Markov-switching Vector Autoregressive Model Research Articles

Granger predictability of real oil prices by us money and inflation in Markov-switching regimes

Abstract This paper presents new evidence that US money supply growth and inflation rates Granger predict real oil prices in a two-regime Markov switching vector autoregression (MS-VAR) model. An asset pricing theory motivates the empirical work by showing how jumps in real oil prices approximately follow jumps in the discount factor to keep constant the competitive return to oil capital. Using monthly data from January 1978 to June 2024, we consider alternative data combinations of US money supply growth rates, US inflation rates, and real oil prices to establish volatility regimes through goodness of fit testing. We set baseline model as that model with the highest likelihood in explaining the real oil price, which combines M2, the CPI less energy prices (CPIE), and real oil prices. Robustness considers two M2 variants combined with the CPIE that have the next highest likelihoods, for two alternative models. In the high volatility regime, results show robust Granger predictability of real oil prices by the baseline M2 and the M2 variants. In the low volatility regime for the baseline model, the CPIE inflation rate Granger predicts real oil prices. The paper contributes these new MS-VAR results that combined with the theory provide nuanced non-conventional support that monetary factors contribute to heightened real oil price episodes in volatile times as well as in calmer periods.

Interactions between sustainable bonds, renewable energy and other financial markets: A macroprudential perspective

We analyse linkages between sustainable bond markets and a number of key financial markets in Europe, namely corporate bond, sovereign bond, renewable energy, equity and volatility markets. We apply a novel empirical approach using zero-volatility spreads (z-spreads) as a measure of relative bond performance to adjust for the sensitivity of bond prices to changes in interest rates. We model these linkages using a Markov-switching vector autoregressive model and static and dynamic copulas that enable us to test for contagion with conditional value-at-risk measures. We find evidence of bi-directional contagion between the sustainability-linked bond and green bond markets along with contagion between other fixed-income markets and the sustainable bond market. Our results indicate possible diversification benefits that green bonds or sustainability-linked bonds may provide to investors active in the key markets analysed.

Transmission of Inflation and Exchange Rate Effects: The Markov Switching Vector Autoregressive Methodology

The aim of this study is to delve into the intricate the mechanism through which alterations in currency exchange rates give rise to shifts in inflation rates, while taking into careful consideration the country’s economic cycle. In order to accomplish this objective, we used a dataset that spanned from 1 January 1999 to 1 July 2023, focusing our analytical lens on three specific geographic areas, namely the Eurozone, the United Kingdom, and Canada. In our pursuit of understanding this complex relationship, we employed the Markov Switching Vector Autoregressive model. Our research outcomes can be succinctly encapsulated as follows: in the initial stages, particularly during phases characterized by robust economic growth, the transmission of exchange rate effects onto inflation levels appeared to exhibit a partial impact across all geographic areas under examination. However, during periods marked by economic downturns, both the United Kingdom and Canada displayed a distinctly more comprehensive transmission of these effects. Moreover, the prevailing projections for the forthcoming time horizon, across all the countries encompassed by our study, strongly indicate the onset of an expansionary phase that is projected to extend over a span of 25 months. Lastly, concerning the implications of unexpected disturbances or shocks, it is noteworthy that the response of exchange rates to inflation induced shocks was neither immediate nor as pronounced as the corresponding reaction of inflation to sudden shifts in exchange rates.

Determinants of Monetary Policy: An Application of Regime Switching Model

The monetary policy of India has undergone substantial changes since 2013, particularly after taper tantrum episodes. The RBI moved from WPI to CPI for measuring inflation. Monetary policy anchoring shifted from a multiple-indicator approach (MIA) to flexible inflation targeting (FIT) in 2016 to deal with the aftermath of the global financial crisis. In this context, the study examined whether there was a significant shift in the monetary policy regime using a non-linear model (Markov Switching-Vector Autoregression Model) covering monthly data from 2013 to 2020. The study also investigated the role of the inflation rate, oil price, growth rate, and exchange rate in influencing monetary policy in India. The study found no change in the RBI monetary policy regime, and monetary policy remained biased towards controlling the inflation rate.

The Asymmetric Effects of Real Estate Uncertainty Shock

In this paper, we explore the asymmetric impact of real estate uncertainty (REU) shock on the U.S. economy and housing market in high- and low-volatility states. To do this, we apply the Markov-switching vector autoregression model. Our empirical results show that the macroeconomic and housing markets react negatively to unexpected uncertainties, and the response to the REU shock is much greater than other housing-related variables in high-volatility states. We confirm the presence of the real-options channel based on the following results: both housing starts and construction employment decrease, and housing inventory increases, especially in low-volatility states. In the short run, we observe a delayed pattern in housing starts and construction employment variables. The effect of the channel is less significant in times of high volatility but confirmed in low volatility. The forecast error variance decomposition results show that the REU shock is greater under high REU volatility and plays a more significant role in explaining most housing-related variables.

