Nonlinear Regime-switching Model Research Articles

Modeling and Forecasting Stock Market Volatility of CPEC Founding Countries: Using Nonlinear Time Series and Machine Learning Models

The highly sensitive, nonlinear, and unpredictable stock marketbehaviours are always challenging for researchers. Stock markets ofPakistan and China, i.e., KSE-100 and SSE-100, respectively, are thetwo most attractive stock markets after the official announcementof CPEC. Thus, the daily closing price of KSE-100 and SSE-100 Stockreturns are used to evaluate the volatility forecast performance ofthe machine learning technique, GARCH family and the nonlinearregime-switching models. The findings of this study revealed that thestandard GARCH model is the best-fitted model based on Akaike’sInformation Criteria (AIC) and Bayesian Information Criteria (BIC).Furthermore, the forecast performance of the machine learning LSTMmodel outperforms other models based on RMSE for SSE-100. Incontrast, the forecast performance of CGARCH for SSE-100 and theMarkov-regime-switchingmodelforKSE-100outperformsothermodelsbased on MAE, MAPE, and SMAPE evaluation criteria. It is also revealedthat the predictive power of the machine learning model is very closeto CGARCH and MRS model; therefore, the LSTM model can be used asan alternative to GARCH and regime-switching models for stock marketvolatility. These findings will help national and international investors,policy-makers, geographical economists, and industrialists to use thebestforecastmodeltomakebetterpoliciesandgaintremendousprofit.

Sovereign debt in emerging market countries: not all of them are serial defaulters

ABSTRACTAvoiding to assign emerging market countries a ‘typical’ behaviour, this article considers the heterogeneity across them and through time to predict their sovereign default episodes. Moreover, it focuses on the imbalance between defaulted debt and GDP. For the first time, we use a panel nonlinear regime-switching model whose explanatory factors have a different impact on sovereign default, depending on the regime the country belongs to. We mitigate some common views of the literature (in particular the ‘serial default’ theory) and identify countries deserving to be monitored carefully, because of a higher exposure to sovereign default risk.Abbreviation: CRAG : Credit Rating Assessment Group; EMBI: Emerging Market Bond Index; FSI: Financial Stress Index; GDP: Gross Domestic Product; GFC: Global Financial Cycle; GTD: Gonzalez, Teräsvirta, and V. Dijk; IMF: International Monetary Fund; LM: Lagrange Multiplier; PSTR: Panel Smooth Transition Regression; PTR: Panel Threshold Regression; STAR: Smooth Transition Auto Regressive model; US: United States; VIX: Volatility Index

Sigma Point Filters for Dynamic Nonlinear Regime Switching Models

In this paper we take three well known Sigma Point Filters, namely the Unscented Kalman Filter, the Divided Difference Filter, and the Cubature Kalman Filter, and extend them to allow for a very general class of dynamic nonlinear regime switching models. Using both a Monte Carlo study and real data, we investigate the properties of our proposed filters by using a regime switching DSGE model solved using nonlinear methods. We find that the proposed filters perform well. They are both fast and reasonably accurate, and as a result they will provide practitioners with a convenient alternative to Sequential Monte Carlo methods. We also investigate the concept of observability and its implications in the context of the nonlinear filters developed and propose some heuristics. Finally, we provide in the RISE toolbox, the codes implementing these three novel filters.

Non linear models and the load of an electricity distributor

Purpose – The purpose of this study is to ascertain whether nonlinearities could be present in electricity loads observed in subtropical environments, where none or little heating is required, and whether threshold autoregressive (TAR)-type regime switching models could be advantageous in the modeling of those loads. Design/methodology/approach – The actual observed load of a Brazilian regional electricity distributor from January 2013 to August 2012 was modeled using a popularly employed ARMA model for reference, and smooth and non-smooth TAR transition (non-linear) models were used as non-linear regime switching models. Findings – Evidence of nonlinearities were found in the load series, and evidence was also found on the intrinsic resistance of this type of models to structural breaks in the data. Additionally, to reacting well to asymmetries in the data, these models avoid the use of exogenous variables. Altogether, this could prove to be a definite advantage of the use of such model alternatives. Research limitations/implications – However, even if the present work may have been limited by the observation frequency of the available data, it appears TAR models appear to be a viable alternative to forecasting short-term electricity loads. Nonetheless, additional research is required to achieve a higher accuracy of forecast data. Practical implications – If such models can be successfully used, it will be a great advantage for electricity generators, as the computational effort involved in the use of such models is not significantly larger than regular linear ones. Originality/value – To our knowledge, this type of research has not yet been made with subtropical/tropical electricity load data.

