Time-varying Parameter Vector Autoregression Research Articles

The impact of the Russia-Ukraine conflict on the connectedness of financial markets

We investigate the impact of geopolitical risks caused by the Russian-Ukrainian conflict on Russia, European financial markets, and the global commodity markets. We measure the dynamic connectedness among them using time- and frequency-based time-varying parameter vector autoregression (TVP-VAR) approaches. The empirical findings indicate that (i) their relationship has changed due to the conflict; (ii) European equities and Russian bonds are the net transmitters of shocks; and (iii) the conflict affects returns and volatility connectedness among them in terms of short- and long-term frequencies, respectively.

International monetary policy and cryptocurrency markets: dynamic and spillover effects

Using daily data over the period August 5, 2013 – September 27, 2019, this study investigates the dynamic spillovers between international monetary policies across four major economies (i.e. Eurozone, Japan, UK and US) and three key cryptocurrencies (i.e. Bitcoin, Litecoin and Ripple). In doing so, we apply a Time-Varying Parameter Vector Auto-Regression (TVP-VAR) model, a dynamic connectedness approach and network analysis. The empirical results indicate that cryptocurrency returns and monetary policy spillovers were particularly large when shadow policy rates became negative, moderated during the Fed's ‘tapering process’, and sharpened again more recently as cryptocurrency buoyancy returned. Gross directional spillovers suggest that shadow policy rates have more ‘to give than to receive’, while those from and to cryptocurrency returns are naturally volatile. There is also strong interconnectedness between monetary policy in either the US or the Eurozone and the UK, and between Bitcoin and Litecoin. However, the spillovers across monetary policy and cryptocurrencies tend to be muted. Finally, spillovers were only slightly larger during the Fed's ‘unconventional’ policy compared to the ‘standard’ era, but their composition qualitatively changed over time.

Impact of COVID-19 on the connectedness across global hospitality stocks

This study investigated the connectedness of top ten hospitality stocks in the world and the impact of the COVID-19 pandemic on this connectedness. For this purpose, we employ the time-varying parameter vector autoregressions (TVP-VAR) to examine the return connectedness among the world’s top ten hospitality stocks. We further utilize the wavelet coherence measure to test the impact of COVID-related indexes on the connectedness across the hospitality stocks from January 1, 2020 to July 16, 2021. Our findings explore a strong connectedness among the hospitality stocks, although the total connectedness index is considerably affected by the first wave, the second wave, and the approval of COVID-19 vaccines. France and UK hospitality stocks appeared to be dominant and were the highest net transmitters of spillover shocks to other sample stocks. We document that the COVID-19 pandemic is the prime driver of the hospitality stocks’ connectedness during the sample period. Aside from the contribution to hospitality and finance literature, our conclusions and implications can also benefit parties such as hospitality firm managers, investors, portfolio managers, and policymakers.

On the dynamic return and volatility connectedness of cryptocurrency, crude oil, clean energy, and stock markets: a time-varying analysis.

The high energy consumption of cryptocurrency transactions has raised concerns about the environment and sustainability among green investors and regulatory authorities. The current study examines the connectedness among clean energy, Bitcoin, the stock market, and crude oil empirically. The time-varying parameter vector autoregression (TVP-VAR) is used to estimate the dynamics of connectedness in a daily dataset spanning the period November 11, 2013 to September 30, 2021. We find that the clean energy and traditional stock markets transmit shocks to Bitcoin and oil in terms of return, and they receive shocks in terms of volatility from Bitcoin and oil. Additionally, Bitcoin and other financial markets are only tenuously linked during non-crisis periods. Nonetheless, their connection strengthens substantially during times of crisis, such as the great cryptocurrency crash of 2018 and the COVID-19 pandemic of 2020. We believe that these findings can help explain how clean energy and cryptocurrency markets are linked during times of crisis.

Do the time-varying effects of oil prices affect the trade balances of ASEAN-5 countries?

ABSTRACT This study investigates the effects of oil price shocks on five Association of Southeast Asian Nations (ASEAN-5) trade balances by employing a time-varying parameter vector autoregression model with stochastic volatility (TVP-VAR). The time-varying responses derived from this model indicate that the impacts of oil price shocks vary significantly across economies due to their distinct characteristics in the oil market. The results also demonstrate the significant time-varying impact of economic activity and the real exchange rate on the trade balances of the five countries. The time-varying responses show that the effects of oil prices on trade balances are more pronounced during global and local economic events. Our findings have important policy implications for each country to avoid the risks associated with fluctuations in oil prices.

Dynamic connectedness and spillovers between Islamic and conventional stock markets: time- and frequency-domain approach in COVID-19 era

This study investigates the dynamic connectedness and spillovers between Islamic and conventional stock markets to reveal the time- and frequency-domain dynamics of the two asset classes under various market conditions. Using the spillover index of Baruník and Křehlík (2018), supplemented by the time-varying parameter vector autoregressions (TVP-VAR) connectedness model, we employ daily stock market indices for Islamic and conventional (G7) markets from November 23, 2015, to September 8, 2021. The findings explicate that the volatility spillovers across and within Islamic and/or G7 markets are time-varying and frequency-dependent but during market turbulences, the conventional stocks are prone to more volatilities than the Islamic stocks. Our findings additionally divulge contagious spillovers among Islamic and conventional stocks during Brexit and the studied COVID-19 period. Relative to mid-and long-term spillovers, we underscore the supremacy of short-term spillovers between Islamic and G7 markets. In turbulent trading periods, investors should utilise knowledge about market patterns and volatility to hedge their positions against lower stock returns, when spillover is more intense. Regulators should pay close attention to spillovers since they undermine cross-market connections. Intriguing findings and their implications are further discussed.

Gold or Bitcoin, which is the safe haven during the COVID-19 pandemic?

This study compares the dynamic spillover effects of gold and Bitcoin prices on the oil and stock market during the COVID-19 pandemic via time-varying parameter vector autoregression. Both time-varying and time-point results indicate that gold is a safe haven for oil and stock markets during the COVID-19 pandemic. However, unlike gold, Bitcoin's response is the opposite, rejecting the safe haven property. Further analysis shows that the safe-haven effects of gold on the stock market become stronger when the pandemic critically spreads.

Interlinkages of cryptocurrency and stock markets during COVID-19 pandemic by applying a TVP-VAR extended joint connected approach

PurposeThe purpose of this paper is to study the interlinkages between the cryptocurrency and stock market by characterizing their connectedness starting from January 1, 2018 to December 31, 2021.Design/methodology/approachThe author employs a time-varying parameter vector autoregression (TVP-VAR) in combination with an extended joint connectedness approach.FindingsThe pandemic shocks appear to have influences on the system-wide dynamic connectedness, which reaches a peak during the COVID-19 pandemic. Net total directional connectedness suggests that each cryptocurrency and stock have a heterogeneous role, conditional on their internal characteristics and external shocks. In particular, Bitcoin and Binance Coin are reported as the net receiver of shocks, while the role of Ethereum shifts from receivers to transmitters. As for the stock market, the US stock market stays persistent as net transmitters of shocks, while the Asian stock market (including Hong Kong and Shanghai) are the two consistent net receivers. During the COVID-19 pandemic shock, pairwise connectedness reveals that cryptocurrencies can explain the volatility of the stock markets with the impact most severe at the beginning of 2020.Practical implicationsInsightful knowledge about key antecedents of contagion among these markets also help policymakers design adequate policies to reduce these markets' vulnerabilities and minimize the spread of risk or uncertainty across these markets.Originality/valueThe author is the first to investigate the interlinkages between the cryptocurrency and the stock market and assess the influences of uncertain events like the COVID-19 health crisis on the dynamic interlinkages among these two markets. The author employs the TVP-VAR combined with an extended joint connectedness approach.

The dynamic connectedness and hedging opportunities of implied and realized volatility: Evidence from clean energy ETFs

This paper aims to examine dynamic connectedness and hedging opportunities between the realized volatilities of clean energy ETFs and energy implied volatilities through Time-Varying Parameter Vector Autoregression Model (TVP-VAR) and Asymmetric Dynamic Conditional Correlation (ADCC) GARCH models. TVP-VAR analysis results show that dynamic connectedness increases during turbulence periods. We also determine that clean energy ETFs such as PBW, QCLN, SMOG, and TAN are net volatility transmitters. Surprisingly, OVX is a net volatility receiver, especially with the developments after the Paris Agreement in 2016.As a result of the ADCC GARCH analysis, we determine that the conditional correlation between clean energy ETFs and implied volatility ETFs is asymmetric, and negative information shocks increase the conditional correlation. Although OVX is a cheap alternative for hedging long position risks in clean energy ETFs, VXXLE is more effective than OVX in terms of hedging effectiveness. These findings provide insight for individual and institutional investors, and portfolio managers on how negative and positive shocks change the conditional correlation between assets at different levels.

