Markov-switching VAR Research Articles

Dynamic Linkages between Stock Market and Exchange Rate in mila Countries: A Markov Regime Switching Approach (2003-2016)

This paper aims to analyse the dynamic relationship between the stock market returns and exchange rates movements for the mila (Mercado Integrado Latinoamericano) countries: Colombia, Chile, Mexico and Peru, over the period 01:2003 to 09:2016. Univariate (Markov Switching-Autoregressive) and multivariate (Markov Switching-Vector Autoregressive) regime-switching models approach are used. The univariate analysis offers evidence indicating that stock returns of the mila countries evolve according to two different regimes: a low volatility regime and a high volatility regime. The Markov Switching Vector Autoregressive models point out that stock markets have more influence on exchange rate than exchange rate has on stock markets. Results for the Peruvian and Chilean markets contribute evidence about contagion between the stock and the exchange rate markets. JEL Code: G15; C58; F31; D53

Nonlinear effects of financial factors on fluctuations in nonferrous metals prices: A Markov-switching VAR analysis

Because of the irreversibility of financialization in nonferrous metals markets, the security of nonferrous metals resources has shifted from a supply security mode based on “production-supply” towards an economic security mode based on “trade-finance”. Thus, the pricing mechanism of nonferrous metals has become more complex and presents features such as nonlinearity, dynamic characteristics and structure dissimilation. Based on this background, we construct a theoretical framework for analysing the effects of financial factors on fluctuations in nonferrous metals prices and employ the Markov-switching vector autoregression (MS-VAR) model to conduct a nonlinear empirical analysis based on monthly data of international copper futures prices from August 2004 to October 2016. Further, we include supply and demand factors for a comparative analysis. The results show that copper futures price fluctuations present a regime switching dynamic that can be characterized as “steep drop”, “small drop” and “steady rise” periods. During each period, financial factors can fully explain the price volatility while in different mechanism, and the “Chinese factor” has apparently been exaggerated. In addition, oil price is key to monitoring the short-term volatility risks of copper futures prices in the downward cycle. The conclusions along with the established nonlinear econometric models provide a new intellectual framework and analysis tool for explaining the financialization of commodity markets.

Understanding the US Natural Gas Market: A Markov Switching VAR Approach

Over the past three decades, the US natural gas market has witnessed significant changes. Utilizing a standard Bayesian model comparison method, this paper formally determines four regimes existing in the market. It then employs a Markov switching vector autoregressive model to investigate the regime-dependent responses of the market to its fundamental shocks. The results reveal that the US natural gas market tends to be much more sensitive to shocks occurring in regimes existing after the Decontrol Act 1989 than the other regimes. The paper also finds that shocks to the natural gas demand and price have negligible effects on natural gas production while the price of natural gas is mainly driven by specific demand shocks. Augmenting the model by incorporating the price of crude oil, the results show that the impacts of oil price shocks on natural gas prices are relatively small and regime-dependent.

Interest rate pass through in a Markov-switching Vector Autoregression model: Evidence from Greek retail bank interest rates

In this paper, we investigate the relationship between Euro Overnight Index Average interest rate (EONIA) and retail Greek bank interest rates in a Markov-switching Vector Autoregression model. Monthly data is used for household and corporate deposit and credit rates since 1999. Two regimes are defined based on high and low interest rate volatility. A separate set of impulse responses for each Markov regime are drawn in order to identify any differences in the retail rates transmission. The results prove that banks in order to assure their resources for a longer term during high variance periods increase significantly their deposit rate after an interbank rate positive shock. They also present a preference to corporations over households. The duration of the responses for deposit rates over the turbulence periods of high volatility show the vital role of Greek deposits on funding of Greek banks.

Economic dynamics during periods of financial stress: Evidences from Brazil

This paper investigates the differences in macroeconomic dynamics that occurred during instabilities in the Brazilian financial market from 2000 to 2015. In this regard, we introduced the Brazil Financial Stress Index as a proxy for financial stress, and investigated its interaction with real activity, inflation and monetary policy using a Markov-switching VAR model. We could verify distinct economic reactions during stressful periods. Furthermore, our results demonstrate that appropriate policies for some countries in normal times, such as an expansionary monetary policy, can worsen the scenario in an adverse situation, indicating that a government might deepen a financial crisis if policy-makers implements a policy used successfully during a regime that is economically and behaviorally dissimilar from tense states.

