Skew-Normal Mixture and Markov-Switching GARCH Processes

This paper introduces skew-normal (SN) mixture and Markov-switching (MS) GARCH processes for capturing the skewness in the distribution of stock returns. The model class is motivated by the fact that the common way of incorporating asymmetries into Gaussian MS GARCH models, i.e., regime-dependent means, leads to autocorrelated raw returns, which may not be desirable. The appearance of the SN distribution can be explained by a pre-asymptotic behavior of daily stock returns, and can still be viewed as "generic." The dynamic properties of the process are derived, and its in- and out-of-sample performance is compared with that of several competing models in an application to three major European stock markets over a period covering the recent financial turmoil. It turns out that parsimoniously parameterized SN mixture GARCH processes perform best overall. In particular, they outperform both a skewed t GARCH specification as well as normal mixture GARCH models with skewness generated via nonzero component means.

[1]  Clive W. J. Granger,et al.  STYLIZED FACTS ON THE TEMPORAL AND DISTRIBUTIONAL PROPERTIES OF ABSOLUTE RETURNS: AN UPDATE , 2000 .

[2]  Ji-chun Liu,et al.  Stationarity of a Markov-Switching GARCH Model , 2006 .

[3]  Petros Dellaportas,et al.  Modelling nonlinearities and heavy tails via threshold normal mixture GARCH models , 2008, Comput. Stat. Data Anal..

[4]  Matteo Grigoletto,et al.  Looking for Skewness in Financial Time Series , 2009 .

[5]  J. Geweke,et al.  Hierarchical Markov Normal Mixture Models with Applications to Financial Asset Returns , 2007 .

[6]  Marc S. Paolella,et al.  A New Approach to Markov-Switching GARCH Models , 2004 .

[7]  E. Ruiz,et al.  Measuring financial risk : comparison of alternative procedures to estimate VaR and ES , 2008 .

[8]  R. Arellano-Valle,et al.  The centred parametrization for the multivariate skew-normal distribution , 2008 .

[9]  Valentina Corradi,et al.  Predicting the volatility of the S & P500 stock index via GARCH models : the role of asymmetries Basel , 2005 .

[10]  Monica Chiogna,et al.  A note on the asymptotic distribution of the maximum likelihood estimator for the scalar skew-normal distribution , 2005, Stat. Methods Appl..

[11]  Bernard Lejeune,et al.  A diagnostic m-test for distributional specification of parametric conditional heteroscedasticity models for financial data , 2009 .

[12]  Ji-Chun Liu,et al.  Stationarity for a Markov-switching Box-Cox transformed threshold GARCH process $ , 2007 .

[13]  Jeroen V. K. Rombouts,et al.  Multivariate Mixed Normal Conditional Heteroskedasticity , 2006, Comput. Stat. Data Anal..

[14]  Jun Cai.  A Markov Model of Switching-Regime ARCH , 1994 .

[15]  Jan Bulla,et al.  Stylized facts of financial time series and hidden semi-Markov models , 2006, Comput. Stat. Data Anal..

[16]  Robert Brooks,et al.  A multi-country study of power ARCH models and national stock market returns , 2000 .

[17]  The past and future of empirical finance: some personal comments , 2005 .

[18]  Stephen Gray.  Modeling the Conditional Distribution of Interest Rates as a Regime-Switching Process , 1996 .

[19]  Martin Scheicher,et al.  A Switching ARCH Model for the German DAX Index , 2006 .

[20]  Jerry Coakley,et al.  Markov-Switching GARCH Modelling of Value-at-Risk , 2008 .

[21]  T. Rydén,et al.  Stylized Facts of Daily Return Series and the Hidden Markov Model , 1998 .

[22]  Peter Christoffersen,et al.  Série Scientifique Scientific Series 2003 s-05 Backtesting Value-at-Risk : A Duration-Based Approach , 2003 .

[23]  T. Bollerslev,et al.  Generalized autoregressive conditional heteroskedasticity , 1986 .

[24]  Alain Monfort,et al.  Pricing and Inference with Mixtures of Conditionally Normal Processes , 2007 .