Impulse response function analysis for Markov switching var models

We exactly derive the regime-dependent impulse response functions for a Markov switching vector autoregression (VAR) model in terms of neat matrix expressions in closed form. The key is to recognize that the latent first-order Markov switching process in the model has a VAR(1) representation, and that the model can be cast into a state-space form. Using such a representation, the regime-dependent impulse response function analysis can be processed with respect to either an asymmetric discrete shock or to a symmetric continuous shock. Our results extend and correct those obtained by Ehrmann et al. (2003) and coincide with those by Hamilton (1994) for the case of standard VAR models.

Financial stress and commodity price volatility

We use a Markov-switching vector autoregressive model to examine the impact of financial stress on the volatility of commodity prices, including energy volatility. An increase in financial stress leads to a persistent increase in the volatility of the commodity index and of individual commodity prices. We confirm the existence of three volatility regimes, with the volatility of the commodity index and of individual commodity prices in the high volatility regime being more than 25 times larger than that in other regimes. A financial stress shock that arrives during a highly volatile period has more destabilizing and persistent effects than when the shock arrives during a low volatility period. The impact on energy volatility in the high volatility regime is over 60% larger than that on the volatility of the commodity index. The high volatility regime is short-lived and reflects major economic events as well as the outbreak of the COVID-19 pandemic.

Statistical analysis of Markov switching vector autoregression models with endogenous explanatory variables

We consider multivariate Markov switching first-order autoregression models with endogenous explanatory variables, propose a joint estimation algorithm of type EM, written at vector–matrix level, to account for endogeneity, and derive matrix formulas for the ML estimators of model parameters. Then we prove the consistency of such estimators, provide matrix expressions for their asymptotic covariances, and present some tests for endogeneity. Further, a simulation study is proposed to illustrate the theoretical results and provide evidence on the usefulness of the considered model.

The Regime Changing Behavior of Exchange Rates and Stock Market Prices of Selected Emerging Countries: An application of the Markov Switching Vector Autoregressive model (MS-VAR)

This article aims to analyze the dynamic relationship between stock market returns and exchange rate movements for emerging countries (Brazil, Argentina, Mexico and India), from January 2005 to December 2021, using Markov Switching Vector Autoregressive model, with regime change. The impact of exchange rate movements on stock returns is not statistically significant in all emerging countries. This reveals that fluctuations in US dollar exchange rates do not have a strong influence on the dynamics of stock market returns during normal and turbulent periods. On the other hand, the impacts of stock returns on exchange rate movements are significant only for the Brazilian and Mexican markets.

Modeling and estimation of synchronization in size-sorted portfolio returns

This paper examines the lead/lag relations between size-sorted portfolio returns through the lens of financial cycles governing these returns using a novel econometric methodology. Specifically, we develop a Markov-switching vector autoregressive model that allows for imperfect synchronization of cyclical regimes such as bull and bear market regimes in US large-, mid- and small-cap portfolio returns. This is achieved by characterizing the cycles of the mid- and small-cap portfolio returns in concordance with the cycle of large-cap portfolio returns together with potential phase shifts. We find that a three-regime model with distinct phase shifts across regimes characterizes the joint distribution of returns most adequately. These regimes are closely linked to the business cycle and small-cap portfolio returns are more sensitive to the cyclical phases than the large-cap portfolios. While all portfolios switch contemporaneously into boom and crash regimes, the large-cap portfolio leads the small-cap portfolio for switches to a moderate regime from a boom regime by a month. This suggests that small-cap portfolio adjusts with a delay to the relatively negative news compared to portfolios with larger market capitalization. We document that information diffusion accelerates in response to surprises related to the monetary policy. This reflects a link between financial returns and real economic activity from the viewpoint of ‘financial accelerator theory’ where portfolios with distinct size serve as a proxy for firm characteristics.

Stock and exchange rate movements in the MENA countries: A Markov Switching –VAR Model

Purpose ― This article explores the causal link between stock and currency returns in The Middle Eastern and North African (MENA) countries from January 2011 through February 2020. Methods ― This study uses the Vector autoregressive (VAR) and the Markov switching vector autoregressive (MS-VAR) models to investigate the dynamic causality between equity and exchange rate markets. Findings ― Results indicate that this relation depends on the state of the markets. Furthermore, generally, equity returns have a significant impact on the currency markets, whatever the market state. Implication ― Regime shifts in the relationship between stock and exchange rate markets are significant for portfolio allocation because they help investors improve their investment decisions through knowledge of the dynamic link between these markets. Originality ― This study adds to the literature on the relationship between exchange rates and stock prices in the MENA countries, which have become attractive destinations for international investors due to their higher returns.

