Time-varying Parameter Vector Autoregression Research Articles

Spillover Effects between Oil, Gold, Stock, and Exchange Rate Returns in Thailand: An Extended Joint Connected TVP-VAR Approach

The objective of this study is to analyze the spillover effects among the returns of oil, gold, the stock market, and exchange rates in Thailand. Using the time-varying parameter vector autoregression model (TVP-VAR) with extended joint connectedness and data from April 2002 to March 2024, our analysis reveals a moderate level of the dynamic linkage among these returns. We observe that the dynamic connectedness among all returns varies over time, influenced by global economic events and country situations. Notably, in Thailand's landscape, stock market and gold returns act as net shock transmitters, with the stock market exhibiting the highest volatility among all variables, while oil and exchange rate markets function as net recipients. These insights significantly contribute to understanding asset and commodity markets and offer valuable policy implications for effectively managing these markets.

Exploring the coherency and predictability between the stocks of artificial intelligence and energy corporations

This paper employs wavelet coherence, Cross-Quantilogram (CQ), and Time-Varying Parameter Vector-Autoregression (TVP-VAR) estimation strategies to investigate the dependence structure and connectedness between investments in artificial intelligence (AI) and eight different energy-focused sectors. We find significant evidence of dependence and connectedness between the stock returns of AI and those of the energy-focused sectors, especially during intermediate and long-term investment horizons. The relationship has become stronger since the COVID-19 pandemic. More specifically, results from the wavelet coherence approach show a stronger association between the stock returns of energy-focused sectors and AI, while results from the CQ analysis show that directional predictability from AI to energy-focused sectors varies across sectors, investment horizons, and market conditions. TVP-VAR results show that since the COVID-19 outbreak, AI has become more of a net shock receiver from the energy market. Our study offers crucial implications for investors and policymakers.

Cross-border ESG rating dynamics: An in-depth connectedness analysis of portfolio returns and volatilities in the USA and Canada

This study uses a time-varying parameter vector autoregression (TVP-VAR) model to examine the dynamic relationship between rating changes and portfolio returns in the US and Canada across the environmental (E), social (S), governance (G) and total ESG assessment pillars. The analysis includes both return and volatility spillovers and covers the period from March 2009 to October 2022. The study reveals a fluctuating pattern of connectedness, influenced by global financial events, such as the 2008 financial crisis. In particular, the US shows higher levels of connectedness. Rating changes, particularly in the ESG dimension, show stronger spillovers than returns, highlighting their importance in portfolio construction. The study further explores net connectedness profiles, identifying ESG rating changes as net transmitters. The results suggest that investors should prioritize rating changes over returns, highlighting the importance of considering ESG factors in portfolio management, especially the social criterion, to mitigate investment risks. The research contributes to the understanding of ESG dynamics in international equity markets and provides valuable insights for investors and market regulators.

Time-frequency higher-order moment Co-movement and connectedness between Chinese stock and commodity markets

This study examines the higher-order moment co-movement and connectedness between China's stock and commodity markets across time and frequency domains. We propose wavelet decomposition to develop a multiscale time-varying parameter vector autoregression (TVP-VAR) approach for measuring higher-order moment connectedness. Our empirical findings are as follows: First, the co-movement of stock-commodity varies over time and across different frequencies, exhibiting heterogeneity at different moments. Stocks demonstrate robust co-movement with commodities over the medium- and long-term periods. Second, higher-order moment connectedness is stronger than return connectedness, whereas weaker than volatility connectedness. Finally, higher-order moment connectedness is highly event-dependent, peaking at COVID-19 onset. And long-run factors have the greatest effect on dynamic moment connectedness.

Harmony in diversity: Exploring connectedness and portfolio strategies among crude oil, gold, traditional and sustainable index

The research investigates dynamic connectedness and portfolio strategies among crude oil, gold, global traditional (DJGI) and sustainable (DJSI) indices. The time-varying parameter vector autoregression (TVP-VAR) findings reveal that the average total connectedness among the assets is 33.03%, with the total dynamic connectedness index exhibiting a notable surge during two crises and one stability period. The upsurge exhibited a predominant prevalence of short-run connectedness during crisis periods, notably amidst the COVID-19 pandemic and the Russia-Ukraine war. Conversely, the last and first quarters of 2017 and 2018 manifested as periods of stability, wherein long-term interconnectedness prevailed. Crude oil and gold emerge as the primary recipients of systemic shocks, while traditional and sustainable stock indices act as net transmitters of shocks. The BEKK and DCC GARCH models indicate short- and long-run persistence among the assets. Further, the study calculated hedge ratios and portfolio weights. Our empirical findings indicate that gold serves as a cost-effective hedging asset. Investors should invest more in the traditional stock index than in gold and crude oil to form an optimal portfolio. Notably, the global sustainable index offers results similar to those of the traditional index. Investors in the sustainable index would invest a similar amount for diversification and hedging with other traditional assets as they would for the traditional index.

