Objective Bayesian analysis for the Lomax distribution

Autor(es)

Ferreira, Paulo H. ^[1] ; Ramos, Eduardo ^[2] ; Ramos, Pedro L. ^[2] ; Gonzales, Jhon F. B. ^[3] ; Tomazella, Vera L. D. ^[4] ; Ehlers, Ricardo S. ^[2] ; Silva, Eveliny B. ^[5] ; Louzada, Francisco ^[2]

Afiliação do(s) autor(es)

^[1] Univ Fed Bahia, Salvador, BA - Brazil

^[2] Univ Sao Paulo, Inst Math & Comp Sci, Sao Carlos, SP - Brazil

^[3] Univ Nacl San Agustin, Arequipa - Peru

^[4] Univ Fed Sao Carlos, Sao Carlos, SP - Brazil

^[5] Univ Fed Mato Grosso, Cuiaba, MG - Brazil

• Tipo de documento: Artigo Científico
• Fonte: Statistics & Probability Letters; v. 159, APR 2020.
• Citações Web of Science: 0

Resumo

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. (C) 2019 Elsevier B.V. All rights reserved. (AU)

• Processo FAPESP: 17/25971-0 - Inferência estatística de sistemas complexos
• Beneficiário: Pedro Luiz Ramos
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado