Testing for the number of states in hidden Markov models

Scale mixtures of normal distributions are frequently used to model the heavy tails of asset returns. A simple specification is a three component scale mixture, where the states correspond to high, intermediate and low volatility phases of the market. Tests for the number of states in hidden Markov models are proposed and used to assess whether in view of recent financial turbulences, three volatility states are still sufficient. The tests extend tests for independent finite mixtures by using a quasi-likelihood which neglects the dependence structure of the regime. The main theoretical insight is the surprising fact that the asymptotic distribution of the proposed tests for HMMs is the same as for independent mixtures with corresponding weights. As application the number of volatility states for logarithmic returns of the S&P 500 index in two HMMs is determined, one with state-dependent normal distributions and switching mean and scale, and the other with state-dependent skew-normal distributions with switching scale and structural mean and skewness parameters. It turns out that in both models, four states are indeed required, and a maximum-a-posteriori analysis shows that the highest volatility state mainly corresponds to the recent financial crisis.

[1]  Claudia Czado,et al.  Computational Statistics and Data Analysis Regime Switches in the Dependence Structure of Multidimensional Financial Data , 2022 .

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

[3]  Pengfei Li,et al.  Testing the Order of a Finite Mixture , 2010 .

[4]  Pengfei Li,et al.  Tuning the EM‐test for finite mixture models , 2011 .

[5]  Jiahua Chen,et al.  Inference on the Order of a Normal Mixture , 2012 .

[6]  Eric Moulines,et al.  Inference in hidden Markov models , 2010, Springer series in statistics.

[7]  Hajo Holzmann,et al.  Identifiability of Finite Mixtures of Elliptical Distributions , 2006 .

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

[9]  G. Lindgren Markov regime models for mixed distributions and switching regressions , 1978 .

[10]  J. Geweke,et al.  Comparing and Evaluating Bayesian Predictive Distributions of Asset Returns , 2008 .

[11]  N. Shephard,et al.  Stochastic Volatility: Origins and Overview , 2008 .

[12]  Jing Zhang,et al.  ESTIMATING COMPONENTS IN FINITE MIXTURES AND HIDDEN MARKOV MODELS , 2005 .

[13]  E. Gassiat,et al.  The likelihood ratio test for the number of components in a mixture with Markov regime , 2000 .

[14]  Jiahua Chen,et al.  Inference for multivariate normal mixtures , 2008, J. Multivar. Anal..

[15]  Hajo Holzmann,et al.  Testing for two states in a hidden Markov model , 2008 .

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

[17]  B. Leroux Consistent estimation of a mixing distribution , 1992 .

[18]  Maciej Augustyniak Maximum Likelihood Estimation of the Markov-Switching GARCH Model , 2014, Comput. Stat. Data Anal..

[19]  R. Arellano-Valle,et al.  Maximum penalized likelihood estimation for skew-normal and skew-t distributions , 2012, 1203.2376.

[20]  Mary R. Hardy,et al.  A Regime-Switching Model of Long-Term Stock Returns , 2001 .

[21]  Stanley J. Kon Models of Stock Returns—A Comparison , 1984 .

[22]  W. Zucchini,et al.  Hidden Markov Models for Time Series: An Introduction Using R , 2009 .