Analyzing and solving the identifability problem in the exponentiated generalized Weibull distribution | ||||
Journal of the Egyptian Mathematical Society | ||||
Volume 29, Issue 1, 2021, Page 1-17 PDF (2.84 MB) | ||||
Document Type: Original Article | ||||
DOI: 10.1186/s42787-021-00130-x | ||||
![]() | ||||
Authors | ||||
Felipe R. S. de Gusmão1; Frank Gomes‑Silva* 2; Cícero C. R. de Brito3; Fábio V. J. Silveira1; Jader S. Jale1; Sílvio F. A. Xavier‑Júnior4; Pedro R. D. Marinho5 | ||||
1DEINFO, Universidade Federal Rural de Pernambuco, Recife, Brazil. | ||||
2DEINFO, Universidade Federal Rural de Pernambuco, Recife, Brazil | ||||
3Instituto Federal de Pernambuco, Campus Recife, Recife, Brazil. | ||||
4Departamento de Estatística, Universidade Estadual da Paraíba, Campina Grande, Brazil. | ||||
5Departamento de Estatística, Universidade Federal da Paraíba, João Pessoa, Brazil. | ||||
Abstract | ||||
The well-known Weibull distribution can be used to model the decreasing and uni‑ modal failure rate quite standard in reliability and biological studies. It is also com‑ monly adopted as baseline to generate new distributions from generalized classes. In this paper, we investigate the identifability of the exponentiated generalized class of distributions and in particular the exponentiated generalized Weibull distribution. We also develop conditions under which the model becomes identifable. To further illustrate the identifability issue, we consider a simulation study, and an application is presented to illustrate the potentialities of the model with the new parameterization. | ||||
Keywords | ||||
Exponentiated; Generalized; Weibull; Identifability; Simulation; Application | ||||
Statistics Article View: 36 PDF Download: 22 |
||||