A new generalized family of distributions: Properties and applications

Abstract

We come up with a new class called log-logistic tan generalized family which provides sub-models with left skewed, symmetrical, right skewed, unimodal, bimodal and reversed-J densities, and increasing, decreasing, modified bathtub, bathtub, unimodal, reversed-J shaped, and J-shaped hazard rates. Some of its sub-models are provided along with some general structural properties. The parameter estimation has been conducted via maximum likelihood. Moreover, the estimators behavior are assessed using various simulation results. The capability of the log-logistic tan-Weibull model is proved using two real-life data sets. It provides higher quality fit than competing Weibull extensions, among others.

Keywords

• bathtub failure rates
• maximum likelihood estimation
• order statistics
• simulation
• weibull distribution