Modeling over-dispersed datasets using generalized geometric distributions
C. Satheesh Kumar, S. Harisankar · Journal of Statistical Computation and Simulation · 2019
Through this article we propose a class of over-dispersed distributions namely ‘the generalized geometric distribution (GGD)’ as an extension of the well-known ‘geometric distribution’. Also, we develop an extended version of it and named it as ‘the extended generalized geometric distribution (EGGD)’. Several properties of these classes of distributions are studied here. The maximum likelihood estimation of the parameters of the EGGD is discussed and fitted to certain real-life data sets for illustrating its usefulness compared to the existing models. Further, the generalized likelihood ratio test procedure is considered for testing the significance of the additional parameter of the EGGD model and a simulation study is carried out for assessing the performance of the estimators of each parameter of the model.