Sparse-structured time-varying parameter vector autoregression for high-dimensional network connectedness measurement

This paper proposes a new sparse-structured time-varying parameter vector autoregression (SS-TVP-VAR) model to effectively measure high-dimensional network connectedness of financial enterprises. Previous VAR based network connectedness methods require high computational cost and are not feasible for high-dimensional networks of a large number of enterprises. The proposed SS-TVP-VAR not only reduces computational cost but also selects key coefficients when building the VAR model. As a result, it produces a more adaptive and effective connectedness to measure systemic risk caused by extreme events. Studies on 57 listed major financial enterprises in China mainland during a 15-year period show that the proposed SS-TVP-VAR achieves reliable and useful results, and it successfully identifies all the major market events during this time.

Islamic cryptocurrency integration for enhanced sustainable finance: evidence from time-frequency volatility transmission investigation

ABSTRACT This study explores the potential of Islamic gold-backed cryptocurrencies in sustainable finance by focusing on volatility transmission between these cryptocurrencies and conventional digital assets like Bitcoin and PaxGold. Using a Time-Varying Parameter Vector Autoregression (TVP-VAR) approach, we analyze data from December 2019 to July 2023, including the COVID-19 pandemic period. Findings reveal a complex volatility network, with Bitcoin and HelloGold as major transmitters of spillover shocks, while X8X and PaxGold mainly serve as net recipients. Notable interactions between Bitcoin and Islamic gold-backed cryptocurrency markets show short-lived pairwise volatility interactions. Islamic gold-backed cryptocurrencies, net recipients of volatility, absorb market shocks, making them suitable for hedging against volatility. This can aid in diversifying portfolios, mitigating adverse market impacts, and informing risk management and regulatory approaches. Our research emphasizes the importance of Islamic finance in ethical and sustainable investment within the evolving cryptocurrency market.

Contagion effect between fuel fossil energies and agricultural commodity markets and portfolio management implications

This study investigates the dynamic spillover effects between fossil fuels (Brent oil and natural gas) and major agricultural markets (maize, soybeans, and wheat) using a time-varying parameter vector autoregression (TVP-VAR) model. Additionally, we quantify the cumulative return of the investment portfolio, optimal weights, time-varying risk coverage, and hedging effectiveness of bivariate commodity portfolios using the Minimum Variance Portfolio (MVP), Minimum Correlation Portfolio (MCP), Minimum Connectedness Portfolio (MCoP) under bearish, tranquil, and bullish market conditions. The results show that maize and natural gas are the main net receivers of spillovers, whereas wheat and Brent oil are the main net transmitters of shocks to the network, respectively. Our findings of optimal weights in multivariate portfolio suggest more weights for agri-commodities against fossil fuels in all three modes of market. In addition, the optimal weights of bivariate portfolio analysis show that the most optimal portfolio which has the highest HE value is related to natural gas pairs with agri-commodities. Moreover, depending on the status of the market; in an average and bearish modes, the highest optimal weight is related to maize/natural gas. However, in the bullish market, the highest optimal weights are related to natural gas/Brent oil pair. Furthermore, the results of optimal bivariate hedge ratios show that natural gas/wheat (wheat/maize and vice versa) portfolio is the cheapest (the most expensive) investment strategy in all modes of market and based on MVP and MCoP approaches.

China’s GDP-at-Risk: Real-Time Monitoring, Risk Tracing, and Macroeconomic Policy Effects

Timely monitoring GDP-at-risk and tracing economic downside risk sources can help establish effective risk warning and prevention systems. This study constructs a probability distribution for China’s economic growth with skewness determined by a multidimensional predictor information set of macro fundamentals. Such a treatment allows us to identify changing drivers of economic downside risks during monitoring GDP-at-risk’s dynamic evolutionary path. We also employ a time-varying parameter vector autoregression model with random volatility to explore the heterogeneous impacts of different macroeconomic policy instruments on economic slowdowns. Our results provide empirical support for macroeconomic management and policy formulation in emerging markets. We reach three conclusions. First, the dynamics of GDP-at-risk exhibit significant event-driven characteristics, and economic downside risk increases significantly under the influence of extreme events. Moreover, the probability distribution of economic growth is asymmetric--as the downside risk of the economy increases, its upside potential increases disproportionately. Second, the time-varying risk trace of GDP-at-risk shows that the contribution of financial conditions and local government debt to economic downside risk declines. The importance of the risk-driving role of housing price growth gradually increases, suggesting that China’s property prices can provide more valuable early warning information about future growth risk, allowing time for precise preventive measures. Nevertheless, interest rates and inflation as risk divers have consistently minimal impacts. Third, the heterogeneity impulse response function of GDP-at-risk suggests that quantity-based monetary policy and fiscal policy can manage economic downside risks in the short run. In contrast, price-based monetary policy can curb economic overheating and reduce downside risks in the medium to long term. Therefore, the effect of price-based monetary policy is more sustainable in China.