ESG Green Equity Finance Risk and Links in Mexico: Conditional Volatility and Markov Switching Vector Analyses

We analyze the differential influence of Mexican oil price, exchange rate and S&P 500 Index on the Mexican Stock Exchange: S&P/BMV IPC ESG Tilted Index (sustainable stock market index), and on the S&P/BMV IPC (General stock market index) in two different regimes. First, we estimate the conditional volatility of the series using a univariate GARCH model under the t-Student distribution. Second, a Markov Switching Vector Autoregressive model is developed. The evidence identifies sustainable asset performance, risk, and interaction with other regular assets. The sustainable index is more vulnerable to the foreign exchange market and to the U.S. stock market, especially in periods of turbulence. Only the S&P 500 shows a statistically significant impact on the overall Mexican index, for both states high and low volatility. Oil prices do not have a significant impact on the Mexican indices analyzed. Evidence allows us to recommend a currency hedging in ESG investments. Originality relies on empirical approaches and the study of ESG index in an emerging market. Limitations are related with the scarce information and limited access to ESG factors data. We conclude that investment strategies should be different during calm and turmoil periods.

On stylized facts of cryptocurrencies returns and their relationship with other assets, with a focus on the impact of COVID-19

ABSTRACT This study provides an empirical analysis on the main univariate and multivariate stylized facts iin return series of the two of the largest cryptocurrencies, namely Ethereum and Bitcoin. A Markov-Switching Vector AutoRegression model is considered to further explore the dynamic relationships between cryptocurrencies and other financial assets. We estimate the presence of volatility clustering, a rapid decay of the autocorrelation function, an excess of kurtosis and multivariate little cross-correlation across the series, except for contemporaneous returns. The analysis covers the pandemic period and sheds lights on the behaviour of cryptocurrencies under unexpected extreme events.

An ocean apart? The effects of US business cycles on Chinese business cycles

This study investigates the economic interdependence between China and the United States. In view of the growing trade and investment between China and the United States, and the reaction of the Chinese economy to the US subprime mortgage crisis, one might reasonably ask, what effect do US business cycles have upon the Chinese economy? We approach this problem by examining various channels of economic interaction, including international trade and foreign direct investment between the two countries. We use regressions, the Markov switching vector autoregressive model, and recursive correlations in an attempt to measure business cycle transmission from the United States to China using annual, quarterly, and monthly data.With both annual and quarterly GDP growth data between 1951 and 2001, business cycles in China and the US are not correlated. Starting in 1978, China undertook significant economic reforms and opened up to the rest of the world. After 1992, trade between the US and China increased, and US firms began to engage in FDI in China. After China's accession to the WTO in 2001, trade accelerated, and the correlation between the GDP growth rates of the US and China increased dramatically. There is evidence that the US has some marginally significant but increasing business cycle transmission effects upon China. Recursive correlations reveal that the synchronization between the two countries is strongest during economic downturns, suggesting that economic downturns and crises are responsible for most of the business cycle synchronization.

Effects of economic policy uncertainty: A regime switching connectedness approach

This paper investigates the impact of economic policy uncertainty (EPU) in the US and China on international financial markets across different states. Although earlier studies have examined the interactions between EPUs and financial markets, few considered the issue from the state-dependence perspective. To fill this gap, we extend the Diebold and Yilmaz connectedness to the two-state Markov Switching Vector Autoregressive model to conduct the empirical analysis. Empirical results indicate connectedness is larger (smaller) in the high (low) volatility state than in the single-state model. Moreover, the two EPUs play distinct roles at different time scales. On the weekly time scale, EPUs are influenced by the financial markets only in the low volatility state while the China EPU becomes a net information sender in the high volatility state. Our findings imply that more attention should be devoted to the possible negative impact of China EPU.

Key factors affecting carbon prices from a time-varying perspective.

For humankind to sustain a livable atmosphere on the planet, many countries have committed to achieving carbon neutralization. Countries mainly reduce carbon emissions by regulations through a carbon tax or by establishing a carbon market using economic stimuli. In this paper, we use the least absolute shrinkage and selection operator (LASSO) method to select the key determinants of a carbon market and then use the Markov switching vector autoregression (MSVAR) model to study the market’s driving factors and analyze its time-varying characteristics. The results show that there are perceptible time-varying characteristics and notable differences among markets. During COVID-19, energy factors had a long-term shock on the carbon market, economic factors had a short-term shock on the carbon market, and the economic recession has led to fluctuations in the carbon market. In addition, through MSVAR, the results show that the energy market has a negative effect on the carbon market, and the stock market has a positive effect on the carbon market. In periods of low volatility, compared with the natural gas market and coal market, the oil market has a stronger shock on the carbon market. In periods of high volatility, the coal market has a stronger shock on the carbon market. In terms of emission reduction, countries around the world would be wise to change their energy consumption structure, reduce coal use, and shift to a cleaner energy consumption structure.

