CFE 2019: Start Registration
View Submission - CMStatistics
B1880
Title: A new flexible Birnbaum Saunders model Authors:  Guillermo Martinez-Florez - Universidad de Cordoba (Colombia)
Inmaculada Barranco-Chamorro - Universidad de Sevilla (Spain) [presenting]
Heleno Bolfarine - University of Sao Paulo (Brazil)
Hector W Gomez - Universidad de Antofagasta (Chile)
Abstract: The Birnbaum-Saunders (BS) distribution was originally introduced to model the fatigue in lifetime of certain materials. During the last decades, mainly due to its good properties, the use of this model spread out to other fields, such as economics and environmental sciences. In these applied scenarios, quite often, departures of the BS model are found, and therefore it is necessary to introduce some improvements. We focus on those situations in which extra asymmetry or bimodality are present in our data, and a generalization of the BS model should be considered. Our proposal is based on the flexible skew-normal and includes, as particular cases, the BS and skew BS distribution. The key aspects of this model, which properly combined result in the flexible BS model, are asymmetry, bimodality and main features of basic BS model. Theoretical properties are studied. Parameter estimation is considered via an iterative maximum likelihood algorithm. Two real applications, of interest in environmental sciences, are included, which reveal that our proposal can perform better than other compelling models.