Time-varying Transition Probabilities Research Articles

Bayesian inference in non-homogeneous Markov mixtures of periodic autoregressions with state-dependent exogenous variables

The Bayesian analysis of a non-homogeneous Markov mixture of periodic autoregressions with state-dependent exogenous variables is proposed to investigate a non-linear and non-Normal time series. It is performed within a Markov chain Monte Carlo framework, along four consecutive steps: the specification of the identifiability constraint; the selection of the exogenous variables which influence the observed process and the time-varying transition probabilities of the hidden Markov chain; the choice of the cardinality of the hidden Markov chain state-space and the autoregressive order; the estimation of the parameters. The selection of the exogenous variables is performed in the complex case of correlation between variables, by means of a new procedure. An application for relating the hourly mean concentrations of sulphur dioxide with six meteorological variables, recorded for three years by an air pollution testing station located in the lagoon of Venice (Italy), is presented. The reconstruction of the sequence of the hidden states, the restoration of the missing values occurring within the observed series, the description of the periodic component are also given.

Long memory with Markov-Switching GARCH

Abstract The paper considers the Markov-Switching GARCH(1,1)-model with time-varying transition probabilities. It derives sufficient conditions for the square of the process to display long memory and provides some additional intuition for the empirical observation that estimated GARCH-parameters often sum to almost one.

Evaluating currency crises: the case of the European monetary system

In this paper we examine the nature of currency crises. We ascertain whether the currency crises of the European Monetary System (EMS) were based either on fundamentals, or on self-fulfilling market expectations driven by extrinsic uncertainty. In particular, we extend previous work of Jeanne and Masson (J Int Econ 50:327–350, 2000) regarding the evaluation of currency crisis. We contribute to the existing literature proposing the use of Markov regime-switching with time-varying transition probability model. Our empirical results suggest that the currency crises of the EMS were not due only to market expectations driven by external uncertainty, or ‘sunspots’, but also to fundamental variables that help to explain the behavior of market expectations.

Modeling the Euro overnight rate

This paper describes the evolution of the daily Euro overnight interestrate (EONIA) by using several models containing the jump component such asa single regime ARCH-Poisson-Gaussian process, with either a piecewisefunction or an autoregressive conditional specification (ARJI) for the jumpintensity, and a two regime-switching process with jumps and time varyingtransition probabilities. To model the jump intensity, we include the followingeffects which are significant for the occurrence of jumps such as: (1) the end ofmaintenance period effect because of reserve requirements, (2) the end ofmonth effect, also known as the calendar day effect, caused mainly by theaccounting adjustments and finally, (3) the meeting effect caused by thefortnightly meetings of the Governing Council of the European Central Bank(ECB). These effects lead to a better performance and several of them are alsoincluded for the behavior of the transition probabilities. Since the target of theECB is keeping the EONIA rate close to the official rate, we have modeled theconditional mean of the overnight rate series as a reversion process to theofficial rate distinguishing two alternative speeds of reversion, in concrete, adifferent speed if EONIA is higher or lower than the official rate. We also studythe jumps of the EONIA rate around the ECB?s meetings by using the ex-postprobabilities of the ARJI model. Finally, we develop an out-of-sampleforecasting analysis to measure the performance of the different candidatemodels

The asymmetric information and price manipulation in stock market

The interaction between asymmetrically informed traders has been mostly investigated in theoretical frameworks. Not only there are relatively few empirical studies but, if any, the mostly focus on cross-sectional analysis and use very short samples. In this study, we blend theoretic with empirical, and propose a new signalling system of turning points in the economy to examine the extent of volatility of these markets relative to their tranquil periods. The signalling system proposed here is based on the Markov-switching model. Differing from the existing literatures, the study employs three phases and time-varying transition probability, and captures the states of volatility. After examining the causality between high volatility and foreign portfolio investment (FPI) by using moving average and generalized autoregressive conditional heteroskedasticity, the portfolio's profitability of FPI and individual investors in different periods are compared. Finally, the investigation of FPI's leading effect is studied.

Colombian Economic Growth Under Markov Switching Regimes with Endogenous Transition Probabilities

In this paper, we modelled the Colombian long run per capita economic growth (1925-2005) using a Markov switching regime model with both fixed (FTP) and time-varying transition probabilities (TVTP) to explain regime changes in the economic growth. We found evidence of non-linearity in the per capita economic growth, and two different levels in the data associated with depression and sustainable growth regimes were identified. In addition, the hypothesis of fixed probabilities is rejected in favour of the time-varying transitional probabilities, meaning that the correct model is the one with endogenous probabilities, when the probability of remaining in the sustainable growth regime increases with a rise in terms of trade, government expenditures and decreases with capital outflows. On the other hand, increases in government expenditures and terms of trade decrease the probability of being in the depression state while an increase in capital outflows raises such probability. Finally, we found that TVTP model gives more information than FTP model because the probabilities have changed significantly during the period under analysis and the explanatory variables are very informative in dating the evolution of the state of the economy, especially those associated with external shocks.

