Time-varying Granger Causality Research Articles

Time-varying Granger causality tests in the energy markets: A study on the DCC-MGARCH Hong test

The analysis of causality among oil prices and, in general, between financial and economic variables is of central relevance in applied economic studies. The recent contribution of Lu et al. (2014) proposes a new causality test, the DCC-MGARCH Hong test. We show that the critical values of the test statistic should be evaluated through simulations to avoid potential Type I errors. We also note that rolling Hong tests represent a more viable solution in the presence of short-lived causality periods.

From systematic to systemic risk among G7 members: Do the stock or real estate markets matter?

Stock and housing market systematic risk may be a critical ingredient in the precipitation of systemic risk and hence a financial crisis. However, surprisingly few studies have so far explored the role of their contagion in triggering systemic risk. In this paper, time-varying connectedness is used to measure two-market systematic risks and time-varying Granger-causality is employed to monitor their causal interactions over time. Using quarterly G7 data over a long period covering 1970–2021, our results indicate that these systematic risks both are very volatile. Moreover, the dominant source of causality in the housing systematic risk implies that policies directed against the possibility of a housing bubble, for example, macroprudential toolkits, deserve special emphasis. Finally, given that the duration of the bilateral causality coincides with those in past crises, a dynamic probit model reveals that adopting an expansionary monetary policy with a huge reduction in interest rates may greatly increase the likelihood of a financial crisis.

Testing for time-varying Granger causality

The concept of Granger causality is an important tool in applied macroeconomics. Recently, recursive econometric methods have been developed to analyze the temporal stability of Granger-causal relationships. This article offers an implementation of these recursive procedures in Stata. An empirical example illustrates their use in analyzing the temporal stability of Granger causality among key U.S. macroeconomic series.

Infectious disease equity market volatility, geopolitical risk, speculation, and commodity returns: Comparative analysis of five epidemic outbreaks

This paper uses a time-varying Granger causality test and time-varying parameter vector autoregression with stochastic volatility model to analyze the effects of infectious disease equity market volatility (ID-EMV), geopolitical risk (GPR), and speculation on commodity returns. The time-varying effects of ID-EMV, GPR, and speculation on commodity returns are investigated and compared in five epidemics during 1998–2021: Bird Flu in 1998, SARS in 2003, Swine Flu in 2009, MERS and Ebola in 2014, and COVID-19 in 2019. A further analysis is performed for five commodity subcategories of textiles, industry, metals, livestock, and food. Results show that time-varying effects are significant, and most responses to ID-EMV are positive, to GPR are changing from negative to positive, and to speculation are negative. Notably, ID-EMV in the ongoing COVID-19 pandemic is the worst hit to commodity returns in more than two decades.

Analyzing the Nexus Between Geopolitical Risk, Policy Uncertainty, and Tourist Arrivals: Evidence From the United States.

This study attempts to explore the causal linkage of the COVID-19 pandemic, economic policy uncertainty, geopolitical risk, and tourism arrivals in the United States taking data from January to November 2020. In order to analyze the above relationship, this study uses a novel time-varying granger causality test developed by Shi et al. (2018), which incorporates its three causality algorithms such as forward recursive causality, rolling causality, and recursive evolving causality. The findings from forward recursive causality could not confirm any significant causal relationship between COVID-19 and tourism, geopolitical risk (GPR) and tourism, economic policy uncertainty and tourism, and geopolitical risk and COVID-19 but found causality between economic policy uncertainty and COVID-19. The rolling window causality reported bidirectional causality between COVID-19 and tourism and unidirectional causality running from tourism to geopolitical risk. However, the recursive evolving causality identified a significant bidirectional causal relationship between all the variables. Based on the findings, policy implications for the tourism sector are provided.

Oil price and economic performance: Additional evidence from advanced economies

This study reexamines the causal relationship between oil price and economic performance (proxy by GDP returns) in seven selected advanced economies: Australia, Canada, China, the US, the UK, Japan, and Germany. We employ the homoscedastic and heteroscedastic-consistent versions of the Shi et al. (2020) bootstrap time-varying Granger causality to detect and date stamp causal changes in the relationship between oil price and GDP returns of the sample countries. Findings indicate bidirectional causality between oil price and economic performance for at least one month across all sample countries within notable global events such as the global financial crisis and the COVID-19 pandemic. The study also detects and date stamps long periods of causality running from the economic performances of Canada, China, the US, Japan, and Germany to oil prices using GDP returns as a predictor. The results indicate the weight and significance of the predictive power of the GDP growth of these economies in shaping the cyclical fluctuation of oil prices extending through pre and post COVID-19 epidemic. The findings inform some policy implications.

