Markov chain monte carlo methods for switching diffusion models

John C. Liechty, Gareth O. Roberts

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Reversible jump Metropolis-Hastings updating schemes can be used to analyse continuous-time latent models, sometimes known as state space models or hidden Markov models. We consider models where the observed process X can be represented as a stochastic differential equation and where the latent process D is a continuous-time Markov chain. We develop Markov chain Monte Carlo methods for analysing both Markov and non-Markov versions of these models. As an illustration of how these methods can be used in practice we analyse data from the New York Mercantile Exchange oil market. In addition, we analyse data generated by a process that has linear and mean reverting states.

Original languageEnglish (US)
Pages (from-to)299-315
Number of pages17
JournalBiometrika
Volume88
Issue number2
DOIs
StatePublished - Jan 1 2001

Fingerprint

Monte Carlo Method
Markov Chains
Monte Carlo method
Markov Chain Monte Carlo Methods
Diffusion Model
Markov processes
Monte Carlo methods
Space Simulation
Reversible Jump
Latent Process
Metropolis-Hastings
Oils
Continuous-time Markov Chain
State-space Model
Markov Model
Updating
Stochastic Equations
Continuous Time
Hidden Markov models
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Mathematics(all)
  • Agricultural and Biological Sciences (miscellaneous)
  • Agricultural and Biological Sciences(all)
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

Liechty, John C. ; Roberts, Gareth O. / Markov chain monte carlo methods for switching diffusion models. In: Biometrika. 2001 ; Vol. 88, No. 2. pp. 299-315.
@article{2280042dba39448f9b9fe02b9dc786e3,
title = "Markov chain monte carlo methods for switching diffusion models",
abstract = "Reversible jump Metropolis-Hastings updating schemes can be used to analyse continuous-time latent models, sometimes known as state space models or hidden Markov models. We consider models where the observed process X can be represented as a stochastic differential equation and where the latent process D is a continuous-time Markov chain. We develop Markov chain Monte Carlo methods for analysing both Markov and non-Markov versions of these models. As an illustration of how these methods can be used in practice we analyse data from the New York Mercantile Exchange oil market. In addition, we analyse data generated by a process that has linear and mean reverting states.",
author = "Liechty, {John C.} and Roberts, {Gareth O.}",
year = "2001",
month = "1",
day = "1",
doi = "10.1093/biomet/88.2.299",
language = "English (US)",
volume = "88",
pages = "299--315",
journal = "Biometrika",
issn = "0006-3444",
publisher = "Oxford University Press",
number = "2",

}

Markov chain monte carlo methods for switching diffusion models. / Liechty, John C.; Roberts, Gareth O.

In: Biometrika, Vol. 88, No. 2, 01.01.2001, p. 299-315.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Markov chain monte carlo methods for switching diffusion models

AU - Liechty, John C.

AU - Roberts, Gareth O.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - Reversible jump Metropolis-Hastings updating schemes can be used to analyse continuous-time latent models, sometimes known as state space models or hidden Markov models. We consider models where the observed process X can be represented as a stochastic differential equation and where the latent process D is a continuous-time Markov chain. We develop Markov chain Monte Carlo methods for analysing both Markov and non-Markov versions of these models. As an illustration of how these methods can be used in practice we analyse data from the New York Mercantile Exchange oil market. In addition, we analyse data generated by a process that has linear and mean reverting states.

AB - Reversible jump Metropolis-Hastings updating schemes can be used to analyse continuous-time latent models, sometimes known as state space models or hidden Markov models. We consider models where the observed process X can be represented as a stochastic differential equation and where the latent process D is a continuous-time Markov chain. We develop Markov chain Monte Carlo methods for analysing both Markov and non-Markov versions of these models. As an illustration of how these methods can be used in practice we analyse data from the New York Mercantile Exchange oil market. In addition, we analyse data generated by a process that has linear and mean reverting states.

UR - http://www.scopus.com/inward/record.url?scp=0242546942&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242546942&partnerID=8YFLogxK

U2 - 10.1093/biomet/88.2.299

DO - 10.1093/biomet/88.2.299

M3 - Article

AN - SCOPUS:0242546942

VL - 88

SP - 299

EP - 315

JO - Biometrika

JF - Biometrika

SN - 0006-3444

IS - 2

ER -