[25]  Juri Marcucci.  Forecasting Stock Market Volatility with Regime-Switching GARCH Models , 2005 .

[26]  Jim Q. Smith,et al.  Diagnostic checks of non‐standard time series models , 1985 .

[27]  K. Arnold,et al.  Tables for Computing Bivariate Normal Probabilities , 1958 .

[28]  Luc Bauwens,et al.  Theory and Inference for a Markov Switching GARCH Model , 2007 .

[29]  Wai Keung Li,et al.  On a Mixture Autoregressive Conditional Heteroscedastic Model , 2001 .

[30]  Allan Timmermann,et al.  Moments of Markov switching models , 2000 .

[31]  Carol Alexander,et al.  Modelling Regime-Specific Stock Price Volatility , 2009 .

[32]  INTEGRATED MARKOV-SWITCHING GARCH PROCESS , 2009, Econometric Theory.

[33]  Emese Lazar,et al.  Option Valuation with Normal Mixture GARCH Models , 2008 .

[34]  Carol Alexander,et al.  Practical financial econometrics , 2008 .

[35]  Christian Francq,et al.  Conditional Heteroskedasticity Driven by Hidden Markov Chains , 2001 .

[36]  N. Henze.  A Probabilistic Representation of the 'Skew-normal' Distribution , 1986 .

[37]  Jeroen V. K. Rombouts,et al.  Mixed Exponential Power Asymmetric Conditional Heteroskedasticity , 2007 .

[38]  M. Steel,et al.  Modeling and Inference with υ-Spherical Distributions , 1995 .

[39]  J. Zakoian,et al.  Autocovariance structure of powers of switching-regime ARMA Processes , 2002 .

[40]  Israel Cohen,et al.  ON THE STATIONARITY OF MARKOV-SWITCHING GARCH PROCESSES , 2007, Econometric Theory.

[41]  Marc S. Paolella,et al.  Conditional density and value‐at‐risk prediction of Asian currency exchange rates , 2000 .

[42]  Jeremy Berkowitz.  Testing Density Forecasts, With Applications to Risk Management , 2001 .

[43]  Christian Francq,et al.  Deriving the autocovariances of powers of Markov-switching GARCH models, with applications to statistical inference , 2008, Comput. Stat. Data Anal..

[44]  Amado Peiró.  Asymmetries and tails in stock index returns: are their distributions really asymmetric? , 2004 .

[45]  Theis Lange,et al.  An Introduction to Regime Switching Time Series Models , 2009 .

[46]  Luc Bauwens,et al.  A Component GARCH Model with Time Varying Weights , 2007 .

[47]  M. Osborne.  Brownian Motion in the Stock Market , 1959 .

[48]  James D. Hamilton,et al.  Autoregressive conditional heteroskedasticity and changes in regime , 1994 .

[49]  Timo Teräsvirta,et al.  An Introduction to Univariate GARCH Models , 2006 .

[50]  Ivana Komunjer,et al.  Asymmetric power distribution: Theory and applications to risk measurement , 2007 .

[51]  A. Azzalini.  A class of distributions which includes the normal ones , 1985 .

[52]  W. Li,et al.  On a dynamic mixture GARCH model , 2009 .

[53]  Marc S. Paolella,et al.  Value-at-Risk Prediction: A Comparison of Alternative Strategies , 2005 .

[54]  A. Azzalini,et al.  Statistical applications of the multivariate skew normal distribution , 2009, 0911.2093.

[55]  Modelling Good and Bad Volatility , 2007 .

[56]  Cathy W. S. Chen,et al.  Volatility Forecasting with Double Markov Switching GARCH Models , 2009 .

[57]  H. Veiga.  Financial Stylized Facts and the Taylor-Effect in Stochastic Volatility Models , 2009 .

[58]  Stephen L Taylor,et al.  Modelling Financial Time Series , 1987 .

[59]  Hsiang-Tai Lee,et al.  A copula‐based regime‐switching GARCH model for optimal futures hedging , 2009 .

[60]  Timo Teräsvirta,et al.  Properties of Moments of a Family of GARCH Processes , 1999 .