Financial variables and economic activity in the Nordic countries

This study focuses on the predictive content of stock returns, short-term interest rates and the term spread by using non-linear regime switching models for forecasting GDP growth in Denmark, Finland, Norway and Sweden. We apply the threshold autoregressive (TAR) model-switching approach and the novel regime-switching signals which combine the inversion of the yield curve and the recession as the signal to switch between economic states.The results suggest that the TAR model approach with an inversion–recession signal is preferable for predicting economic activity in all four of the Nordic countries. Among the Nordic countries, the predictive relationship between financial variables and economic activity is found to be the strongest in Finland and Sweden.

Some Pitfalls in Smooth Transition Models Estimation: A Monte Carlo Study

Nonlinear regime switching models are becoming increasingly popular in recent applied literature, as they allow capturing state-dependent behaviors which would be otherwise impossible to model. However, despite their popularity, the specification and estimation of these type of models is computationally complex and it is far from being a univocally solved issue.This paper aims at contributing to this debate. In particular, we use Monte Carlo experiments to assess whether employing the standard trick of `concentrating the sum of squares' by Leybourne et al. (Journal of Time Series Analysis, 19(1): 83---97, 1998) in the application of nonlinear least squares to smooth transition models yields estimates with desirable asymptotic properties. Our results confirm that this procedure needs to be used with caution as it may yield biased and inconsistent estimates, especially when faced with small samples.

Nonlinearity and nonstationarity in international art market prices: evidence from Markov-switching ADF unit root tests

This study investigates the presence (or lack thereof) of nonlinear dynamics and nonstationarity in international art market prices using quarterly data for the period 1990–2011. We first test whether art market price indices follow stochastic trends or whether they are stationary by means of linear unit root tests. Next, we estimate the Markov regime-switching ADF model and test whether the linear or the nonlinear regime-switching model provides a better characterization of the global art market price series. We find that all art market price indices (except for Drawings) exhibit nonlinearity. To our knowledge, our study is the first one in the literature to suggest that a nonlinear (Markov regime-switching) model provides a better characterization of the behavior of price dynamics in international art markets. In particular, our findings indicate that the market for the overall global art market, paintings, old masters, sculptures, photographs, prints, and contemporary art might indeed be stationary while exhibiting nonlinear regime-switching properties. On the other hand, the market for drawings and the Nineteenth century art are found to be nonstationary. Overall, despite the common ground of a regime-switching framework, we still find that the sub-segments of the art market have their own inner regime switching dynamics and hence they can evolve differently overtime.

A Markov-switching approach to measuring exchange market pressure

This paper characterizes exchange market pressure (EMP) as a nonlinear Markov-switching phenomenon, and examines its dynamics in response to money growth and inflation over three regimes. The empirical results identify episodes of EMP in the Kyrgyz Republic and confirm the statistical superiority of the nonlinear regime-switching model over a linear VAR version in understanding EMP. The nonlinear empirical approach adequately characterizes the data generation process and yields results that are consistent with theoretical predictions, particularly the dampening effect of monetary contraction on depreciation pressure. During periods of appreciation pressure, however, the reverse policy option—monetary expansion—may not be efficient, particularly where PPP rather than UIP drives exchange rates. In addition, monetary expansion in such cases defeats the primary objective of monetary policy—price stability—and may exacerbate the instability. Copyright © 2010 John Wiley & Sons, Ltd.

