Exponential dispersion models for overdispersed zero-inflated count data

We consider two classes of exponential dispersion models discrete probability distributions which are defined by specifying their variance functions in mean value parameterization. These were considered our earlier paper as overdispersed zero-inflated distributions. In this we analyze the application these to fit count data having and statistics. For reason, first elaborate on computational aspects distributions, before fitting with models. execute an extensive comparison other statistical that recently proposed, both real sets, simulated sets. Our findings framework is a flexible tool gives excellent results wide range cases. Moreover, specifically when characteristics show also large skewness kurtosis perform best.