Cyclical Variation in the Government Spending Multipliers: A Markov-switching SVAR Approach

We explore a century-long dataset with a Markov-switching structural VAR to estimate state-dependent government spending multipliers. We show that the multiplier values are statistically larger during recessions than during expansions. However, the multipliers are always smaller than 1. Our model has two features. First, we combine quantitative data and qualitative indicators to infer the regimes of the economy across which the multipliers differ. Second, we propose a simple method to estimate impulse response functions that allows for regime changes after the shock. We argue that these two features are important for reconciling the main findings in previous studies.

Regime-Dependent Effect of Crude Oil Price on BRICS Stock Markets

ABSTRACTIn this study, the dynamic relation between global crude oil prices and stock prices is investigated in terms of crude oil-exporting and -importing countries. The relationship between crude oil prices and stock prices is examined for BRICS countries (Brazil, Russia, India, China, and South Africa) for the periods of January 1995 to December 2016 by means of the Markov Switching Vector Autoregression (MS-VAR) model. The impulse-response analysis results suggest that the responses of the stock market to an oil price shock vary over the regimes for all countries. Specifically, we find that the responses of the stock market to an unexpected oil price shock are positive and statistically significant in the high-volatility regime in all countries except for China, and these results suggest that the increase in oil prices may be evaluated by demand-side shock in these countries.

The effects of oil prices on confidence and stock return in China, India and Russia

This study aims to investigate the relationships between oil price, business confidence and stock return for China, India and Russia by employing the Markov Switching Vector Auto Regressive(MS-VAR) and MS-Granger Causality(MS-GC) methods. For China, the causality relationship between business confidence and stock return differ from the results of Russia and India. For China, while there is unidirectional causality from stock return to business confidence for all regimes, in India there is the evidence of bidirectional causality in all regimes. For Russia, there is the evidence of a bidirectional causality between business confidence and stock return in the first regime, while there is none causality in the second regime. In all regimes for the selected countries, there is the evidence of a unidirectional causality from oil price to stock return. But there are different results between oil price and business confidence. The different results obtained for the selected countries are explained by the three different factors. One of the reasons is that the differences in oil reserves of the countries. The other one is the differences in oil demand of the countries' economies. The last one is that the selected countries have different business confidence that can be affected by various parameters of the economy.

A comparison of methodologies in the stress testing of credit risk – alternative scenario and dependency constructs

In the aftermath of the financial crisis of the last decade, banking supervisors have sought the solution to the problem of determining the optimal capital levels that an institution should hold, in order to support their risk taking activities. The experience of this financial downturn has given rise to the conclusion that traditional approaches, such as regulatory or economic capital are inadequate to this end, leading to the prevalence of supervisory stress testing as a primary tool of prudential supervision. A critical input into this process is the set of macroeconomic scenarios, either provided by the prudential supervisors, or developed by financial institutions. Prevalent among approaches in the industry is the combination of expert opinion and an econometric methodology, for example the Vector Autoregression (VAR) model that captures the dependency structure among and between macroeconomic explanatory variables and banking loss / income target variables. Despite the prevalence of this approach, we know from the previous finance literature that Gaussian VAR models are unable to cope with the empirical fact of deviation from normality. In this paper we investigate the alternative Markov Switching VAR (MS-VAR) model, featured more commonly in the academic realm as opposed to being applied in practice. We conduct an empirical experiment using data from regulatory filings and Federal Reserve macroeconomic data released by the regulators for mandated stress testing exercises. Our finding is that the MS-VAR model performs better than the VAR model, both in terms of producing severe scenarios conservative than the VAR model, as well as showing superior predictive accuracy. Furthermore, we find that the multiple equation VAR model outperforms the single equation autoregressive (AR) models according to various metrics across all modeling segments.

An analysis of diversification benefits of commodity futures using Markov regime-switching approach

This study investigates the hedge and safe haven properties of individual commodity futures against stock market movements using a nonlinear regime-switching framework. Based on the results of Brock, Dechert and Scheinkman (BDS) test and information selection criterion, Markov-switching vector auto-regression (MS-VAR) model is applied with three regimes for gold and silver futures and with two regimes for crude oil, copper and zinc futures. The results demonstrate strong hedge and weak safe haven property of gold and silver futures, while it shows a weak hedge and weak safe haven potential of copper and zinc futures. Conversely, crude oil futures cannot be used as a safe haven against extreme stock market movements. In addition, portfolio analysis confirms that these findings provide significant information to investors for the construction of better risk-adjusted return portfolio.

