Title of article
Integer Valued AR(1) with Geometric Innovations
Author/Authors
Aghababaei Jazi, Mansour university of sistan and baluchestan - Faculty of Mathematics, زاهدان, ايران , Jones, Geoff Massey University - Institute of Fundamental Sciences, New Zealand , Lai, Chin-Diew Massey University - Institute of Fundamental Sciences, New Zealand
From page
173
To page
190
Abstract
The classical integer valued first-order autoregressive (INA- R(1)) model has been defined on the basis of Poisson innovations. This model has Poisson marginal distribution and is suitable for modeling equidispersed count data. In this paper, we introduce an modification of the INAR(1) model with geometric innovations (INARG(1)) for model- ing overdispersed count data. We discuss some structural mathematical properties of the process comparing with classical INAR(1). Also, the superiority of the model in contrast with the INAR(1) is shown by some real time series
Keywords
Binomial thinning operator , conditional maximum likeli , hood estimation , infinitely divisible distributions , mixture distributions
Journal title
Journal of the Iranian Statistical Society (JIRSS)
Journal title
Journal of the Iranian Statistical Society (JIRSS)
Record number
2578579
Link To Document