Bivariate Poisson-Weighted Exponential Distribution with Applications

摘要

This paper proposes the bivariate version of Poisson-weighted exponential (PWE) distribution considered in Zamani and Ismail (2010). This new discrete bivariate Poisson-weighted exponential (BPWE) distribution can be used as an alternative for modeling dependent and over-dispersed count data. Several properties such as mean, variance, correlation and joint moment generating function of the new BPWE distribution are discussed. A numerical example is given and the BPWE distribution is compared to bivariate Poisson (BP) distribution. The results show that BPWE distribution provides larger log likelihood and smaller AIC, indicating that BPWE distribution is better than BP distribution and can be used as an alternative for fitting dependent and over-dispersed count data.