Zero inflation Poisson Regression estimation by using Genetic Algorithm (GA)
Main Article Content
Abstract
In this research, the phenomena that follow the models for dealing with numerical data, which take the form of time series, have been dealt with, the time series that take the numerical form often suffer from the problem of zero inflation, which represents a problem that cannot be overlooked, so a set of methods and methods have been proposed to deal with this problem, and one of the most important models in this case is Poisson's zero-inflated model. It should be noted here that there are a set of methods that are used for the purpose of estimating the parameters of the Poisson zero-amplified model, including the MLE method and the NLM method. In this paper, a genetic algorithm method was proposed for the purpose of improving the above estimates. The simulation and real data were used for the purpose of verifying the performance of the proposed method, where the research relied on the MSE standard for the purpose of comparison, which proved that the proposed method gave good results compared to other methods.