Estimating a Taylor Rule with Markov Switching Regimes for Switzerland

Alexander Perruchoud
Swiss Journal of Economics and Statistics / Schweizerische Zeitschrift für Volkswirtschaft und Statistik / Revue Suisse d'Economie politique et de Statistique, Volume 145, Issue 2, 2009, Pages 187-220
Download Browse issue

Keywords

Taylor rule, Markov switching, Non-constant transition probabilities, Maximum likelihood, EM algorithm

Abstract

In this paper a Taylor rule including the exchange rate gap is estimated for Switzerland under the assumption that the parameters depend on two states governed by a Markov switching process. The estimates suggest the presence of an ordinary and an aggressive regime. The former is characterized by a high degree of interest rate smoothing and by significant reactions to inflation and the output gap. The aggressive regime shows much less smoothing, an aggressive reaction to inflation, and a large coefficient on the exchange rate gap. Furthermore, an asymmetry in the occurrence of the two regimes is found.