![]() | Only 14 pages are availabe for public view |
Abstract In this thesis, apart from discretization techniques, we propose and study a new natural discrete analog of the Lindley distribution as a mixture of geometric and negative binomial distributions. The proposed model extends some recent discrete Lindley distributions like the discrete Lindley of Bakouch et al. (2014), the two-parameter discrete Lindley of Hussain et al. (2016).The new distribution has many interesting properties which make it superior to many other discrete distributions, particularly in analyzing over dispersed count data. Practical implications and future directions are also discussed at the conclusion of the study |