Bayesian hidden Markov modelling using circular‐linear general projected normal distribution

We introduce a multivariate hidden Markov model to jointly cluster time‐series observations with different support, that is, circular and linear. Relying on the general projected normal distribution, our approach allows for bimodal and/or skewed cluster‐specific distributions for the circular variable. Furthermore, we relax the independence assumption between the circular and linear components observed at the same time. Such an assumption is generally used to alleviate the computational burden involved in the parameter estimation step, but it is hard to justify in empirical applications. We carry out a simulation study using different data‐generation schemes to investigate model behavior, focusing on well recovering the hidden structure. Finally, the model is used to fit a real data example on a bivariate time series of wind speed and direction. Copyright © 2015 John Wiley & Sons, Ltd.

[1]  William M. Rand,et al.  Objective Criteria for the Evaluation of Clustering Methods , 1971 .

[2]  K. Mardia.  Statistics of Directional Data , 1972 .

[3]  K. V. Mardia,et al.  Linear-Circular Correlation Coefficients and Rhythmometry , 1976 .

[4]  Richard A. Johnson,et al.  Some Angular-Linear Distributions and Related Regression Models , 1978 .

[5]  G. S. Watson.  Statistics on Spheres , 1983 .

[6]  Anne Lohrli.  Chapman and Hall , 1985 .

[7]  N. I. Fisher.  Problems with the Current Definitions of the Standard Deviation of Wind Direction , 1987 .

[8]  Alan J. Lee,et al.  Regression Models for an Angular Response , 1992 .

[9]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[10]  D. M. Titterington,et al.  Computational Bayesian Analysis of Hidden Markov Models , 1998 .

[11]  Gérard Govaert,et al.  Assessing a Mixture Model for Clustering with the Integrated Completed Likelihood , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Geoffrey J. McLachlan,et al.  Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.

[13]  S. R. Jammalamadaka,et al.  Topics in Circular Statistics , 2001 .

[14]  Sw. Banerjee,et al.  Hierarchical Modeling and Analysis for Spatial Data , 2003 .

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

[16]  Eric Moulines,et al.  Inference in Hidden Markov Models (Springer Series in Statistics) , 2005 .

[17]  Ajay Jasra,et al.  Markov Chain Monte Carlo Methods and the Label Switching Problem in Bayesian Mixture Modeling , 2005 .

[18]  Sylvia Frühwirth-Schnatter,et al.  Finite Mixture and Markov Switching Models , 2006 .

[19]  Haikady N. Nagaraja,et al.  Inference in Hidden Markov Models , 2006, Technometrics.

[20]  A. Munk,et al.  Hidden Markov models for circular and linear-circular time series , 2006, Environmental and Ecological Statistics.

[21]  Michael I. Jordan,et al.  Hierarchical Dirichlet Processes , 2006 .

[22]  A. Munk,et al.  On Identifiability in Capture–Recapture Models , 2006, Biometrics.

[23]  T. Gneiting,et al.  The continuous ranked probability score for circular variables and its application to mesoscale forecast ensemble verification , 2006 .

[24]  A. Raftery,et al.  Strictly Proper Scoring Rules, Prediction, and Estimation , 2007 .

[25]  Amilcar Soares,et al.  Stochastic environmental research risk assessment , 2007 .

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

[27]  Tobias Rydén,et al.  EM versus Markov chain Monte Carlo for estimation of hidden Markov models: a computational perspective , 2008 .

[28]  P. Deb.  Finite Mixture Models , 2008 .

[29]  Gilles Celeux,et al.  Selecting hidden Markov model state number with cross-validated likelihood , 2008, Comput. Stat..

[30]  Grace S. Shieh,et al.  A CIRCULAR-CIRCULAR REGRESSION MODEL , 2008 .

[31]  Luigi Spezia.  Reversible jump and the label switching problem in hidden Markov models , 2009 .

[32]  Luigi Spezia,et al.  Bayesian analysis of multivariate Gaussian hidden Markov models with an unknown number of regimes , 2009 .

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

[34]  A. Farcomeni,et al.  A Multivariate Extension of the Dynamic Logit Model for Longitudinal Data Based on a Latent Markov Heterogeneity Structure , 2009 .

