Sep 6 – 10, 2026
Centro Didattico Morgagni
Europe/Rome timezone

INAR(1) Processes based on the Zipf-PSS distribution

Not scheduled
20m
Centro Didattico Morgagni

Centro Didattico Morgagni

Viale Morgagni 40, Firenze
Time Series, Forecasting and Dynamic Systems

Speaker

Marta Perez-Casany (Universitat Politècnica de Catalunya)

Description

The Zipf-PSS distribution is a Poisson Stopped-Sum with a Zipf distribution as secondary distribution. In this work, we consider two INAR(1) processes: The Zipf-PSS-INAR(1) innovations process, whose innovations follow a Zipf-PSS distribution, and the Zipf-PSS-INAR(1) marginal process, whose stationary marginal distribution is Zipf-PSS. Working with the marginal process is more complex than working with the innovation process, because it requires to compute the unknown distribution of the innovations. Nevertheless, the distribution of the innovation has a notable feature: it depends on the survival parameter (a larger survival parameter implies less immigration). This property is appealing from an applied perspective, and it is never achieved in the INAR(1) processes which are defined specifiying the innovation distribution. A practical parameter interpretation of the two processes is provided, and their performance fitting real time series is compared with the Possion INAR(1) and the NB-INAR(1) processes.

Classification Both methodology and application
Keywords INAR(1), Zipf, Poisson-Stopped-Sum

Primary authors

Dr Ariel Duarte-López (Technical University of Catalonia) Dr Manuel Gonzalez Scotto (Técnico de Lisboa) Marta Perez-Casany (Universitat Politècnica de Catalunya)

Presentation materials

There are no materials yet.