Do global factors drive the interconnectedness among green, Islamic and conventional financial markets?

PurposeThis study aims to examine the connectedness among green, Islamic and conventional financial markets from December 2008 to May 2021. Moreover, the impact of global factors on the connectedness of given financial markets is also observed.Design/methodology/approachThis study first employed the time-varying parameter vector autoregressions (TVP-VAR) technique to explore the connectedness of markets. Second, This study utilized the wavelet coherence analysis to test the time-frequency impact of global factors in terms of implied volatilities of stock, oil, gold, currency and bond on the connectedness across financial markets.FindingsThis study finds Islamic stocks, sustainability index and S&P500 composite index are the net transmitters, whereas Sukuk, commodity index, bond market, clean energy and green bonds are the net recipient of spillovers. Time-varying features of green, Islamic and conventional financial markets are evident in system-wide connectedness. This study further evidenced that global factors drive the connectedness of financial markets, particularly during stressful times.Practical implicationsThe findings of this study furnish significant implications for policymakers, regulatory authorities, investors, financial market participants and portfolio managers in terms of carefully assessing the unique characteristics offered by each financial market in terms of risk mitigation and diversifying the portfolios.Originality/valueUsing a portfolio of green, Islamic and conventional financial markets, the uniqueness of this study lies in the examination of the connectedness of these markets by deploying the TVP-VAR technique. In addition, wavelet analysis offers a significant contribution in terms of global factors driving the connectedness of green, Islamic and conventional markets.

Dynamic connectedness in non-ferrous commodity markets: Evidence from India using TVP-VAR and DCC-GARCH approaches

This study seeks to conduct a comprehensive analysis of the return and volatility spillover dynamics between a network of base metals, in the Indian context, for the time period ranging from January 2011 to March 2020. This paper aims to study the dynamic connectedness between the metal markets by employing the time-varying parameter vector autoregressions (TVP-VAR) framework to analyze return spillovers and the dynamic conditional correlation–generalized autoregressive conditional heteroskedasticity (DCC-GARCH) approach to investigate the volatility spillovers. The results of the TVP-VAR approach show that Zinc, Lead and Nickel are the primary transmitters of disturbances that in turn affect the returns of other metals in the network. At the same time, Copper and Tin are the net receivers of return spillovers. The DCC-GARCH approach reveals that Tin, Aluminium and Zinc are continuous net transmitters of volatility shocks in the network, while Nickel and Lead are the net receivers. Overall, our analysis reveals a definite and substantial level of interconnectedness and implied market risk that exists within the base metal markets, both in terms of returns and volatility. This study therefore suggests a need to reduce the degree of portfolio diversification that involves base metals. These findings may be of particular relevance to policymakers and risk management professionals who seek to understand the risk associated with the base metal commodity markets in an emerging economy.

Dynamic dependence between main-byproduct metals and the role of clean energy market

This paper explores the dynamic dependence between the prices of main-byproduct metal pairs by applying the time-varying parameter vector autoregression (TVP-VAR) modelling. The novel insights into the effect of clean energy market on the connectedness of main-byproduct metal markets are also provided via Granger causality tests and nonparametric causality-in-quantiles approach. Empirical results indicate the time-varying nature of the spillover between main-byproduct metals and the overlooked spillover effect from the byproduct metal market. The significant causal effect of the clean energy market on the co-movement between main-byproduct metal markets implies that the clean energy market and main-byproduct metal markets are closely linked. Particularly, the wind energy market has a stronger effect than the solar energy market on the total spillover of the main-byproduct metal pairs. Furthermore, a battery of linear and nonlinear causality tests suggests the heterogeneous effect of the clean energy market, which causes a linear impact on the spillover from main metal to byproduct metal market, while brings a nonlinear causal effect on the spillover from byproduct metal to main metal market. Our findings highlight the significant role of clean energy market in the connectedness between main-byproduct metal markets.

