A New Poisson Generalized Lindley Regression Model

Abstract

In this paper, a new count distribution is introduced. It is a mixture of the Poisson and generalized Lindley distributions. Statistical properties of the proposed distribution including the factorial moments, probability generating function, moment generating function and moments are studies. Maximum likelihood estimators of unknown parameters are derived. Moreover, an alternative count regression model based on the proposed distribution is presented. Finally, the proposed model is applied for real data and compared with other well-known models.