High-order extensions of the Double Chain Markov Model

DOI10.1081/STM-120004464MaRDI QIDQ3147435zbMATH OpenFDO

Authors André Berchtold

Publication date 12 November 2002

Published in Stochastic Models (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1081/STM-120004464

zbMATH Keywords

Baum-Welch algorithmdouble chain Markov modelforward-backward algorithmmixture transition distribution modelViterbi algorithm

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)

Review text

Let \(\{Y_t\}\) be a non-homogeneous \(f\)-order Markov chain taking values in the set \(\{1,\dots,K\}\). The matrix of transition probabilities at time \(t\) depends on an unobservable variable \(X_t\) where \(\{X_t\}\) is an \(l\)-order Markov chain with the set of states \(\{1,\dots,M\}\). This double chain Markov model (DCMM) can represent time series in a random environment. Since the DCMM has many parameters, their number can be considerably reduced using a mixture transition distribution model. The estimation of parameters is based on an EM algorithm. The optimal sequence of states is computed via Viterbi algorithm. The model is applied to an analysis of a sequence of DNA, to the song of the wood pewee and to the behavior of young monkeys. The author introduces a www address where a software called MARCH for the computation of DCMM is freely available.

Recommendations

• The double chain markov model
• The mixture transition distribution model for high-order Markov chains and non-Gaussian time series
• Fitting Markov Chain Models to Discrete State Series such as DNA Sequences
• Estimation and Modelling Repeated Patterns in High Order Markov Chains with the Mixture Transition Distribution Model
• Probabilistic and statistical analysis of higher-order Markov chains

Cites work

• Estimation and Modelling Repeated Patterns in High Order Markov Chains with the Mixture Transition Distribution Model
• Estimation in the mixture transition distribution model
• Finite-horizon dynamic optimisation when the terminal reward is a concave functional of the distribution of the final state
• scientific article; zbMATH DE number 3514781 (Why is no real title available?)
• scientific article; zbMATH DE number 846906 (Why is no real title available?)
• scientific article; zbMATH DE number 965582 (Why is no real title available?)
• On Some Criteria for Estimating the Order of a Markov Chain
• The double chain markov model
• The ergodic theory of Markov chains in random environments

Cited in

(10)

• General framework and model building in the class of hidden mixture transition distribution models
• The mixture transition distribution model for high-order Markov chains and non-Gaussian time series
• Lumps, breathers, interactions and rogue wave solutions for a stochastic gene evolution in double chain deoxyribonucleic acid system
• Modeling the coupled return-spread high frequency dynamics of large tick assets
• Экономные модели цепей Маркова высокого порядка для оценивания криптографических генераторов
• The table auto-regressive moving-average model for (categorical) stationary series: statistical properties (causality; from the all random to the conditional random)
• The double chain markov model
• Hidden-Markov models for ordinal time series
• Efficient backward decoding of high-order hidden Markov models
• Efficient Bayesian estimation of the multivariate double chain Markov model

This page was built for publication: High-order extensions of the Double Chain Markov Model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3147435)