Bayesian analysis of ARMA-GARCH models

A Markov chain sampling approach

Research output: Contribution to journalArticle

60 Citations (Scopus)

Abstract

We develop a Markov chain Monte Carlo method for a linear regression model with an ARMA(p, q)-GARCH(r, s) error. To generate a Monte Carlo sample from the joint posterior distribution, we employ a Markov chain sampling with the Metropolis-Hastings algorithm. As illustration, we estimate an ARMA-GARCH model of simulated time series data.

Original languageEnglish
Pages (from-to)57-69
Number of pages13
JournalJournal of Econometrics
Volume95
Issue number1
Publication statusPublished - 2000 Mar
Externally publishedYes

Fingerprint

Metropolis-Hastings Algorithm
ARMA Model
GARCH Model
Generalized Autoregressive Conditional Heteroscedasticity
Autoregressive Moving Average
Markov Chain Monte Carlo Methods
Bayesian Analysis
Time Series Data
Linear Regression Model
Posterior distribution
Joint Distribution
Markov chain
Estimate
Bayesian analysis
GARCH model
Sampling
Autoregressive moving average
Markov chain Monte Carlo methods
Time series data
Generalized autoregressive conditional heteroscedasticity

Keywords

  • ARMA process
  • Bayesian inference
  • GARCH
  • Markov chain Monte Carlo
  • Metropolis-Hastings algorithm

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance
  • Statistics and Probability

Cite this

Bayesian analysis of ARMA-GARCH models : A Markov chain sampling approach. / Nakatsuma, Teruo.

In: Journal of Econometrics, Vol. 95, No. 1, 03.2000, p. 57-69.

Research output: Contribution to journalArticle

@article{c1ad9208a69a4f18aec12ae60271117d,
title = "Bayesian analysis of ARMA-GARCH models: A Markov chain sampling approach",
abstract = "We develop a Markov chain Monte Carlo method for a linear regression model with an ARMA(p, q)-GARCH(r, s) error. To generate a Monte Carlo sample from the joint posterior distribution, we employ a Markov chain sampling with the Metropolis-Hastings algorithm. As illustration, we estimate an ARMA-GARCH model of simulated time series data.",
keywords = "ARMA process, Bayesian inference, GARCH, Markov chain Monte Carlo, Metropolis-Hastings algorithm",
author = "Teruo Nakatsuma",
year = "2000",
month = "3",
language = "English",
volume = "95",
pages = "57--69",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "1",

}

TY - JOUR

T1 - Bayesian analysis of ARMA-GARCH models

T2 - A Markov chain sampling approach

AU - Nakatsuma, Teruo

PY - 2000/3

Y1 - 2000/3

N2 - We develop a Markov chain Monte Carlo method for a linear regression model with an ARMA(p, q)-GARCH(r, s) error. To generate a Monte Carlo sample from the joint posterior distribution, we employ a Markov chain sampling with the Metropolis-Hastings algorithm. As illustration, we estimate an ARMA-GARCH model of simulated time series data.

AB - We develop a Markov chain Monte Carlo method for a linear regression model with an ARMA(p, q)-GARCH(r, s) error. To generate a Monte Carlo sample from the joint posterior distribution, we employ a Markov chain sampling with the Metropolis-Hastings algorithm. As illustration, we estimate an ARMA-GARCH model of simulated time series data.

KW - ARMA process

KW - Bayesian inference

KW - GARCH

KW - Markov chain Monte Carlo

KW - Metropolis-Hastings algorithm

UR - http://www.scopus.com/inward/record.url?scp=0347318519&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0347318519&partnerID=8YFLogxK

M3 - Article

VL - 95

SP - 57

EP - 69

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 1

ER -