Multiple hidden Markov models for categorical time series

DOI10.1016/J.JMVA.2015.04.002MaRDI QIDQ495338zbMATHOpenAlexFDO

Authors R. Colombi, S. Giordano

Publication date 10 September 2015

Published in Journal of Multivariate Analysis (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1309.3895

zbMATH Keywords

graphical modelsconditional independencemultivariate Markov chainsGranger noncausalitymarginal modelsMarkov properties

Mathematics Subject Classification ID

Multivariate analysis (62H99) Markov processes: estimation; hidden Markov models (62M05) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10)

Abstract: We introduce multiple hidden Markov models (MHMMs) where an observed multivariate categorical time series depends on an unobservable multivariate Mar- kov chain. MHMMs provide an elegant framework for specifying various independence relationships between multiple discrete time processes. These independencies are interpreted as Markov properties of a mixed graph and a chain graph associated to the latent and observable components of the MHMM, respectively. These Markov properties are also translated into zero restrictions on the parameters of marginal models for the transition probabilities and the distributions of the observable variables given the latent states.

Recommendations

• Mixed Hidden Markov Models
• Hidden Markov partition models
• Bayesian analysis of multivariate Gaussian hidden Markov models with an unknown number of regimes
• A note on the mixture transition distribution and hidden Markov models
• Categorical time series models for contingency tables

Cites work

• scientific article; zbMATH DE number 1134987 (Why is no real title available?)
• scientific article; zbMATH DE number 795293 (Why is no real title available?)
• scientific article; zbMATH DE number 846906 (Why is no real title available?)
• A multivariate Markov chain model for categorical data sequences and its applications in demand predictions
• Chain graph models of multivariate regression type for categorical data
• Discrete chain graph models
• Dynamic Linear Models with R
• Graphical models for multivariate Markov chains
• Hidden Markov Models for Time Series
• Hidden Markov models for bioinformatics
• Inference in hidden Markov models.
• Markov Properties for Acyclic Directed Mixed Graphs
• Observability and nonlinear filtering
• Selecting hidden Markov model state number with cross-validated likelihood
• Testing lumpability for marginal discrete hidden Markov models

Cited in

(7)

• Two hidden Markov models for multiple processes and their contribution to the definition of a postural style
• Bayesian analysis of multivariate Gaussian hidden Markov models with an unknown number of regimes
• Hidden Markov models for longitudinal rating data with dynamic response styles
• Some conditional independencies in bivariate categorical time series
• Quantile hidden semi-Markov models for multivariate time series
• Hidden Markov models for multivariate functional data
• Asymmetric hidden Markov models

Describes a project that uses

Uses Software

• R
• dlm
• hmmm

This page was built for publication: Multiple hidden Markov models for categorical time series

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q495338)