An Extension of the Birnbaum-Saunders Distribution Based on Skew-Normal t Distribution

Abstract

Abstract. In this paper, we introducte a family of univariate BirnbaumSaunders distributions arising from the skew-normal-t distribution. We obtain several properties of this distribution such as its moments, the maximum likelihood estimation procedure via an EM-algorithm and a method to evaluate standard errors using the EM-algorithm. Finally, we apply these methods to a real data set to demonstrate its flexibility and conduct a simulation study to demonstrate the usefulness of this distribution when compared to the ordinary Birnbaum-Saunders and skew-normal Birnbaum-Saunders distributions.