A new modified Lindley distribution with properties and applications
Christophe Chesneau, Lishamol Tomy, Jiju Gillariose
Abstract
This paper introduces a new one-parameter distribution derived from the Lindley distribution, called the modified Lindley distribution. Its main feature is to operate a simple trade-off between the exponential and Lindley distributions, offering an interesting alternative to these two well-established distributions. We study the main properties of the proposed distribution, with a special emphasis on its moments, reliability parameter and asymptotic distributions of the extreme order statistics. Then, inferential considerations are explored. We discuss the parameter estimation by the moments and maximum likelihood methods. Three applications reveal that the new model has the ability to fit well practical data sets.