Quantifying nonlinear effects of BRIC and G4 liquidity on oil prices

Research on oil prices has concentrated on demand and supply factors and has largely underestimated the importance of the financialization of commodities. To assess the impact of financial factors on oil prices, this article investigates the liquidity of Brazil, Russia, India, and China (BRIC) and that of a group of four developed economies (G4) consisting of the Eurozone, Japan, the United Kingdom, and the United States. An application of the single-state vector autoregressive (VAR) model to monthly data from the 1999–2020 sample period reveals that a positive shock to the liquidity of the BRIC countries leads to significant increases in real oil prices. These novel findings stem from a consideration of Markov-switching vector autoregressive (MSVAR) models, which shows that an unanticipated increase in the G4 liquidity is positively linked with real oil prices. The main findings are as follows. (1) We identify three regimes that are associated with the volatility of real oil prices and the liquidity measure, including a crisis regime that characterizes the subprime crisis and the COVID-19 pandemic. (2) Impulse response function analyses show that the impact of G4 liquidity under the crisis regime is almost twice as large as that during normal periods, while the impact of BRIC liquidity during such a crisis period is almost three times larger. (3) A shock to BRIC liquidity has a greater impact on real oil prices than a shock to the liquidity of the G4 economies. This analysis helps in assessing the importance of BRIC and G4 liquidity in relation to upsurges in the real oil prices.

Study on the nonlinear interactions among the international oil price, the RMB exchange rate and China's gold price

To investigate the nonlinear interactions among the international oil price, the RMB exchange rate and China's gold price, we construct a Markov-switching vector autoregression (MS-VAR) model that contains the three aforementioned variables and conduct an empirical study with monthly data from July 2005 to December 2017. The results verify that the nonlinear interactions exhibit regime switching, which can be precisely represented using three regime states. A significant momentum effect exists between the international oil price and the RMB exchange rate. China's gold price is mainly affected by international factors, such as the international oil price, while the influence of the RMB exchange rate on China's gold price is limited. Additionally, the dynamic interactions among the three variables vary in different regimes and have obvious asymmetric effects.

Detection of structural regimes and analyzing the impact of crude oil market on Canadian stock market: Markov regime-switching approach

PurposeThis study aims to analyze the impact of the crude oil market on the Toronto Stock Exchange Index (TSX).Design/methodology/approachThe focus is on detecting nonlinear relationship based on monthly data from 1970 to 2021 using Markov-switching vector auto regression (VAR) model.FindingsThe results indicate that TSX return contains two regimes: positive return (Regime 1), when growth rate of stock index is positive; and negative return (Regime 2), when growth rate of stock index is negative. Moreover, Regime 1 is more volatile than Regime 2. The findings also show the crude oil market has a negative effect on the stock market in Regime 1, while it has a positive effect on the stock market in Regime 2. In addition, the authors can see this effect in Regime 1 more significantly in comparison to Regime 2. Furthermore, two-period lag of oil price decreases stock return in Regime 1, while it increases stock return in Regime 2.Originality/valueThis study aims to address the effect of oil market fluctuation on TSX index using Markov-switching approach and capture the nonlinearities between them. To the best of the author’s knowledge, this is the first study to assess the effect of the oil market on TSX in different regimes using Markov-switching VAR model. Because Canada is the sixth-largest producer and exporter of oil in the world as well as the TSX as the Canada’s main stock exchange is the tenth-largest stock exchange in the world by market capitalization, this paper’s framework to analyze a nonlinear relationship between oil market and the stock market of Canada helps stock market players like policymakers, institutional investors and private investors to get a better understanding of the real world.

Renewable energy and economic growth: A Markov-switching approach

This paper examines the dynamic causal relationship between renewable energy prices and economic growth in the cases of Norway, New Zealand, and two Canadian provinces. A Markov-switching vector autoregression (MS-VAR) model is used with model parameters being governed by a hidden Markov chain, allowing the causal relationship to vary amongst different states of the economy. A unidirectional causal link, running from economic growth to renewable energy is found in the case of New Zealand, Alberta, and Ontario. The causality emerges in the cases of New Zealand and Ontario, during periods of high economic growth, whilst it materializes in the cases of Alberta during periods of low economic growth. Our empirical results document the existence of a time-dependent causal relationship between renewable-energy prices and economic growth.