[35]  Christian P. Robert,et al.  Introducing Monte Carlo Methods with R , 2009 .

[36]  Gilles Celeux,et al.  Combining Mixture Components for Clustering , 2010, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[37]  Francesco Bartolucci,et al.  Assessment of School Performance Through a Multilevel Latent Markov Rasch Model , 2009, 0909.4961.

[38]  A. Farcomeni,et al.  A note on the mixture transition distribution and hidden Markov models , 2010 .

[39]  Antonello Maruotti,et al.  A Hierarchical Model for Time Dependent Multivariate Longitudinal Data , 2010 .

[40]  A. Doucet,et al.  Particle Markov chain Monte Carlo methods , 2010 .

[41]  Qiang Zhang,et al.  Multivariate Discrete Hidden Markov Models for Domain-Based Measurements and Assessment of Risk Factors in Child Development , 2010, Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America.

[42]  R. Langrock,et al.  Hidden Markov models with arbitrary state dwell-time distributions , 2011, Comput. Stat. Data Anal..

[43]  S. R. Jammalamadaka,et al.  Directional Statistics, I , 2011 .

[44]  A. Maruotti.  Mixed Hidden Markov Models for Longitudinal Data: An Overview , 2011 .

[45]  Maurizio Vichi,et al.  Studies in Classification Data Analysis and knowledge Organization , 2011 .

[46]  A Bayesian regression model for circular data based on the projected normal distribution , 2011 .

[47]  Giovanna Jona-Lasinio,et al.  Spatial analysis of wave direction data using wrapped Gaussian processes , 2012, 1301.1446.

[48]  A. Maruotti,et al.  A Multivariate Hidden Markov Model for the Identification of Sea Regimes from Incomplete Skewed and Circular Time Series , 2012 .

[49]  F. Lagona,et al.  Model-based clustering of multivariate skew data with circular components and missing values , 2012 .

[50]  Iain L. MacDonald,et al.  Some nonstandard stochastic volatility models and their estimation using structured hidden Markov models , 2012 .

[51]  Jörn Dannemann,et al.  Semiparametric Hidden Markov Models , 2012 .

[52]  Francesco Bartolucci,et al.  Latent Markov Models for Longitudinal Data , 2012 .

[53]  Roland Langrock,et al.  Flexible and practical modeling of animal telemetry data: hidden Markov models and extensions. , 2012, Ecology.

[54]  Francesco Bartolucci,et al.  Latent Markov models: a review of a general framework for the analysis of longitudinal data with covariates , 2014 .

[55]  Antonello Maruotti,et al.  The environmental Kuznets curve: functional form, time‐varying heterogeneity and outliers in a panel setting , 2013 .

[56]  A. Gelfand,et al.  Directional data analysis under the general projected normal distribution. , 2013, Statistical methodology.

[57]  Jean-Michel Marin,et al.  Bayesian Essentials with R , 2013 .

[58]  Ajay Jasra,et al.  Parameter Estimation in Hidden Markov Models With Intractable Likelihoods Using Sequential Monte Carlo , 2013, 1311.4117.

[59]  Roland Langrock,et al.  Combining hidden Markov models for comparing the dynamics of multiple sleep electroencephalograms , 2013, Statistics in medicine.

[60]  A. Gelfand,et al.  Joint spatio-temporal analysis of a linear and a directional variable: space-time modeling of wave heights and wave directions in the Adriatic Sea , 2014 .

[61]  A. Gelfand,et al.  Modeling Space and Space-Time Directional Data Using Projected Gaussian Processes , 2014 .

[62]  Eduardo Gutiérrez-Peña,et al.  A Bayesian model for longitudinal circular data based on the projected normal distribution , 2014, Comput. Stat. Data Anal..

[63]  Marco Picone,et al.  A hidden Markov approach to the analysis of space–time environmental data with linear and circular components , 2015, Stochastic Environmental Research and Risk Assessment.

[64]  Zhiwei Zhang,et al.  A TWO-STATE MIXED HIDDEN MARKOV MODEL FOR RISKY TEENAGE DRIVING BEHAVIOR. , 2015, The annals of applied statistics.