Non-Homogeneous Poisson Process to Model Seasonal Events: Application to the Health Diseases
Pages 337-346
María Victoria Cifuentes-Amado and Edilberto Cepeda-Cuervo
DOI: http://dx.doi.org/10.6000/1929-6029.2015.04.04.4
Published: 03 November 2015

Abstract: The daily number of hospital admissions due to mosquito-borne diseases can vary greatly. This variability can be explained by different factors such as season of the year, temperature and pollution levels, among others. In this paper, we propose a new class of non-homogeneous Poisson processes which incorporates seasonality factors to more realistically fit data related to rare events, and in particular we show how the modifications applied to the special NHPP intensity function improve the analysis and fit of daily hospital admissions, due to dengue in Ribeirão Preto, São Paulo state, Brazil.