Determination of Best Variable Set for Count Models by Particle Swarm Optimization

In most scientific studies quantitative data are used which take non-negative integer values, called count data. Count data are also used frequently in the context of regression analysis, which is one of the most basic analysis methods of statistical analysis. The regression models in which the dependent variable can be expressed by integers are defined as count models. In this study, the model selection in the context of count models was investigated by using classical selection methods and PSO algorithm. Applications were made on both simulation and real data. As a result, it has been shown that PSO algorithm can be used as an alternative method for PSO algorithm selection for count models when the number of model variables increases and the correlation values between independent variables increases as compared to classical methods