Valuing a gas-fired power plant: A comparison of ordinary linear models, regime-switching approaches, and models with stochastic volatility

Energy prices are often highly volatile with unexpected spikes. Capturing these sudden spikes may lead to more informed decision-making in energy investments, such as valuing gas-fired power plants, than ignoring them. In this paper, non-linear regime-switching models and models with mean-reverting stochastic volatility are compared with ordinary linear models. The study is performed using UK electricity and natural gas daily spot prices and suggests that with the aim of valuing a gas-fired power plant with and without operational flexibility, non-linear models with stochastic volatility, specifically for logarithms of electricity prices, provide better out-of-sample forecasts than both linear models and regime-switching models.

A Markov-Switching Approach to Measuring Exchange Market Pressure

This paper characterizes exchange market pressure as a nonlinear Markov-switching phenomenon, and examines its dynamics in response to money growth and inflation over three regimes. The empirical results identify episodes of exchange market pressure in the Kyrgyz Republic and confirm the statistical superiority of the nonlinear regime-switching model over a linear VAR version in understanding exchange market pressure. The nonlinear empirical approach adequately characterizes the data generation process and yields results that are consistent with theoretical predictions, particularly the dampening effect of monetary contraction on depreciation pressure. During periods of appreciation pressure, however, the reverse policy option-monetary expansion-may not be efficient, particularly where PPP rather than UIP drives exchange rates. In addition, monetary expansion in such cases defeats the primary objective of monetary policy-price stability-and may exacerbate the instability.

A Markov-Switching Approach to Measuring Exchange Market Pressure

This paper characterizes exchange market pressure as a nonlinear Markov-switching phenomenon, and examines its dynamics in response to money growth and inflation over three regimes. The empirical results identify episodes of exchange market pressure in the Kyrgyz Republic and confirm the statistical superiority of the nonlinear regime-switching model over a linear VAR version in understanding exchange market pressure. The nonlinear empirical approach adequately characterizes the data generation process and yields results that are consistent with theoretical predictions, particularly the dampening effect of monetary contraction on depreciation pressure. During periods of appreciation pressure, however, the reverse policy option-monetary expansion-may not be efficient, particularly where PPP rather than UIP drives exchange rates. In addition, monetary expansion in such cases defeats the primary objective of monetary policy-price stability-and may exacerbate the instability.

Point and Interval Forecasting of Spot Electricity Prices: Linear vs. Non-Linear Time Series Models

In this paper we assess the short-term forecasting power of different time series models in the electricity spot market. In particular we calibrate AR/ARX (X stands for exogenous/fundamental variable—system load in our study), AR/ARX-GARCH, TAR/TARX and Markov regime-switching models to California Power Exchange (CalPX) system spot prices. We then use them for out-ofsample point and interval forecasting in normal and extremely volatile periods preceding the market crash in winter 2000/2001. We find evidence that (i) non-linear, threshold regime-switching (TAR/TARX) models outperform their linear counterparts, both in point and interval forecasting, and that (ii) an additional GARCH component generally decreases point forecasting efficiency. Interestingly, the former result challenges a number of previously published studies on the failure of non-linear regime-switching models in forecasting.

The composite index of leading economic indicators: A comparison of approaches

I compare the real-time recession predicting performance of the Conference Board Leading Index, the Stock and Watson Leading Index, and the yield curve in the period since 1988. I first calculate the real-time probability of recession for the yield curve and Conference Board Leading Index using a simple non-linear regime-switching model. I then compare these estimates to the probability of recession published by Stock and Watson. The Conference Board Leading Index gave the strongest signal of recession in the six months prior to the 1990–1991 recession and gave no false signals in the 1990s. The Stock and Watson Leading Index failed to give recession signals in the first half of 1990 and the yield curve may have given a false signal in early 1999. The results show that the traditional leading index is still a useful tool for monitoring the ebb and flow of regional and national economies.

Long Swings in Exchange Rates: Are They Really in the Data?

The random walk is often used to model exchange rates. According to the Lucas critique, however, policy shifts may lead to breaks in the trend of exchange rates and hence to long swings. We use a Markov regime-switching model to allow for such swings and we reject the random walk in favor of the regime-switching model. Earlier papers report this result too, but the authors are concerned about the reliability of their Wald based tests in the strongly nonlinear regime-switching model. We show that these tests are indeed not very robust. Hence, we use a likelihood ratio test for which the (non-standard) critical values have been computed recently.