A0409
Title: Parameter estimation of ADCINAR($p$) process
Authors: Xiaoqiang Zeng - Guangdong University of Education (China) [presenting]
Yoshihide Kakizawa - Hokkaido University (Japan)
Abstract: The analysis of count time series has made rapid progress during the last few decades. There is a huge amount of literature about the formulations of models and parameter estimation. Among them, the focus is on nonnegative integer-valued autoregressive (INAR) type processes based on the thinning operation. An alternative dependent counting INAR process of the $p$th-order is introduced. To estimate the model parameter and the innovation mean and variance, the CLS and two-step CLS methods are first applied. The QML method is next applied. The resulting estimators are shown to be strongly consistent and asymptotically normal.
