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 et al. (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.

Voir le document

Dernières publications

2018s-02 CS
The Logic of Collective Action Revisited
Jeannette Brosig-Koch, Timo Heinrich, Heike Hennig-Schmidt, Claudia Keser et Joachim Weimann
Voir le document

2018s-03 CS
Innovation in Humanitarian Supply Chains: A Systematic Review
Nezih Altay, Graham Heaslip, Gyöngyi Kovács, Karen Spens, Peter Tatham et Alain Vaillancourt
Voir le document

2018RP-06 RP
Adéquation des transferts aux besoins des municipalités. Quelques réflexions sur les enjeux d’équité et d’efficacité
Stéphanie Boulenger, Jean-Philippe Meloche, Brigitte Milord et François Vaillancourt
Voir le document

Centre interuniversitaire de recherche en analyse des organisations
1130 rue Sherbrooke Ouest, suite 1400
Montréal, Québec (Canada) H3A 2M8
(514) 985-4000
(514) 985-4039

© 2018 CIRANO. Tous droits réservés.

Partenaire de :