatility spillovers between non-fungible tokens and conventional currencies: evidence from the TVP-VAR model

This study investigates the static and dynamic return and volatility spillovers between non-fungible tokens (NFTs) and conventional currencies using the time-varying parameter vector autoregressions approach. We reveal that the total connectedness between these markets is weak, implying that investors may increase the diversification benefits of their multicurrency portfolios by adding NFTs. We also find that NFTs are net transmitters of both return and volatility spillovers; however, in the case of return spillovers, the influence of NFTs on conventional currencies is more pronounced than that of volatility shock transmissions. The dynamic exercise reveals that the returns and volatility spillovers vary over time, largely increasing during the onset of the Covid-19 crisis, which deeply affected the relationship between NFTs and the conventional currencies markets. Our findings are useful for currency traders and NFT investors seeking to build effective cross-currency and cross-asset hedge strategies during systemic crises.