Maria da Conceição Costa
Departamento de Matemática e CIDMA, Universidade de Aveiro
The analysis of low integer-valued time series is an area of growing interest as time series of small non-negative counts have become available in a wide variety of contexts over the last years. In this work we focus our attention in a particular class of observation-driven models and introduce an asymmetric power autoregressive conditional Poisson model for the analysis of time series of counts exhibiting asymmetric overdispersion. Basic probabilistic and statistical properties of the INAPARCH (p, q) model (INteger-valued Asymmetric Power ARCH model) are presented. Parameter estimation is also addressed and the conditional maximum likelihood (ML) estimation method is applied. The asymptotic theory related to the ML estimation procedure is established. Finally, a simulation study and an empirical application to a set of data concerning the daily number of stock transactions are presented to better illustrate the proposed model.
