Just Accepted Manuscripts
Articles

BAYESIAN INFERENCE FOR EXPONENTIATED INVERTED WEIBULL DISTRIBUTION IN PRESENCE OF PROGRESSIVE TYPE-II CENSORING

PDF
  • Teena Goyal,
  • Piyush K Rai,
  • Mahaveer S Panwar,
  • Sandeep K Maurya
Teena Goyal
Department of Mathematics & Statistics, Banasthali Vidyapith, Rajasthan, India
Piyush K Rai
Department of Statistics, Banaras Hindu University, Varanasi, India
Mahaveer S Panwar
Department of Statistics, Banaras Hindu University, Varanasi, India
Sandeep K Maurya
Department of Statistics, Banaras Hindu University, Varanasi, India
DOI: https://doi.org/10.26398/IJAS.248

Published 2024-12-21

Keywords

  • Progressive censoring,
  • Bayes estimation,
  • Loss function,
  • Metropolis-Hastings algorithm,
  • Simulated risk

How to Cite

Goyal, T., Rai, P. K., Panwar, M. S., & Maurya, S. K. (2024). BAYESIAN INFERENCE FOR EXPONENTIATED INVERTED WEIBULL DISTRIBUTION IN PRESENCE OF PROGRESSIVE TYPE-II CENSORING. Italian Journal of Applied Statistics. https://doi.org/10.26398/IJAS.248

Copyright (c) 2024 Teena Goyal, Piyush K Rai, Mahaveer S Panwar, Sandeep K Maurya

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

The present article gives the point as well as interval estimates for the parameters and lifetime characteristics as reliability and hazard rate functions of the exponentiated inverted Weibull distribution in presence of progressive type-II censored data under classical and Bayesian approach. The point estimates under classical paradigm are obtained with the help of maximum likelihood estimation procedure and in case of Bayesian paradigm, gamma prior is used for both unknown parameters under squared error and linex loss functions. The Metropolis-Hasting algorithm is applied to generate MCMC samples from the posterior density. In case of interval estimation; bootstrap confidence intervals (Boot-t and Boot-p) and highest posterior density intervals for the unknown parameters are computed. The performance of these estimates are studied on the basis of their simulated risks and length of intervals. Additionally, a real dataset is used to illustrate the proposed censoring technique and a simulation study is used to support the given study.

PDF