Functional form for the Zero - Inflated generalized Poisson regression model

Functional form for the Zero - Inflated generalized Poisson regression model

The generalized Poisson (GP) is an increasingly popular approach for modeling overedispersed as well as underdispersed count data. Several ཆ ཆ་རྒྱས་ parameterizations have been performed for the GP. Such as GP-1. GP-2 and the GP-P model which recently has been proposed. This paper develops a functional form of the ZIGP regression model that parametrically nests the ZIP and the two well known ZIGP regression models (ZIGP-1 and ZIGP-2). The proposed model has the advantage of allowing a statistical test of the pro s A k ZIGP-1 and the ZIGP-2 against a more general alternative. The ZIP and the ZIGP regression models are fitted, compared and tested on insurance count tiafa.