Leadership shift in the global soybean market: Dynamic connectedness approach (TVP-VAR)

The price transmission in international soybean market has been extensively examined. However, recent econometric advancements have enabled the application of dynamic connectedness methodology as outlined by Antonakakis and Gabauer (2017) [1], which is based on a Time-varying Parameter Vector Autoregressive (TVP-VAR) model. This approach captures the time-varying connectedness of time series, considering potential risk shock emitters and receivers. The connectedness index (Diebold and Yilmaz, Jan. 2012) [2] was developed using Generalized Forecast Error Variance Decomposition (GFEVD) and the Generalized Impulse Response Function (GIRF) (Koop et al., Sep. 1996; Pesaran and Shin, Jan. 1998) [3,4]. This study aims to understand the dynamic connectedness and price leadership. The research examined markets including the US Soybean futures market (Chicago Board of Trade), Rotterdam Port spot market representing the European soybean market, Paranaguá port representing Brazil, Argentina represented by Rosario Futures and Spot, and the Chinese domestic spot market and the Dalian futures on behalf of China. The research spanned approximately ten years, from September 2009 to May 2019. The findings suggest that the soybean market has reached a high level of maturity, able to withstand exogenous shocks for at least the past seven years. The net pairwise directional connectedness revealed dynamic and bidirectional causality. The dynamic connectedness index showed a highly connected and developed market in the West (Chicago Futures, Rotterdam, Paranaguá, and Rosario Futures and Spot). However, the connectedness between Western and Eastern markets was relatively low, indicating some level of market isolation. Furthermore, the pairwise connectedness index between Eastern market (China spot and Dalian Futures) was also considerable low. Lastly, Paranaguá and Rosario overtook Rotterdam as price-leading markets and were identified as the primary net transmitters of shocks, indirectly implying causality. Chicago, Rosario, and Paranaguá formed a triumvirate leading international prices, while Rotterdam adopted a secondary leading position, deviating from its historical role as the price leader.

Dynamic interconnectedness of economic confidence, energy prices, and interest rates: Insights from the euro area

This work examines the time-varying interlinkages among economic confidence, energy prices, geopolitical stress, and short/long-term interest rates in the Euro Area. Our research meticulously explores the interplay between economic confidence and various determinants, including financial indicators, geopolitical stress incidents, and energy prices. Employing innovative approaches such as the time-varying parameter vector autoregression (TVP-VAR) time and frequency-domain connectedness, we uncover the nuanced relationships between economic confidence, financial indicators, and energy prices. We illuminate the systemic nature of shock transmission in the Euro Area, identifying key net transmitters and recipients of shocks, with short-term interconnectedness emerging as a dominant feature, especially during pivotal events such as the global financial crisis, the COVID-19 pandemic, and geopolitical conflicts. Our empirical findings can be summarized as follows: First, both the time and frequency-domain connectedness indexes correctly associate with major financial/geopolitical events. Second, BCI and CCI respond to the GFC asymmetrically. Third, Brent and short/long-term interest rates are the net transmitters of shocks on average. Fourth, there is a considerable augmentation in return spillovers during the period characterized by the pandemic crisis compared to the GFC. Finally, our findings for frequency-dependent connectedness networks indicate that the market is particularly susceptible to short-term shocks. This study has significant ramifications for investors, market players, and policymakers.

The nexus between mineral, renewable commodities, and regional stock sectors during health and military crises

We examine the return and volatility spillover dynamics and their portfolio implications among regional stock super-sectors, mineral (Energy, Industrial, and Precious Metals), and renewable (Agricultural and Livestock) commodities. To this end, we apply the time-varying parameter-vector autoregressive (TVP-VAR) model to analyze the intersectoral-commodity linkages separately in four major regions (Europe, Eastern Europe, Asia Pacific, and North America). The empirical results show that stock market sectors dominate the spillover transmission mechanism, while commodities emerge as net recipients of shocks. Moreover, we find heterogeneous connectedness patterns between stock sectors and commodities, predominantly running from the Energy and Basic Resources stocks to the Energy and Industrial Metals commodities. Thus, energy commodities play a more vital role as a spreader of volatility shocks amid the COVID-19 pandemic and the wake of the Russia-Ukraine war. The optimal portfolio weights reflect two episodes of “flight to safety” towards all commodities except Energy, triggered by the pandemic and the war, as investors decrease their fund allocation to stocks in favor of commodities.

Overlooked carbon sinks in the house building industry and the influential factors

The study aims to establish a carbon sink measurement model for the house building industry and analyze the time-varying characteristics of influential factors. China's house building industry exhibited an increasing trend in carbon sink, from 0.336 billion tons in 2000 to 234.1 million tons in 2020. This study defines the carbon sink coefficient of the house building industry to understand its carbon sink capacity. From 2000 to 2020, the average carbon dioxide absorption per square meter of floor space annually, throughout its life cycle, is 2.09 kg. Factors influencing the carbon sink were analyzed using Logarithmic Mean Divisia Index (LMDI) model. The most influential factor was resource consumption intensity, followed by value dependence level and output scale effect. Employing Time-Varying Parameter Vector Autoregression (TVP-VAR), this study examines the impact of macro factors on carbon sinks at various lead times and specific points. Resource consumption intensity exhibits significant time-varying effects. Value dependence level negatively influences, primarily in the medium and long terms, while the output scale effect consistently shows a positive influence, mainly in the long term. Scenario forecasting suggests that by 2035, under low-carbon transition scenarios, carbon sinks could increase by 8.28% and 17.26% compared to baseline and high-carbon crude scenarios, respectively. To foster this growth, prolonging the service life of houses, enhancing construction site management and waste treatment, and employing higher value-added production factors are recommended.

Dynamic Returns Connectedness: Portfolio Hedging Implications During the COVID‐19 Pandemic and the Russia–Ukraine War

ABSTRACTWe apply a Time‐Varying Parameter Vector Auto Regressive (TVP‐VAR) connectedness approach on global assets to investigate time‐varying dynamic connectedness, portfolio performance, and hedge effectiveness during COVID‐19 and the Russia–Ukraine war. With increased connectedness and the changing role of energy and soft commodities during these two events, we find the minimum correlation (connectedness) portfolio performing better during COVID‐19 and the Russia–Ukraine war and that cumulative returns of portfolios are higher during COVID‐19. Additionally, we find varying (stable) hedge effectiveness of equity market indices and soft commodities (cryptocurrencies). This paper provides specific insights to investors about using optimal portfolios and hedging during pandemics and military conflicts.

The impact of COVID-19 on global financial markets: A multiscale volatility spillover analysis

This paper presents a comprehensive multiscale analysis of volatility spillover mechanisms among diverse financial markets utilizing a novel combination of Normalized Adaptive Multivariate Empirical Mode Decomposition (NA-MEMD) and Time-Varying Parameter Vector Autoregressive (TVP-VAR) model. Our analysis spans Bitcoin, crude oil, gold, foreign exchange, emerging stock markets, and developed stock markets, examining their respective roles in global volatility transmission. Utilizing the NA-MEMD methodology and a time-varying volatility spillover index, we find that in the short-term, Bitcoin and crude oil primarily act as volatility receivers, while other markets serve as volatility transmitters. Over the long-term, gold and Bitcoin consistently act as volatility receivers, with Bitcoin and gold showing evident safe-haven effects, while the remaining markets primarily function as volatility transmitters. Particularly post-COVID-19, developed stock markets emerge as significant transmitters of volatility, largely directed towards the crude oil market. By evaluating and comparing risk transmission patterns among financial markets before and during the COVID-19 pandemic, our findings offer valuable insights that can assist policymakers and other stakeholders in managing financial uncertainty in times of global crises.

A new method for measuring financial resilience

This paper proposes a new model to measure financial resilience from the perspective of external risk shocks, which composes of three submodels, namely, the dynamic factor model, the time-varying parameter vector autoregression (TVP-VAR) model, and the resilience characteristic measurement model with two dimensions: absorption intensity and absorption duration. At the theoretical level, we simulate and analyze the changing paths of financial resilience under different scenarios. At the empirical level, we apply the model to study the resilience of the UK financial market. The results indicate that the UK financial resilience fluctuations exhibit phased characteristics and there is a clear inverse relationship between absorption intensity and absorption duration. Notably, periods of low resilience often coincide with specific risk events.