The term structure of interest rates under regime shifts and jumps

This paper develops a tractable dynamic term structure models under jump-diffusion and regime shifts with time varying transition probabilities. The model allows for regime-dependent jumps while both jump risk and regime-switching risk are priced. Closed form solution for the term structure is obtained for an affine-type model under log-linear approximations.

Bayesian analysis of non-homogeneous hidden Markov models

Bayesian estimation of the unknown parameters of a non-homogeneous Gaussian hidden Markov model is described here. The hidden Markov chain presents time-varying transition probabilities, depending on exogenous variables through a logistic function. Bayesian model choice is also proposed to select the unknown number of states of the hidden non-homogeneous Markov chain. Both the analyses are developed by using Markov chain Monte Carlo algorithms. Model selection and parameter estimation are performed after making the model identifiable, by selecting suitable constraints through a data-driven procedure. The methodology is illustrated by an empirical analysis of ozone data.

Duration dependence of the business cycle in Japan: A Bayesian analysis of extended Markov switching model

For the purpose of analyzing cyclical stochastic processes in business cycles, we propose a regime-switching model with duration dependence that makes use of the Weibull model. The advantage of this model is that it relaxes a constraint of the Markov-switching model in favor of time-varying transition probabilities, and investigates the property of duration dependence in business states. We employ Bayesian inference via MCMC to overcome the drawbacks of maximum likelihood estimation. Estimation using the composite index of coincident indicator shows that both the contractions and the expansions of the Japanese business cycle exhibited positive duration dependence during the last two decades.

Revisiting the interest rate–exchange rate nexus: a Markov-switching approach

In this paper the interest rate–exchange rate nexus and the effectiveness of an interest rate defense are investigated empirically. I present a reduced form evidence which characterizes the empirical relationship between interest rates and exchange rates. I use a Markov-switching specification of the nominal exchange rate with time-varying transition probabilities. Empirical evidence from six developing countries: Indonesia, South Korea, the Philippines, Thailand, Mexico, and Turkey indicates that raising nominal interest rates leads to a higher probability of switching to a crisis regime. Thus, the empirical results presented here may support the view that a high interest rate policy is unable to defend the exchange rate. Unlike other studies which consider linear models only, my findings are robust and consistent over different countries and crisis episodes (Asian 1997 crises, Mexico 1994 crisis, and Turkey 1994, 2001 crises). In order to explain the empirical findings, I construct a simple theoretical model by incorporating an interest rate rule in the model proposed by Jeanne and Rose (2002) [Jeanne, O., Rose, A.K., 2002. Noise trading and exchange rate regimes, Quarterly Journal of Economics. 117 (2) 537–569]. The model has multiple equilibria, and under plausible conditions, higher exchange rate volatility is associated with higher interest rates.

The Brazilian Currency Turmoil of 2002: A Nonlinear Analysis

This paper investigates the main sources of instability in Brazil during the currency and financial distress episode of 2002. We test for financial contagion from the Argentine crisis and the high yield market in developed countries as well as for political uncertainty arising from the Brazilian presidential elections and the expected victory of the left-wing candidate in that contest. Markov-switching time-varying transition-probability models, applied to high-frequency data, provide significant evidence for both interpretations, as well as for a strong impact of IMF intervention on Latin American Economics.

The Valuation of the Electricity Future Contract Under Weather Uncertainty

This paper is concerned with the effects of weather uncertainty on the electricity future curve. Following the approach used by Lucia and Schwartz (2002), the behavior of the underlying spot price is assumed to consist of two components ‘ a totally predictable deterministic component that accounts for regularities in the evolution of prices and a stochastic component that accounts for the behavior of residuals from the deterministic part. The weather uncertainty is modeled consistently with seasonal outlook probabilities from the CPC (Climate Prediction Center) outlook. For a given realization of temperature, the electricity load can be predicted very accurately by a time series model using temperature and other explanatory variables. Furthermore, if temperature and electricity load are known, the spot price can be predicted as well using the regime switching model with time-varying transition probabilities. The electricity future price can be calculated for the given seasonal probabilities from the CPC outlook. Then the electricity future price can be obtained as the arithmetic average of the one-day electricity future price. The future price reflects clearly the response of the spot price to different weather patterns. As the summer gets warmer, the high price regime is more likely to be realized, and as a result, the future price increases.

