Estatísticas de ordem superior dos modelos INAR

Abstract

During the last decades, the high-order statistics of a stochastic process have been applied in several fields, specially in problems where is conjectured a lack of Gaussianity and/or non-linearity. In this work, the INteger-valued AutoRegressive, INAR, process, which is a non-linear process, is considered. Two estimation methods for the parameters of an INAR model that use high-order statistics are proposed. A Monte Carlo study, to investigate the performance of the estimators, is carried out. Finally, these methods are applied to a set of observations consisting in the number of body movements of newborn babies.