Agenda

14 Mag 2025 12:15

Andrew Harvey (University of Cambridge) - Score-driven autoregressions

Meeting Room 1, San Giobbe Economics Campus + online

Andrew Harvey (University of Cambridge) - Score-driven autoregressions

Abstract:

Score-driven time series models are now widely used in economics and statistics. The canonical model features a filter for a time-varying parameter that is a linear combination of its lagged value and the conditional score. It therefore depends on all the observations in the sample and invertibility must be established to ensure that reliable forecasts are made. Purely autoregressive score-driven models have not been considered in the literature and one of their attractions is that the question of invertibility does not arise. Score-driven autoregressions are proposed here and their properties are investigated. An alternative approach, whereby restrictions are imposed on a standard score-driven model,  is also considered. Both approaches can be modified by using what we call a "composite score".

The seminar can be attended also remotely, connecting to ZOOM.

Link Zoom: bit.ly/insem-2425
ID riunione:  880 2639 9452
Passcode: InSem-2425

Lingua

L'evento si terrà in inglese

Organizzatore

Department of Economics (InSeminars)

Link

http://bit.ly/insem-2425

Cerca in agenda