Objective Bayesian analysis for the Lomax distribution

Paulo H. Ferreira, Eduardo Ramos, Pedro L. Ramos, Jhon Franky Bernedo Gonzales, Vera L.D. Tomazella, Ricardo S. Ehlers, Eveliny B. Silva, Francisco Louzada

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

In this paper, we propose to make Bayesian inferences for the parameters of the Lomax distribution using non-informative priors, namely the (dependent and independent) Jeffreys prior and the reference prior. We assess Bayesian estimation through a Monte Carlo study with 10,000 simulated datasets. In order to evaluate the possible impact of prior specification on estimation, two criteria were considered: the mean relative error and the mean square error. An application on a real dataset illustrates the developed procedures.

Original languageEnglish
Article number108677
JournalStatistics and Probability Letters
Volume159
DOIs
StatePublished - Apr 2020

Bibliographical note

Funding Information:
The authors are grateful to the Editor and the two reviewers for their helpful and useful comments that improved the manuscript. Pedro L. Ramos is grateful to the São Paulo State Research Foundation, Brazil (FAPESP Proc. 2017/25971-0 ). Appendix A

Funding Information:
The authors are grateful to the Editor and the two reviewers for their helpful and useful comments that improved the manuscript. Pedro L. Ramos is grateful to the S?o Paulo State Research Foundation, Brazil (FAPESP Proc. 2017/25971-0).

Publisher Copyright:
© 2019 Elsevier B.V.

Keywords

  • Jeffreys prior
  • Lomax distribution
  • Objective Bayesian analysis
  • Reliability

Fingerprint

Dive into the research topics of 'Objective Bayesian analysis for the Lomax distribution'. Together they form a unique fingerprint.

Cite this