Stability Measurement of Dual Banking System in Indonesia: Markov Switching Approach

Various macro and microeconomic shocks that occur during this time suggest the potential for financial instability. This study attempts to analyze the influence of macro and microeconomic variables of the dual banking stability in Indonesia and compares the stability level of both banking system by using two similar stability measurement models namely the Z-score and Banking Stability Index. The method used in this is a Markov Switching VAR. The results of this study described through two analyze: First, the calculation index of financial stability with Z-score and BSI. Second, results of Markov-Switching prove that the sharia banking system has a higher level of stability compared to the conventional banking system. It means sharia banking is more stable than conventional ones. DOI: 10.15408/aiq.v10i1.5867

Interaction of Housing Market and Stock Market in the U.S. - A Markov Switching Model Analysis

This paper uses the Markov Switching VAR model to examine the dynamics relationships between stock returns and housing returns in the US covering the periods from 1987 to 2017. The results show significant regime-dependent auto-correlations in stock and housing returns in both the high volatility and the low volatility regimes. The feedback effects are stronger in than housing markets than the stock markets. We observe significant positive cross-market spillovers, which are consistent with the wealth story. Increases in stock return in the low volatility regime create positive spillover effects into housing markets; and likewise, the positive spillovers in the reverse direction from housing market to the stock market occur in the high volatility regime. We also find significant negative correlations between the lagged stock returns and the current housing returns in the high volatility regime, which imply that capital switching occur where investors move their investments out of the housing market into the stock market.

Regime-dependent relation between Islamic and conventional financial markets

The aim of this paper is to examine regime-dependent dynamic relation between Islamic and conventional financial markets by means of Markov Switching Vector Autoregression (MS-VAR). Empirical results suggest evidence in favor of regime-switching properties in all returns series. These findings provide strong evidence in favor of nonlinear relation between the conventional and Islamic stock markets and thus, it is necessary to employ the MS-VAR models to determine the dynamic relationship between series. The regime-dependent Granger causality test and impulse-responses analysis results suggest that Islamic stock market is affected from conventional stock markets in both the bear and bull markets regimes. Therefore, the idea that Islamic financial markets provide diversification benefits and they are safe havens during financial distressed periods cannot be supported empirically.

Inflation and Output Growth Dynamics in South Africa: Evidence from the Markov Switching Vector Autoregressive Model

ABSTRACTThis paper introduces the possibility of asymmetry in the reaction of output growth to inflation shocks in South Africa by making use of the Markov-switching vector autoregressive model. Using quarterly data from 1969Q1 to 2013Q4, the empirical finding suggests that the reaction of output growth to inflation shocks is not only regime dependent but is also contingent on how the monetary authority reacts to such shocks. Two important regimes are identified; the high and low inflation volatility regimes. Consistent with the signal extraction theory, the output effect of inflation shocks is found to be significantly lower in the high inflation volatility regime compared to the low inflation regime.

The Impact of Oil Price on South African GDP Growth: A Bayesian Markov Switching‐VAR Analysis

AbstractOne characteristic of many macroeconomic and financial time series is their asymmetric behaviour during different phases of a business cycle. Oil price shocks have been amongst those economic variables that have been identified in theoretical and empirical literature to predict phases of business cycles. However, the role of oil price shocks to determine business cycle fluctuations has received less attention in emerging and developing economies. The aim of this study is to investigate the role of oil price shocks in predicting phases of the South African business cycle associated with higher and lower growth regimes. By adopting a regime dependent analysis, we investigate the impact of oil price shocks under two phases of the business cycle, namely high and low growth regimes. As a net importer of oil, South Africa is expected to be vulnerable to oil price shocks irrespective of the phase of the business cycle. Using a Bayesian Markov switching vector autoregressive (MS‐VAR) model and data for the period 1960Q2 to 2013Q3, we found the oil price to have predictive content for real output growth under the low growth regime. The results also show the low growth state to be shorter‐lived compared to the higher growth state.