Contagion, Monsoons and Domestic Turmoil in Indonesia: A Case Study in the Asian Currency Crisis

This paper investigates whether Indonesia's recent currency crisis was due to domestic fundamentals, common external shocks (monsoons), or contagion from neighboring countries. Markov-switching models attribute speculative pressures on Indonesia's currency to domestic political and financial factors and contagion from speculative pressures in Thailand and Korea. In particular, the results from a time-varying transition probability Markov-switching model (which overcomes some drawbacks from previous methods) show that inclusion of exchange rate pressures from Thailand and Korea in the transition probabilities improves the conditional probabilities of crisis in Indonesia. There is also evidence of contagion in the stock market.

Credibility of European Monetary System Interest Rate Policies: A Markov Regime‐Switching Approach

The Markov regime‐switching modelling framework, with time‐varying transition probabilities, is utilized to study the credibility of monetary policy in five member countries of the European Monetary System during the period 1979–98 (Austria, Belgium, France, Italy and the Netherlands). The output‐gap variability and the inflation variability variables are incorporated in the determination of the monetary policy preferences of the five countries. Empirical evidence is provided to show that although all the countries in our sample followed a credible monetary policy regarding price stability, they had different preferences regarding the trade‐off between the stabilization of output‐gap variability and inflation variability.

Prediction of Currency Crises: Case of Turkey

This paper explores the issue of constructing an economic predictive model of financial vulnerability through an alternative econometric methodology that addresses drawbacks in existing approaches. The methodology entails estimating a Markov regime switching model of exchange rate movements, with time-varying transition probabilities. Experiments with monthly and weekly models indicate that real exchange rate, foreign exchange reserves and domestic credit/deposit ratio are the most important determinants of financial vulnerability. These variables should be observed very closely by researchers and policy makers in order to determine if the country is heading for financially difficult times.

Fundamentals and asset price dynamics

The relation between fundamentals and asset returns is analyzed by means of Markov-switching regression models with time-varying transition probabilities. By referring to the Italian Stock Exchange over the 1973-2002 period, we find that (i) returns ‘switch’ between a zero-expected return/low volatility state and a high expected return/high volatility state; (ii) states are persistent and hence state changes can be forecast to some extent; (iii) the probability of state changes can be explained in terms of changes in the fundamentals; (iv) fundamentals do not have a direct impact on the expected returns but they only affect the transition probability matrix. Overall, our results show that a non-linear relation between market price changes and market fundamentals can be caught within the framework of (Markov) switching regession models.

Estimating PINs through a Markov Chain Model with Time-Varying Probabilities and Dynamic Behaviour

The main scope of this paper is to assess the role of intradaily information available in real time to infer the probability of informed trades in an order-driven market. The analysis conducted here provides new evidence about the mechanism by which private information modifies the probability of informed trades, and how it can be used to forecast more accurately private information arrivals. We consider the regime switching model proposed in Nyholm (2002) with time-varying transition probabilities as a function on different sets of quote-to-quote information, including market trading variables and order aggressiveness. We also include predictability in the trade flow in the regime switching scheme. Evidence suggest that variables such as order aggressiveness are key elements to forecast the probability of an informed trade, and large improvements over the basic specification are evidenced. The omission of time-varying dynamics is regarded as model misspecification and cause underestimation of the informed probability in the benchmark model. Improvements over the benchmark model when including dynamic specification are also evidenced.

Credibility of EMS Interest Rate Policies: A Markov Regine-switching Approach

The primary objective of this paper is to use the Markov regime-switching modeling framework to study the credibility of monetary policy in five member countries of the European Monetary System (EMS) during the period 1979 to 1998. The five countries examined for this purpose are Austria, Belgium, France, Italy, and the Netherlands. The major innovation of this paper is the use of a Markov regime-switching model with time-varying transition probabilities. The output-gap variability and the inflation variability variables are incorporated into the determination of the monetary policy preferences of individual member countries of the EMS. Empirical evidence is provided to show that although all the countries in our sample followed a credible monetary policy regarding price stability, they had different preferences regarding the trade-off between the stabilization of output-gap variability and inflation variability.

New directions in business cycle research and financial analysis

This paper serves as a partial introduction to and survey of the literature on Markov-switching models. We review the history of this class of models, describe their mathematical structure, and exposit the basic ideas behind estimation and inference. The paper also describes how the approach can be extended in a variety of directions, such as non-Gaussian distributions, time-varying transition probabilities, vector processes, state-space and GARCH models, and surveys recent methodological advances. The contributions of the other papers in this volume are reviewed. A final section offers conclusions and implications for policy.

Regime switching in currency markets and portfolio flows

This paper analyses a three-state Markov switching model with time-varying transition probabilities. The transition probabilities are modelled as functions of portfolio flows at a daily frequency. The evidence supports the hypothesis that currency market behaviour is characterised by regimes and that the probability of staying in a regime is materially impacted by portfolio flows. This suggests that timely knowledge of portfolio flows should be useful information for market partifipants attempting to add value via active currency trading.