Centre for Mathematics, University of Coimbra

<Reference List>
Type:	Preprint
National /International:	International
Title:	Zero-truncated compound Poisson integer-valued GARCH models for time series
Publication Date:	2016-09-29
Authors:	- Esmeralda Gonçalves - Nazaré Mendes-Lopes
Abstract:	Starting from the Compound Poisson INGARCH models ([3]), we introduce in this paper a new family of integer-valued models suitable to describe count data without zeros that we name Zero Truncated CP-INGARCH processes. For such class of models, a probabilistic study concerning stationarity, ergodicity and moments existence is developed. The conditional maximum likelihood method is used to consistently estimate the parameters of the conditional Poisson subfamily of models, for which the main asymptotic properties are analyzed. A simulation study illustrating the finite distance behavior of those estimators and a real-data application conclude the paper.
Institution:	DMUC 16-42
Online version:	http://www.mat.uc.pt...prints/eng_2016.html
Download:	Not available