Macroeconomic Switching Regimes and Monetary Policy in Canada

This study examines the behaviour of monetary policy in Canada over the last 40 years using a Markov-switching VAR model of the macroeconomy. The Markov-switching estimates capture three continuous regimes that are interpreted as the ‘surprise’ regime from 1972Q1 to 1982Q2, the ‘recovery’ regime from 1982Q3 to 1991Q3 and the ‘target’ regime from 1991Q4 to 2014Q4. Monetary policy multipliers for the output gap are greater than one for all three regimes, suggesting that the central bank does not accommodate any expected changes in inflation over the long-run due to the domestic relationship between the output gap and future inflation. The long-run multipliers for inflation are equal to one in the surprise and recovery regimes, indicating that monetary policy also responds to offset inflation shocks. Overall, the policy multipliers and impulse response functions indicate a proactive central bank that responds systematically to movements in the output gap in order to control expected future inflation and to inflation surprises in the three regimes. The regime-dependent behaviour of monetary policy indicates a central bank pursuing an implicit form of inflation targeting as a means of achieving a nominal anchor for policy. The implicit inflation tar­gets are consistent with historical episodes of inflation in Canada over the past 40 years.

Forecasting US interest rates and business cycle with a nonlinear regime switching VAR model

AbstractThis paper introduces a regime switching vector autoregressive model with time‐varying regime probabilities, where the regime switching dynamics is described by an observable binary response variable predicted simultaneously with the variables subject to regime changes. Dependence on the observed binary variable distinguishes the model from various previously proposed multivariate regime switching models, facilitating a handy simulation‐based multistep forecasting method. An empirical application shows a strong bidirectional predictive linkage between US interest rates and NBER business cycle recession and expansion periods. Due to the predictability of the business cycle regimes, the proposed model yields superior out‐of‐sample forecasts of the US short‐term interest rate and the term spread compared with the linear and nonlinear vector autoregressive (VAR) models, including the Markov switching VAR model.

How Indian CPI and Industrial Production Respond to Global Oil Price Shocks? Regime-Dependent Impulse Responses

For emerging markets like India, where around 80 percent of the crude requirements are met through imports, it is an imperative task to comprehend impact of global crude oil price shocks on Indian macroeconomic variables. The present study attempts to understand these asymmetric dynamic interactions between global crude oil price shocks and Indian macroeconomic variables by employing Markov switching-Vector Autoregressive (MS-VAR) regime-dependent impulse responses in level forms. The findings hold an important place in the wake of inflation targeting regime adopted by the monetary policy authorities. The findings highlight the existence of two regimes, namely lower and higher oil price variance regimes. The response of industrial production and consumer prices is different towards oil price shocks in different regimes. In the lower oil variance regime, there is negative (positive) relationship observed between crude oil shocks and industrial production (consumer prices). On the other hand, there is a positive equilibrium shift in the industrial production in the higher oil variance regime with cost pushing inflationary pressures in the long run. The findings bear strong implication for the policy makers in their attempt to combat effects of crude oil shocks. As per the findings, the emerging market policy makers should display a cautious approach during higher oil price volatile phases in order to support industrial production and consumer demand.

Testing the dependency theory on small island economies: The case of Cyprus

This paper empirically tests the validity of dependency theory in the small island setting of Cyprus, to establish whether a periphery/patron relationship exists between each of the island's two economies and their respective mainland partners of Greece and Turkey. Using data for the 1978–2013 period, we first test for the necessary condition, i.e. whether there is a long-run cointegrating relationship in the economic development of the Republic of Cyprus (RC) and Greece, and the Turkish Republic of Northern Cyprus (TRNC) and Turkey. We then test for the sufficient condition, i.e. whether periphery-economy per capita income series to be weakly endogenous, while those of patron economies are weakly exogenous. Our results indicate strong dependency within the periphery/patron economy pairs of the RC/Greece and the TRNC/Turkey. Further, we show that economic growth in the periphery economies is largely driven by that of the patron economies. Using a Markov-switching vector autoregressive (MS-VAR) model of the short-run business cycle, we demonstrate that the RC/Greece and the TRNC/Turkey co-move in the short-run, and that business cycles with each pair are synchronized. The policy implications of these findings are then discussed.

Outbound Tourism Demand of Turkey: A Markov Switching Vector Autoregressive Approach

Abstract Tourism has been one of the fastest-growing sectors in the world. Especially developed countries have been major markets for tourism destinations over the decades. Furthermore, the outbound tourism demand in emerging markets has increased rapidly in recent years. This study aims to investigate the determinants of Turkey’s outbound tourism demand by using the data from 1960 to 2013. For this purpose, the Markov Switching Vector Autoregressive Model is used as an empirical analysis. This model classifies the time period into different regimes in order to obtain more robust results. Finally, our findings show that Turkish citizens’ outbound visits have been influenced by income and the exchange rates.