COMPARING POISSON REGRESSION VIA NEGATIVE BINOMIAL REGRESSION FOR MODELING ZERO-INFLATED DATA

Zero inflation indicates that the data set includes a great number of zeros. Regression analysis is one of the generally applied statistical methods in data analysis. Occasionally researchers can count more additional zeros than precise ones. Outrageous zero may be defined as Zero-Inflation. Excess zeros cause over-dispersion. Zero inflated data are numerous in many disciplines. In marketing, econometrics, ecology, statistical quality control of the frequency of earthquakes, rainfall, etc., data with existing zeros is particularly common. The zero-inflated Poisson (ZIP) and zero-inflated Negative Binomial (ZINB) models in this article can be used to evaluate results.