UTHM Institutional Repository

Hierarchical Bayesian estimation for stationary autoregressive models using reversible jump MCMC algorithm

S., Suparman and Rusiman, Mohd Saifullah (2018) Hierarchical Bayesian estimation for stationary autoregressive models using reversible jump MCMC algorithm. International Journal of Engineering & Technology, 7 (4.30). p. 67. ISSN 2227524X

[img]
Preview
PDF
J7231_1d20c902a88a7b7f6e778e04d504dc57.pdf

Download (278kB)

Abstract

The autoregressive model is a mathematical model that is often used to model data in different areas of life. If the autoregressive model is matched against the data then the order and coefficients of the autoregressive model are unknown. This paper aims to estimate the order and coefficients of an autoregressive model based on data. The hierarchical Bayesian approach is used to estimate the order and coeffi-cients of the autoregressive model. In the hierarchical Bayesian approach, the order and coefficients of the autoregressive model are as-sumed to have a prior distribution. The prior distribution is combined with the likelihood function to obtain a posterior distribution. The posterior distribution has a complex shape so that the Bayesian estimator is not analytically determined. The reversible jump Markov Chain Monte Carlo (MCMC) algorithm is proposed to obtain the Bayesian estimator. The performance of the algorithm is tested by using simulated data. The test results show that the algorithm can estimate the order and coefficients of the autoregressive model very well. Research can be further developed by comparing with other existing methods

Item Type: Article
Uncontrolled Keywords: Autoregressive model; Hierarchical Bayesian; Reversible jump MCMC
Subjects: Q Science > QA Mathematics > QA71 Instruments and machines
Divisions: Faculty of Applied Science and Technology > Department of Mathematics and Statistic
Depositing User: Mr. Mohammad Shaifulrip Ithnin
Date Deposited: 31 Oct 2019 02:33
Last Modified: 31 Oct 2019 02:33
URI: http://eprints.uthm.edu.my/id/eprint/11784
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year