Riry Sriningsih, Bambang Widjanarko Otok, Sutikno
This paper discusses model formation which is a modification between multivariate adaptive regression spline (MARS) and generalized Poisson regression (GPR). The maximum likelihood estimation method (MLE) is performed to determine the estimation of model parameters. Furthermore, the model was applied to cases of dengue hemorrhagic fever (DHF) in Java. The results obtained are estimates of model parameters that are not closed form. Therefore, it was solved by the Bernd Hall Hausman (BHHH) numerical method. The results of the application get a very good model on the basis of function = 16, maximum interaction = 3, and minimum observation = 1. © 2024 Author(s).
Department of Statistics, Faculty of Science and Data Analytics, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia; Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Negeri Padang, Padang, Indonesia
