Bayesian Inference using Multiple-try Metropolis Hastings Scheme for the Efficiency of Estimating Gumbel Distribution Parameters

Authors

  • Nor Azrita Mohd Amin University of Malaysia, Perlis image/svg+xml
  • Mohd Bakri Adam Institute of Mathematical Research Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia
  • Noor Akma Ibrahim Institute of Mathematical Research Universiti Putra Malaysia, 43400 UPM Serdang, Selangor, Malaysia

DOI:

https://doi.org/10.11113/matematika.v31.n1.743

Abstract

This paper aims to explore the efficiency for estimating the parameters of Gumbel simulated data using Multiple-try Metropolis algorithm (MTM). Several goodness-of-fit tests are used to compare the performance of MTM and the former, Metropolis-Hastings algorithm (MH). Concerning for a fair comparison, this study uses the equivalent starting point, the similar number of iterations and also the same length of burn-in periods. The numerical studies show that the MTM method performs slightly better than MH method after 5000 iterations to meet the stationary distribution. More candidates in the proposals lead to a higher accuracy of MTM estimation.

Downloads

Published

28-07-2015

Issue

Volume 31 (June 2015)

Section

Articles

License

Copyright of articles that appear in MATEMATIKA: MJIAM belongs exclusively to Penerbit UTM Press, Universiti Teknologi Malaysia. This copyright covers the rights to reproduce the article, including reprints, electronic reproductions or any other reproductions of similar nature.

How to Cite

Bayesian Inference using Multiple-try Metropolis Hastings Scheme for the Efficiency of Estimating Gumbel Distribution Parameters. (2015). MATEMATIKA, 31(1), 25-36. https://doi.org/10.11113/matematika.v31.n1.743