The contagion effect of COVID-19-induced uncertainty on US tourism sector: Evidence from time-varying granger causality test

This study investigates the effect of COVID-19-induced uncertainty on the overall stock market and the stock performance of the tourism and hospitality industry and its subsectors utilizing a novel time-varying robust Granger causality test. The results show that the COVID-19 pandemic–induced uncertainty has an adverse impact on the overall economy, tourism and hospitality industry, and subsectors of tourism and hospitality. However, the impact of COVID-19 pandemic–induced uncertainty is more significant in the tourism and hospitality industry and its subsectors. In particular, hotels sector has experienced the largest impact from the COVID-19 pandemic, followed by restaurants and airline sectors, respectively. Research and practical implications are discussed. JEL Classification: C1, C5, F2, G11, G17, G41

Are clean energy and carbon emission allowances caused by bitcoin? A novel time-varying method

The bitcoin market has substantially grown in recent years. The researchers are exploring its various repercussions for socioeconomic and political matters; however, the literature still lacks clear evidence on how bitcoin interacts with energy and the environment. This study aims to explore the causal relationship between bitcoin, clean energy, and carbon emissions allowances by applying the novel time-varying Granger causality test on the daily data spanning from Sept 17, 2014, to October 12, 2021. The empirical findings confirm that both clean energy and emission allowances are causally associated with bitcoin. However, this causal relationship varies over time and the duration of causality is longer as suggested by the recursive evolving procedure. The outcome is robust when bitcoin is measured by the volume and the price. Furthermore, the results obtained from robustness analysis conducted through heteroskedastic consistent test also validate the findings that bitcoin causes clean energy and carbon allowance. The findings offer a platform for government officials and policy managers to improve clean energy and carbon allowance markets for sustainable development by managing and using the tools to control and regulate cryptocurrency markets.

Housing networks and driving forces

This paper investigates patterns in housing market networks using Australian and Chinese data and a novel econometric approach based on pairwise time-varying Granger causality tests. The focus is on four fundamental questions. (1) Have housing markets become increasingly connected over time? (2) Does housing market connectivity increase or decrease with house prices? (3) Are socio-economic and geographic proximity important for housing market connections? (4) Do economic fundamentals or sentiment drive connectivity? The results reveal interesting differences in these markets and suggest that one size is not likely to fit all in terms of housing market policy.

Evaluating influential nodes for the Chinese energy stocks based on jump volatility spillover network

We employ a complex network approach to dig out the influential Chinese energy stocks in this paper. We first use the 5-min high-frequency data of the Chinese energy stocks over the period of 2013–2018 to build a static jump volatility spillover network. Then a novel method of entropy weight TOPSIS (Technique for Order Preference by Similarities to Ideal Solution) is proposed to evaluate the influential nodes. Furthermore, we construct dynamic networks with the help of time-varying Granger causality test. Empirical analyses show that: (1) Combining static network and the proposed entropy weight TOPSIS scores, we find that China Petroleum Engineering & Construction Corp, Zhengzhou Coal Industry & Electric Power Co.,Ltd., Shenzhen Guangju Energy Co.,Ltd., China Coal Energy Company Limited and Shaanxi Provincial Natural Gas Co.,Ltd. are influential energy stocks. (2) The advantage of entropy weight TOPSIS lies in the fact that it has the highest correlation coefficient between its score and jump volatility is the highest, comparing with the traditional methods such as equal weight, TOPSIS, analytic hierarchy process and principal component analysis. (3) Particularly, by making full use of dynamic network analysis, a very interesting finding in this paper indicates that the network density also provides an “early warning” for possible upcoming crises. (4) In addition, a very interesting fact in point is that most of the stocks with larger market capitalization usually have high-level influence during Chinese stock market crash; such smallcapitalization energy stocks with high scores are however particularly crucial for investors and regulatory authorities to grasp the risk characteristic. The results can provide us some light for finding out those influential energy stocks whose volatilities may cause many other stocks in the energy industry to rise and fall.

The causal relationship between economic policy uncertainty and stock indices in OECD and non-OECD countries: evidence from time-varying Granger causality tests on a lag-augmented VAR model

ABSTRACT This study re-examined the causal relationship between economic policy uncertainty (EPU) and stock indices for Organization for Economic Co-operation and Development (OECD) and non-OECD countries. To this aim, it applied the lag-augmented vector autoregression model with a time-varying Granger causality test . Based on the standard Granger causality test results, only afew countries demonstrated acausal relationship between two variables. However, the empirical findings using of time-varying Granger causality test indicate that the causal relationship between the two variables is not present for the entire period, but it is present for some sub-periods in many countries. Additionally, the results found that causality running from stock indices to EPU (stock price-leading hypothesis) for many periods and countries. The results indicate that the relationship between two variables is not constant, meaning that it changes from one period to the next in many countries.

Time-varying Granger causality between the stock market and unemployment in the United States

ABSTRACT In this paper, we look at the connection between the stock market and the unemployment rate in the United States. Using a recent time-varying Granger causality framework covering the period from January 1960 to October 2020, tests reveal that lagged realizations of the stock market have predictive power regarding unemployment, and vice et versa, but that the predictive ability only occurs sporadically over time, particularly during ‘crash’ periods. These results are in line with the literature on the information spillover between finance markets and the real-life economy, with changes of causality across time.

The dynamics of U.S. industrial production: A time-varying Granger causality perspective

The concept of Granger causality is an important tool in applied macroeconomics. Recursive econometric methods to analyze the temporal stability of Granger-causal relationships have recently been developed. These recursive procedures are used to re-evaluate the temporal stability of Granger causality between US industrial production and three macroeconomic variables. There appears to be significant evidence of temporal variation in the causal relationships. A clear pattern that emerges from the results is that the causal channels from all three variables to industrial production appear to be very strong in the latter part of the sample period.

Understanding gas pricing mechanisms: implications for the Asian market

ABSTRACT This article aims to understand the gas-pricing mechanisms in the world’s major markets and hence draw implications for gas-pricing reform in Asia. It adopts a newly proposed time-varying Granger causality test to investigate the connection between crude oil and natural gas prices. The empirical results suggest the necessity to establish gas trading hubs and hence adopt hub-based pricing in Asia and Europe so that gas pricing can fully reflect the fundamentals in gas markets and help achieve more efficient gas allocation. The resultant growth in gas consumption and potential replacement of dirtier fuels such as coal and oil is important for emission reduction and hence climate change action in the world, particularly in Asia, the world’s most dynamic region.

The time-varying causal relationship between the Bitcoin market and internet attention

The increasing attention on Bitcoin since 2013 prompts the issue of possible evidence for a causal relationship between the Bitcoin market and internet attention. Taking the Google search volume index as the measure of internet attention, time-varying Granger causality between the global Bitcoin market and internet attention is examined. Empirical results show a strong Granger causal relationship between internet attention and trading volume. Moreover, they indicate, beginning in early 2018, an even stronger impact of trading volume on internet attention, which is consistent with the rapid increase in Bitcoin users following the 2017 Bitcoin bubble. Although Bitcoin returns are found to strongly affect internet attention, internet attention only occasionally affects Bitcoin returns. Further investigation reveals that interactions between internet attention and returns can be amplified by extreme changes in prices, and internet attention is more likely to lead to returns during Bitcoin bubbles. These empirical findings shed light on cryptocurrency investor attention theory and imply trading strategy in Bitcoin markets.

