Neutrosophic Birnbaum-Saunders distribution with applications

TL;DR

This paper introduces a neutrosophic extension of the Birnbaum-Saunders distribution to better handle uncertain and imprecise data, providing maximum likelihood estimates and demonstrating practical applications in industry and environment.

Contribution

It presents the first neutrosophic Birnbaum-Saunders distribution, enhancing data modeling under uncertainty and offering a new approach for imprecise data analysis.

Findings

Improved data modeling with neutrosophic BSD

Maximum likelihood estimates derived for the model

Successful application in industrial and environmental cases

Abstract

Classical statistics deals with determined and precise data analysis. But in reality, there are many cases where the information is not accurate and a degree of impreciseness, uncertainty, incompleteness, and vagueness is observed. In these situations, uncertainties can make classical statistics less accurate. That is where neutrosophic statistics steps in to improve accuracy in data analysis. In this article, we consider the Birnbaum-Saunders distribution (BSD) which is very flexible and practical for real world data modeling. By integrating the neutrosophic concept, we improve the BSD's ability to manage uncertainty effectively. In addition, we provide maximum likelihood parameter estimates. Subsequently, we illustrate the practical advantages of the neutrosophic model using two cases from the industrial and environmental fields. This paper emphasizes the significance of the neutrosophic BSD as a robust solution for modeling and analysing imprecise data, filling a crucial gap left by classical statistical methods.