NOVA GENERALIZAÇÃO PARA A CLASSE BETA-G DE DISTRIBUIÇÕES DE PROBABILIDADE

Main Article Content

Glaucia Tadu de SOUZA
Wilson Rosa de OLIVEIRA JUNIOR
Cícero Carlos Ramos de BRITO
Frank Sinatra GOMES-SILVA
Ronaldo Venâncio da SILVA

Abstract

We propose a new generator of continuous distributions with three extra parameters called the Beta (θ(1 - G); (1 - θ)G + θ), which generalizes the Beta-G class. A special case is presented. The new density function can be expressed as a difference of linear combinations of exponentiated densities based on the same baseline distribution. Various structural properties of the new class, which hold for any baseline model, are derived including explicit expressions for the moments of order n, the moment generating function, the characteristic function, central moments of order n, the general coefficient, the mean deviations, residual life function, reverse residual life function and order statistics. We discuss estimation of the model parameters by maximum likelihood and provide an application to a real data set.

Article Details

How to Cite
SOUZA, G. T. de, OLIVEIRA JUNIOR, W. R. de, BRITO, C. C. R. de, GOMES-SILVA, F. S., & SILVA, R. V. da. (2017). NOVA GENERALIZAÇÃO PARA A CLASSE BETA-G DE DISTRIBUIÇÕES DE PROBABILIDADE. Brazilian Journal of Biometrics, 35(4), 785–809. Retrieved from http://www.biometria.ufla.br/index.php/BBJ/article/view/153
Section
Articles
Author Biographies

Frank Sinatra GOMES-SILVA, Universidade Federal Rural de Pernambuco

Departamento de Estatística e Informática

Ronaldo Venâncio da SILVA, Colégio Militar do Recife

Colégio militar do Recife

Most read articles by the same author(s)