Estimating the natural rate of interest for the emerging Asia

This paper evaluates the natural rate of interest (NRI) for Indonesia, Malaysia, Philippines, Singapore, South Korea, [Taipei, China], and Thailand and aggregates them using a GDP-weighted average. This paper discusses four key points. Firstly, to estimate the NRI in emerging Asian economies, this paper introduces a Time Varying Parameter Vector Autoregression (TVP-VAR) model that integrates exchange rates alongside conventional growth and inflation variables. Secondly, the results show that NRIs in the emerging Asia have been declining in trend since the 1990s. Thirdly, the behavior of the NRI for each economy is not uniform across crises—the Asian Financial Crisis, the Global Financial Crisis, and the COVID-19 pandemic. Fourthly, the findings reveal that the ascertained Asian NRI decreased to the vicinity of 0% during the COVID-19 pandemic period.

Asymmetric TVP-VAR connectedness between highly traded commodities and hedging strategies: Evidence from major contagions

The objective of this study is to examine the return interconnectedness and asymmetric spillover effects in global commodity futures markets, with a focus on the impact of contagion. A competent asymmetric time-varying parameter vector autoregressive (TVP-VAR) model was employed for highly traded commodity futures (cocoa, coffee, corn, cotton, soy, sugar, wheat, and oil) between January 1, 2000, and March 31, 2024. This study investigates the connectedness of commodities in three dimensions: asymmetric spillovers, the influence of oil and oil substitutes on the network, and the impact of major contagions. The average total connectedness index (TCI) indicates that the connectedness is significant throughout the period and increases during the invasion. The findings imply that contagion effects trigger a potential alteration in the structure of the network integration level of the commodities, amplifying system-wide dynamic connectivity due to disurptions caused by oil and oil substitutes. The net plot depicts corn and soy as the net transmitters, with their magnitude increasing during the contagions. The pairwise connectedness index (PCI) revealed that corn-soy, corn‒wheat, and soy-wheat were the primary interactors, while oil became a significant interactor, particularly during the oil crash and the COVID-19 outbreak. Additionally, compared with other contagions, GFC had a potential asymmetric effect on the network. Positive returns dominate the interaction between the primary transmitter and receivers, whereas negative returns do not significantly dominate the total network. These investigations contribute to the literature on the food-fuel nexus in terms of asymmetries and the impact of contagions on the futures market. It also identified the optimal portfolio allocation based on the hedging effectiveness of three portfolio construction strategies.

The trend of digital finance: unveiling the multidimensional network of cryptocurrency risk propagation

ABSTRACT This study primarily explores the mechanisms of risk propagation among cryptocurrencies, unveiling for the first time the frequency dimension of risk propagation within the cryptocurrency market and identifying the role of oscillation frequency in this process. By employing Variational Mode Decomposition (VMD) and the DY spillover matrix to construct a complex network, the paper analyzes the frequency dimension risk propagation mechanisms of nine major cryptocurrencies from 2017 to 2023. Key findings include the significant risk propagation capabilities of Ethereum (ETH) and Bitcoin (BTC) during periods of high market volatility, while stablecoins such as Tether and USD Coin exhibit minimal risk propagation ability. Additionally, the characteristics of cryptocurrency risk propagation have been enhanced following the COVID-19 pandemic. Overall, the risk propagation of most cryptocurrencies is primarily realized through high-frequency oscillations. The robustness of the conclusions is verified using the Time-Varying Parameter Vector Autoregressive (TVP-VAR) model. The results are significant for understanding the dynamic characteristics of the cryptocurrency market, predicting future market risks, and formulating risk management strategies. Furthermore, the methodology and findings of this study provide new perspectives and tools for exploring the risk propagation relationships among cryptocurrencies.

Volatility and returns connectedness between cryptocurrency and China’s financial markets: A TVP-VAR extended joint connectedness approach

We employ a time-varying parameter vector autoregression (TVP-VAR) joint connectedness approach to study the dynamic risk spillover effects between cryptocurrencies and China’s financial market, further exploring the impact of cryptocurrencies on China’s financial market. Our results show that there is asymmetric risk transmission between cryptocurrencies and China’s financial market, and the risk spillover effect is very weak. Specifically, the spillover of cryptocurrencies to China’s financial market is significantly stronger than the spillover of China’s financial market to cryptocurrencies. Cryptocurrencies have a stronger spillover effect to China’s exchange rate and gold. The net spillover effect of cryptocurrencies is weakening over time. Overall, the return spillover impact of cryptocurrencies on China’s financial market is greater than the volatility spillover impact, and the degree of impact of different cryptocurrencies is heterogeneous. The findings of this study have several implications for policymakers and investors.