Frequency connectedness and cross-quantile dependence among medicare, medicine prices and health-tech equity

We investigate the dynamic connectedness among health-tech equity and medicine prices (producer and consumer) and Medicare cost indices for the US market. In doing so, we apply Cross-Quantilogram Dynamic Connectedness based on Time-Varying Parameter Vector Autoregression (TVP-VAR) approaches to analyse historical high-frequency time-series data. TVP-VAR results show that health-tech equity is the highest volatility transmitter while Medicare price is the highest volatility receiver. We also find medicine producer price is the net volatility contributor while the retail price of medicine is the net volatility receiver. The Cross-Quantilogram analysis confirms a strong bivariate quantile dependence between respective markets at a higher quantile of each market. Cross-quantilogram demonstrates a higher level of connectedness among the markets when considering medium and long memory. We observe health-tech equity turned to be a profound volatility contributor, while medicine price (both producer and retail prices) and Medicare appeared to net volatility receiver during the time of COVID19 Pandemic. The financial performance of health-tech equity returns elevates the price volatility of medicine and eventually Medicare cost, which imply that equity return should be incorporated forming medicine prices.

Linkages between DeFi assets and conventional currencies: Evidence from the COVID-19 pandemic

This paper examines the static and dynamic returns connectedness between four renowned DeFi assets, namely, Chainlink, Maker, Basic Attention Token, and Synthetix, and four internationally important conventional currencies, being they Chinese Yuan, Japanese Yen, Euro, and Pound Sterling. We use the time-varying parameter vector autoregressions framework combined with the connectedness approach based on the generalized forecast error variance decomposition. Our static connectedness analysis evidences a low connection of the DeFi markets with the conventional currency markets. The results of our dynamic analysis reveal that the return spillovers are time-varying, with an abrupt increase in connectedness between the DeFi and currency markets in early 2020, during the initial escalation of the pandemic. However, the spillover from the Chinese Yuan to the system does not exhibit any hike due to the COVID-19-triggered meltdown, highlighting a pandemic-caused decoupling of the Chinese financial system from the other centralized and decentralized markets. We observe unprecedentedly high spillovers from the system to the DeFi markets at the beginning of the pandemic. However, we still find that the DeFi markets act predominantly as net innovation transmitters during the first COVID-19 year. Moreover, we detect the existence of a pairwise-like relationship between the net return spillover profiles and report on inversely symmetric profiles for the Maker - Euro, Basic Attention Token - Japanese Yen, and the Chainlink - Pound Sterling pairs. Given the time-varying transmission-reception patterns for all markets, investors and policymakers can make use of our spillover analysis to improve portfolio allocation and regulatory decisions.

Risk transmissions between bitcoin and traditional financial assets during the COVID-19 era: The role of global uncertainties

This paper examines return and volatility connectedness between Bitcoin, traditional financial assets (Crude Oil, Gold, Stocks, Bonds, and the United States Dollar-USD), and major global uncertainty measures (the Economic Policy Uncertainty-EPU, the Twitter-based Economic Uncertainty-TEU, and the Volatility Index-VIX) from April 29, 2013, to June 30, 2020. To this end, the Time-Varying Parameter Vector Autoregression (TVP-VAR) model, dynamic connectedness approaches, and network analyses are used. The results indicate that total spillover indices reached unprecedented levels during COVID-19 and have remained high since then. The evidence also confirms the high return and volatility spillovers across markets during the COVID-19 era. Regarding the return spillovers, Gold is the centre of the system and demonstrates the safe heaven properties. Bitcoin is a net transmitter of volatility spillovers to other markets, particularly during the COVID-19 period. Furthermore, the causality-in-variance Lagrange Multiplier (LM) and the Fourier LM tests' results confirm a unidirectional volatility transmission from Bitcoin to Gold, Stocks, Bonds, the VIX and Crude Oil. Interestingly the EPU is the only global factor that causes higher volatility in Bitcoin. Several potential implications of the results are also discussed.

