Fiche du document
juin 2019
- handle: 10670/1.8b8zqk
- hal: hal-04582262
Sujets proches
Service of process Service of papers Abuse of process ProcessCiter ce document
Serge Darolles et al., « Bivariate integer-autoregressive process with an application to mutual fund flows », HALSHS : archive ouverte en Sciences de l’Homme et de la Société, ID : 10670/1.8b8zqk
Métriques
Partage / Export
Résumé
We propose a new family of bivariate nonnegative integer-autoregressive (BINAR)models for count process data. We first generalize the existing BINAR(1) model byallowing for dependent thinning operators and arbitrary innovation distribution. Theextended family allows for intuitive interpretation, as well as tractable aggregationand stationarity properties. We then introduce higher order BINAR(p) and BINAR(∞)dynamics to accommodate more flexible serial dependence patterns. So far, the literaturehas regarded such models as computationally intractable. We show that the extendedBINAR family allows for closed-form predictive distributions at any horizons and forany values of p, which significantly facilitates non-linear forecasting and likelihoodbased estimation. Finally, a BINAR(∞) model with memory persistence is applied toopen-ended mutual fund purchase and redemption order counts