Download this Paper Open PDF in Browser

Identification-Robust Moment-Based Tests for Markov-Switching in Autoregressive Models

22 Pages Posted: 1 Jan 2017  

Jean-Marie Dufour

McGill University

Richard Luger

Université Laval

Date Written: December 30, 2016

Abstract

This paper develops tests of the null hypothesis of linearity in the context of autoregressive models with Markov-switching means and variances. These tests are robust to the identification failures that plague conventional likelihood-based inference methods. The approach exploits the moments of normal mixtures implied by the regime-switching process and uses Monte Carlo test techniques to deal with the presence of an autoregressive component in the model specification. The proposed tests have very respectable power in comparison to the optimal tests for Markov-switching parameters of Carrasco-Hu-Ploberger (2014} and they are also quite attractive owing to their computational simplicity. The new tests are illustrated with an empirical application to an autoregressive model of U.S. output growth.

Keywords: Mixture distributions, Markov chains, Regime switching, Parametric bootstrap, Monte Carlo tests, Exact inference

JEL Classification: C12, C15, C22, C52

Suggested Citation

Dufour, Jean-Marie and Luger, Richard, Identification-Robust Moment-Based Tests for Markov-Switching in Autoregressive Models (December 30, 2016). Available at SSRN: https://ssrn.com/abstract=2891810

Jean-Marie Dufour (Contact Author)

McGill University ( email )

Department of Economics, McGill University
Leacock Building Room 443, 855 Sherbrooke West
Montreal, Quebec H3A 2T7
Canada
(1) 514 398 6071 (Phone)
(1) 514 398 4800 (Fax)

HOME PAGE: http://www.jeanmariedufour.com

Richard Luger

Université Laval ( email )

Université Laval
Département de finance, assurance et immobilier
Quebec City, Quebec
Canada

Paper statistics

Downloads
13
Abstract Views
107