[61]  Shin-Ho Chung,et al.  Markov chain models, time series analysis and extreme value theory , 1996 .

[62]  E. Gonçalves,et al.  A mathematical approach to detect the Taylor property in TARCH processes , 2009 .

[63]  Carol Alexander,et al.  Normal Mixture Garch(1,1): Applications to Exchange Rate Modelling , 2004 .

[64]  H. White,et al.  On More Robust Estimation of Skewness and Kurtosis: Simulation and Application to the S&P500 Index , 2003 .

[65]  Michael J. Dueker.  Markov Switching in GARCH Processes and Mean-Reverting Stock-Market Volatility , 1997 .

[66]  C. Granger,et al.  A long memory property of stock market returns and a new model , 1993 .

[67]  Carol Alexander,et al.  Markov Switching GARCH Diffusion , 2008 .

[68]  James D. Hamilton.  Regime switching models , 2010 .

[69]  L. Ederington,et al.  Forecasting Volatility , 2004 .

[70]  Amado Peiró.  Skewness in financial returns , 1999 .

[71]  Amado Peiró.  Skewness in individual stocks at different investment horizons , 2002 .

[72]  Parameterizing Unconditional Skewness in Models for Financial Time Series , 2008 .

[73]  Yannick Malevergne,et al.  Testing the Gaussian copula hypothesis for financial assets dependences , 2001, cond-mat/0111310.

[74]  Klaassen.  Improving GARCH Volatility Forecasts with Regime-Switching GARCH Klaassen, F.J.G.M , 2001 .

[75]  Tsung-I Lin,et al.  Finite mixture modelling using the skew normal distribution , 2007 .

[76]  Marc S. Paolella,et al.  Asymmetric multivariate normal mixture GARCH , 2009, Comput. Stat. Data Anal..

[77]  J. Zakoian,et al.  Contemporaneous asymmetry in GARCH processes , 2001 .

[78]  Luc Bauwens,et al.  Bayesian Inference for the Mixed Conditional Heteroskedasticity Model , 2005 .

[79]  C. Granger,et al.  Some Properties of Absolute Return, An Alternative Measure of Risk , 1995 .

[80]  S. Laurent,et al.  Value-at-Risk for long and short trading positions , 2003 .

[81]  C. Granger,et al.  Modeling volatility persistence of speculative returns: A new approach , 1996 .

[82]  M. Rosenblatt.  Remarks on a Multivariate Transformation , 1952 .

[83]  David Ardia.  Bayesian Estimation of a Markov-Switching Threshold Asymmetric GARCH Model with Student-Tinnovations , 2008 .

[84]  Campbell R. Harvey,et al.  Current Version : April 6 , 1999 Autoregressive Conditional Skewness , 1999 .

[85]  Marc S. Paolella,et al.  Mixed Normal Conditional Heteroskedasticity , 2004 .

[86]  Paul H. Kupiec,et al.  Techniques for Verifying the Accuracy of Risk Measurement Models , 1995 .

[87]  S. Chung,et al.  A Long Memory Model with Normal Mixture GARCH , 2011 .

[88]  Ching-Hui Chang,et al.  A Note on Improved Approximation of the Binomial Distribution by the Skew-Normal Distribution , 2008 .

[89]  Markus Haas.  Persistence in volatility, conditional kurtosis, and the Taylor property in absolute value GARCH processes , 2009 .

[90]  David Ardia,et al.  Financial Risk Management with Bayesian Estimation of GARCH Models , 2008 .

[91]  Eric Jondeau,et al.  Conditional volatility, skewness, and kurtosis: existence, persistence, and comovements , 2003 .

[92]  Daniel B. Nelson.  Stationarity and Persistence in the GARCH(1,1) Model , 1990, Econometric Theory.

[93]  Thierry Ané,et al.  An analysis of the flexibility of Asymmetric Power GARCH models , 2006, Comput. Stat. Data Anal..

[94]  Carol Alexander,et al.  Quantitative methods in finance , 2008 .

[95]  Franz C. Palm,et al.  The message in weekly exchange rates in the European Monetary System: mean reversion , 1993 .