Energy, agriculture, and precious metals: Evidence from time-varying Granger causal relationships for both return and volatility

The existing literature on the Granger causality between various commodity sector (energy, agriculture, and precious metals) indices remains limited in several aspects such as the long length of the sample period, time-variation in the causality relationship, and the examination of both returns and volatility. In the context of an enduring debate on the dynamic relationships among commodity sector indices during various turbulent and crisis periods, we use a long sample period, from January 1960 to May 2021, and detect changes in the relationships for both returns and volatility series via the application of the recent time-varying Granger causality test of Shi et al. (2020). The results show evidence of significant time changes in the relationships across all pairs of commodity sector indices, for both return and volatility and, in some cases, significant sequential feedback effects that are heterogenous across the three commodity sector indices. The evidence of temporary spillovers between energy and agriculture and energy and precious metals is more frequent than between agricultural and precious metals, especially for the return series. The time-variation and heterogeneity in the Granger causal relationships among the commodity sector indices do not always coincide with stress and crisis periods but can be seen in light of continuous developments and challenges in the commodity markets such as biofuel expansion and the financialization phenomenon.

Changes in the revenue–expenditure nexus: confronting evidence with fiscal policy in Brazil

ABSTRACT This study examines causality shifts in the revenue–expenditure nexus in Brazil during the years 1996–2019. The literature usually assumed a time-invariant causality link between government revenues and expenditures. Such assumption becomes often implausible when the sample period covers significant economic, political and policy changes, like the case of Brazil in the last two decades. Based on time-varying Granger causality tests, we found three distinct causality episodes: fiscal synchronization in 2005–2008, spend-and-tax in 2010–2013, and a tax-and-spend in 2015–2018. These episodes are intercalated with periods of no causality that coincides with economic crisis, political turmoil and major shifts in fiscal policy. The findings suggest that the interplay between fiscal policy orientation and primary surplus targeting is an important factor in the revenue–expenditure nexus. The most recent causality episode suggests stronger effects running from revenues to expenditures in the Brazilian primary budget dynamics. In this context, according to the tax-and-spend hypothesis, cutting spending seems to be the right course of action to restore fiscal balance in Brazil. A tax increase should be considered with caution because it may only incentive the government to grow its expenditures.

Oil volatility index and Chinese stock markets during financial crisis: a time-varying perspective

PurposeThis study aims to examine the interconnection among the oil volatility index (OVX) and the Chinese stock markets (CSM) during the financial crisis over the period June 1, 2007 to June 26, 2012.Design/methodology/approachApplying the time-varying Granger causality test, this paper conducts an exhaustive analysis of the OVX and the CSMs during the financial crisis. In particular, the financial crisis is classified in three stages, namely, the US subprime crisis, the global financial crisis and the sovereign debt crisis.FindingsBriefly, the findings indicate almost a neutral relationship between the OVX and the CSMs during the entire financial crisis, the US subprime crisis and the global financial crisis. Finally, this paper has found a positive relationship between the OVX and the CSMs during the sovereign debt crisis.Practical implicationsThis outcome clearly suggests that Chinese investors have to disregard uncertain information. In addition, policymakers can ameliorate the willingness of market investors in the CSM and further deepen the market-oriented reform of China’s domestic oil prices.Originality/valueThe innovative combination of these two strands, the OVX and the three stages of the financial crisis, is empirically examined in the study and this paper finds a non-linear linkage between the OVX and CSMs.

Time-Varying Granger Causality Tests for Applications in Global Crude Oil Markets: A Study on the DCC-MGARCH Hong Test

Analysing causality among oil prices and, in general, among financial and economic variables is of central relevance in applied economics studies. The recent contribution of Lu et al. (2014) proposes a novel test for causality— the DCC-MGARCH Hong test. We show that the critical values of the test statistic must be evaluated through simulations, thereby challenging the evidence in papers adopting the DCC-MGARCH Hong test. We also note that rolling Hong tests represent a more viable solution in the presence of short-lived causality periods.

What role do futures markets play in Bitcoin pricing? Causality, cointegration and price discovery from a time-varying perspective?

Recent papers that have explored spot and futures markets for Bitcoin have concluded that price discovery takes place either in the spot, or the futures market. Here, we consider the robustness of previous price discovery conclusions by investigating causal relationships, cointegration and price discovery between spot and futures markets for Bitcoin, using appropriate daily data and time-varying mechanisms. We apply the time-varying Granger causality test of Shi, Phillips, and Hurn [2018]; time-varying cointegration tests of Park and Hahn [1999], and time-varying information share methodologies, concluding that futures prices Granger cause spot prices and that futures prices dominate the price discovery process.