Testing for Threshold Effect in ARFIMA Models: Application to US Unemployment Rate Data

21 Pages Posted: 9 Dec 2008 Last revised: 23 Dec 2008

Amine Lahiani

Université Paris Ouest - Nanterre, La Défense - EconomiX

O. Scaillet

University of Geneva GSEM and GFRI; Swiss Finance Institute

Date Written: December 4, 2008

Abstract

Macroeconomic time series often involve a threshold effect in their ARMA representation, and exhibit long memory features. In this paper we introduce a new class of threshold ARFIMA models to account for this. The threshold effect is introduced in the autoregressive and/or the fractional integration parameters, and can be tested for using LM tests. Monte Carlo experiments show the desirable finite sample size and power of the test with an exact maximum likelihood estimator of the long memory parameter. Simulations also show that a model selection strategy is available to discriminate between the competing threshold ARFIMA models. The methodology is applied to US unemployment rate data where we find a significant threshold effect in the ARFIMA representation and a better forecasting performance over TAR and symmetric ARFIMA models.

Keywords: Threshold ARFIMA, LM test, Asymmetric time series

JEL Classification: C12, C13, C22

Suggested Citation

Lahiani, Amine and Scaillet , O., Testing for Threshold Effect in ARFIMA Models: Application to US Unemployment Rate Data (December 4, 2008). Swiss Finance Institute Research Paper No. 08-42. Available at SSRN: https://ssrn.com/abstract=1311866 or http://dx.doi.org/10.2139/ssrn.1311866

Amine Lahiani

Université Paris Ouest - Nanterre, La Défense - EconomiX ( email )

200 Avenue de la République
Nanterre cedex, Nanterre Cedex 92000
France

Olivier Scaillet (Contact Author)

University of Geneva GSEM and GFRI ( email )

40 Boulevard du Pont d'Arve
Geneva 4, 1211
Switzerland
+ 41 22 379 88 16 (Phone)
+41 22 389 81 04 (Fax)

HOME PAGE: http://www.scaillet.ch

Swiss Finance Institute

40, Boulevard du Pont-d'Arve
40, Bd du Pont-d'Arve
1211 Geneva 4, CH-6900
Switzerland

Paper statistics

Downloads
237
Rank
105,609
Abstract Views
1,613