Volatility spillovers between fine wine and major global markets during COVID-19: A portfolio hedging strategy for investors

Motivated by the growing necessity of portfolio diversification, this paper investigates the dynamic connectedness among fine wine, equities, bonds, crude oil, commodities, gold, copper, shipping and real estate by applying the Diebold and Yilmaz (2012) approach, based on the time-varying parameter vector autoregressive (TVP-VAR) model of Antonakakis et al. (2020), for the period 1/1/2010-5/31/2021. Our results indicate moderate volatility spillovers among the markets over time, whereas total connectedness is prone to exogenous shocks, reaching its peak during stress periods. Equities, crude oil, gold and fine wine are the net contributors of spillovers, whereas real estate, commodities, copper, bonds and shipping constitute the net receivers of the diffused shocks. Furthermore, we estimate and compare the hedging ability of fine wine, before and after the emergence of the coronavirus pandemic, to instruct investors in rebalancing their portfolio strategies during COVID-19. The empirical findings suggest that fine wine can form an effective hedging tool to reduce the risk deriving from adverse movements of the markets and its hedging ability was enhanced during COVID-19, with few exceptions. Regardless time period, the highest hedging effectiveness can be achieved by taking a long position in the volatility of crude oil and a short position in the volatility of fine wine.

Exchange rate pass-through to Japanese prices: Import prices, producer prices, and the core CPI

Against the background of the two percent inflation target that Japan set in 2013, we investigate the impediments in the process of passing on exchange rate fluctuations to the core consumer price index. To this end, we construct the industry-level nominal effective exchange rate and industry-level producer price indices, which are matched with the industry classifications used for import price indices. Time-varying parameter vector autoregression analysis reveals that, in general, exchange rate pass-throughs increased, especially after the global financial crisis. Among the pass-throughs that occur at each stage of the import price, domestic producer price, and consumer price, we find that the weakest link exists between the import price and domestic producer price. However, the impact on the within-industry effect is not negligible; the small spillover effect on other industries at the producer price stage prevents consumer prices from rising after depreciation.

Dynamic nonlinear connectedness between the green bonds, clean energy, and stock price: the impact of the COVID-19 pandemic.

This paper uses weekly data from July 01, 2011 to July 09, 2021 to examine the dynamic nonlinear connectedness between the green bonds, clean energy, and stock price around the COVID-19 outbreak in the global markets. By building a time-varying parameter vector autoregression model (TVP-VAR), the comparison analyses of pre- and during the COVID-19 sample groups verify the existence of nonlinear and dynamic correlation among the three variables. First, prior to the COVID-19 pandemic, the simultaneous impacts of clean energy on stock price increased over time. Second, the results of impulse responses at different horizons indicate that green bonds lead to a short-term increase of clean energy, and it exerts an increasingly positive impacts after the COVID-19 outbreak. The COVID-19 has weakened the negative impacts of green bonds on stock price in the medium term. Finally, through the analysis of impulse responses at different points, we find that stock prices will rise when clean energy is subjected to a positive shock, and this positive effect is stronger during economic recovery period than in the other two periods.

Clean Energy, Australian Electricity Markets, and Information Transmission

This study investigates the connectedness between the clean energy and Australian electricity markets from May 2005 to December 2020. Using time-varying parameter vector autoregressions, we find weak connectedness between the clean energy and Australian electricity markets. The weak connectedness of the clean energy markets to the electricity markets illustrates the diversification potential of clean energy for Australian electricity markets. We cite several implications for policymakers, regulatory bodies, investors, and market participants.

The CARR-volatility connectedness between USD/TRY and foreign banks in Turkey: Evidence by TVP-VAR

This study focuses on the volatility spillover between the stock prices of foreign banks having business in Turkey and the exchange rate. More particularly, it analyzes the connectedness between the USD-TRY exchange rate volatility and the foreign banks’ stock price volatility in their own country’s stock markets. We select ten foreign banks with the biggest total assets and divide them into two panels: eastern and western capitalized banks. The dataset contains weekly data from 2016-01-04 to 2022-01-17. We estimate volatilities utilizing the Conditional Autoregressive Range (CARR) model and then apply the Time-Varying Parameter- Vector Autoregressive (TVP-VAR) based Diebold–Yilmaz Connectedness Index to reveal the transition and connectedness of volatility. The total connectedness indices show that 26.72 and 54.75% of the forecast error variance originate from other assets included in the spillover analysis for eastern and western panels, respectively. We also explore net pairwise comovements and find that shocks in USD-TRY have dominated on the forecast error variance of bank stocks in the eastern panel, while it is a net volatility receiver in the western panel.