A hidden Markov regime-switching smooth transition model

Robert J. Elliott, Tak Kuen Siu, John W. Lau

Research output: Contribution to journalArticle

Abstract

In this paper, we develop a new class of parametric nonlinear time series models by combining two important classes of models, namely smooth transition models and hidden Markov regime-switching models. The class of models is general and flexible enough to incorporate two types of switching behavior: smooth state transitions and abrupt changes in hidden states. The estimation of the hidden states and model parameters is performed by applying filtering theory and a filter-based expectation-maximization (EM) algorithm. Applications of the model are illustrated using simulated data and real financial data. Other potential applications are mentioned.

Original languageEnglish
Article number20160061
JournalStudies in Nonlinear Dynamics and Econometrics
Volume22
Issue number4
DOIs
Publication statusE-pub ahead of print - 29 Jun 2018

Fingerprint

Markov Switching
Regime Switching
Transition Model
regime
Nonlinear Time Series Model
Regime-switching Model
Financial Data
Expectation-maximization Algorithm
State Transition
Model
Markov Model
Filtering
Filter
Markov regime-switching
Smooth transition models
time series
Class

Cite this

@article{f213c29217a24a088a7af66fa12e7d74,
title = "A hidden Markov regime-switching smooth transition model",
abstract = "In this paper, we develop a new class of parametric nonlinear time series models by combining two important classes of models, namely smooth transition models and hidden Markov regime-switching models. The class of models is general and flexible enough to incorporate two types of switching behavior: smooth state transitions and abrupt changes in hidden states. The estimation of the hidden states and model parameters is performed by applying filtering theory and a filter-based expectation-maximization (EM) algorithm. Applications of the model are illustrated using simulated data and real financial data. Other potential applications are mentioned.",
keywords = "filtering, Laplace series expansion, nonlinear time series, regime switching model, smooth transition model",
author = "Elliott, {Robert J.} and Siu, {Tak Kuen} and Lau, {John W.}",
year = "2018",
month = "6",
day = "29",
doi = "10.1515/snde-2016-0061",
language = "English",
volume = "22",
journal = "Studies in Nonlinear Dynamics and Econometrics",
issn = "1081-1826",
publisher = "Berkeley Electronic Press",
number = "4",

}

A hidden Markov regime-switching smooth transition model. / Elliott, Robert J.; Siu, Tak Kuen; Lau, John W.

In: Studies in Nonlinear Dynamics and Econometrics, Vol. 22, No. 4, 20160061, 29.06.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hidden Markov regime-switching smooth transition model

AU - Elliott, Robert J.

AU - Siu, Tak Kuen

AU - Lau, John W.

PY - 2018/6/29

Y1 - 2018/6/29

N2 - In this paper, we develop a new class of parametric nonlinear time series models by combining two important classes of models, namely smooth transition models and hidden Markov regime-switching models. The class of models is general and flexible enough to incorporate two types of switching behavior: smooth state transitions and abrupt changes in hidden states. The estimation of the hidden states and model parameters is performed by applying filtering theory and a filter-based expectation-maximization (EM) algorithm. Applications of the model are illustrated using simulated data and real financial data. Other potential applications are mentioned.

AB - In this paper, we develop a new class of parametric nonlinear time series models by combining two important classes of models, namely smooth transition models and hidden Markov regime-switching models. The class of models is general and flexible enough to incorporate two types of switching behavior: smooth state transitions and abrupt changes in hidden states. The estimation of the hidden states and model parameters is performed by applying filtering theory and a filter-based expectation-maximization (EM) algorithm. Applications of the model are illustrated using simulated data and real financial data. Other potential applications are mentioned.

KW - filtering

KW - Laplace series expansion

KW - nonlinear time series

KW - regime switching model

KW - smooth transition model

UR - http://www.scopus.com/inward/record.url?scp=85049500628&partnerID=8YFLogxK

U2 - 10.1515/snde-2016-0061

DO - 10.1515/snde-2016-0061

M3 - Article

VL - 22

JO - Studies in Nonlinear Dynamics and Econometrics

JF - Studies in Nonlinear Dynamics and Econometrics

SN - 1081-1826

IS - 4

M1 - 20160061

ER -