Bayesian estimation of ARMA-GARCH model of weekly foreign exchange rates

Teruo Nakatsuma, Hiroki Tsurumi

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Three Bayesian methods (Markov chain Monte Carlo, Laplace approximation and quadrature formula) are developed to estimate the parameters of the ARMA-GARCH model. The ARMA-GARCH model is applied to weekly foreign exchange rate data of five major currencies, and their stochastic volatilities are judged by the posterior probabilities of stationarity and other conditions.

Original languageEnglish
Pages (from-to)71-84
Number of pages14
JournalAsia-Pacific Financial Markets
Volume6
Issue number1
Publication statusPublished - 1999
Externally publishedYes

Fingerprint

Foreign exchange rates
Bayesian estimation
GARCH model
Autoregressive moving average
Markov chain Monte Carlo
Stationarity
Quadrature
Posterior probability
Laplace approximation
Bayesian methods
Stochastic volatility
Currency

Keywords

  • Bayesian inference
  • Foreign exchange rate
  • GARCH

ASJC Scopus subject areas

  • Finance

Cite this

Bayesian estimation of ARMA-GARCH model of weekly foreign exchange rates. / Nakatsuma, Teruo; Tsurumi, Hiroki.

In: Asia-Pacific Financial Markets, Vol. 6, No. 1, 1999, p. 71-84.

Research output: Contribution to journalArticle

@article{42dfe8c4b650450b8281b8dad2cc2e34,
title = "Bayesian estimation of ARMA-GARCH model of weekly foreign exchange rates",
abstract = "Three Bayesian methods (Markov chain Monte Carlo, Laplace approximation and quadrature formula) are developed to estimate the parameters of the ARMA-GARCH model. The ARMA-GARCH model is applied to weekly foreign exchange rate data of five major currencies, and their stochastic volatilities are judged by the posterior probabilities of stationarity and other conditions.",
keywords = "Bayesian inference, Foreign exchange rate, GARCH",
author = "Teruo Nakatsuma and Hiroki Tsurumi",
year = "1999",
language = "English",
volume = "6",
pages = "71--84",
journal = "Asia-Pacific Financial Markets",
issn = "1387-2834",
publisher = "Springer New York",
number = "1",

}

TY - JOUR

T1 - Bayesian estimation of ARMA-GARCH model of weekly foreign exchange rates

AU - Nakatsuma, Teruo

AU - Tsurumi, Hiroki

PY - 1999

Y1 - 1999

N2 - Three Bayesian methods (Markov chain Monte Carlo, Laplace approximation and quadrature formula) are developed to estimate the parameters of the ARMA-GARCH model. The ARMA-GARCH model is applied to weekly foreign exchange rate data of five major currencies, and their stochastic volatilities are judged by the posterior probabilities of stationarity and other conditions.

AB - Three Bayesian methods (Markov chain Monte Carlo, Laplace approximation and quadrature formula) are developed to estimate the parameters of the ARMA-GARCH model. The ARMA-GARCH model is applied to weekly foreign exchange rate data of five major currencies, and their stochastic volatilities are judged by the posterior probabilities of stationarity and other conditions.

KW - Bayesian inference

KW - Foreign exchange rate

KW - GARCH

UR - http://www.scopus.com/inward/record.url?scp=22544462777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22544462777&partnerID=8YFLogxK

M3 - Article

VL - 6

SP - 71

EP - 84

JO - Asia-Pacific Financial Markets

JF - Asia-Pacific Financial Markets

SN - 1387-2834

IS - 1

ER -