Download this Paper Open PDF in Browser

Generalized Autoregressive Score Models in R: The GAS Package

26 Pages Posted: 21 Aug 2016 Last revised: 9 Sep 2016

David Ardia

University of Neuchatel - Institute of Financial Analysis; Laval University - Département de Finance et Assurance

Kris Boudt

Vrije Universiteit Brussel (VUB); VU University Amsterdam

Leopoldo Catania

University of Aarhus - School of Business and Social Sciences

Date Written: August 17, 2016

Abstract

This paper presents the R package GAS for the analysis of time series under the Generalized Autoregressive Score (GAS) framework of Creal et al. (2013) and Harvey (2013). The distinctive feature of the GAS approach is the use of the score function as the driver of time{variation in the parameters of nonlinear models. The GAS package provides functions to simulate univariate and multivariate GAS processes, estimate the GAS parameters and to make time series forecasts. We illustrate the use of the GAS package with a detailed case study on estimating the time-varying conditional densities of a set of financial assets.

Keywords: GAS, Time Series Models, Score Models, Dynamic Conditional Score, R Software

JEL Classification: C01, C22, C32, C53

Suggested Citation

Ardia, David and Boudt, Kris and Catania, Leopoldo, Generalized Autoregressive Score Models in R: The GAS Package (August 17, 2016). Available at SSRN: https://ssrn.com/abstract=2825380

David Ardia (Contact Author)

University of Neuchatel - Institute of Financial Analysis ( email )

Rue A.-L. Breguet 2
Neuchatel, CH-2000
Switzerland

Laval University - Département de Finance et Assurance ( email )

Pavillon Palasis-Prince
Quebec G1K 7P4
Canada

Kris Boudt

Vrije Universiteit Brussel (VUB) ( email )

Pleinlaan 2
http://www.vub.ac.be/
Brussels, 1050
Belgium

VU University Amsterdam ( email )

De Boelelaan 1105
Amsterdam, ND North Holland 1081 HV
Netherlands

Leopoldo Catania

University of Aarhus - School of Business and Social Sciences ( email )

Fuglesangs Allé 4
Aarhus V, DK-8210
Denmark

Paper statistics

Downloads
591
Rank
36,910
Abstract Views
1,675