Using of generalized additive model for model selection in multiple poisson regression for air pollution data

Abstract

Multiple Poisson regression analysis is one of the most widely used statistical techniques in analysing air pollution data. It is a powerful tool when its assumptions are met, including that the relationships between the predictors and the response are a function such as straight-line, polynomial, or exponential. In many applications, however, the reliance on a defined mathematical function is difficult. Many phenomena do not have a relationship that can be easily defined. Generalized additive models (GAM) enable us to relax this assumption by replacing a defined function with a non-parametric smoother to uncover existing relationships. GAM can be used for model selection in multiple Poisson regression. This study focuses on GAM for model selection in multiple Poisson regression for modelling associations between air pollution and increases in hospital admissions for respiratory disease.