Multivariate Count Time Series Modelling

TL;DR

This paper reviews autoregressive models for multivariate count time series, discussing distribution choices and three main modeling approaches, highlighting recent developments and proposing future research directions.

Contribution

It provides a comprehensive review of existing methods for multivariate count time series analysis and suggests new research avenues.

Findings

Comparison of three main modeling approaches

Discussion on distribution choices for count vectors

Identification of recent methodological advancements

Abstract

We review autoregressive models for the analysis of multivariate count time series. In doing so, we discuss the choice of a suitable distribution for a vectors of count random variables. This review focus on three main approaches taken for multivariate count time series analysis: (a) integer autoregressive processes, (b) parameter-driven models and (c) observation-driven models. The aim of this work is to highlight some recent methodological developments and propose some potentially useful research topics.