B0760
Title: Estimating a constrained regime-switching model by means of the EM-algorithm
Authors: Andrea Beccarini - University of Münster (Germany) [presenting]
Abstract: A new method is proposed for estimating regime-switching models when some slope parameters are constrained to be non-regime-switching. It is shown that the constrained parameters are simply found by an appropriate weighted average of the unconstrained parameters. The advantage of this approach is twofold. First, the constrained estimates are obtained by an unconstrained estimation procedure such as the EM-algorithm, and hence they are relatively easy to implement. Secondly, as the constrained and unconstrained estimators are available, testing based on Likelihood-Ratio and model selection by means of likelihood-based information criteria are particularly simple. The procedure is applied to a three-state Markov-switching variance model.
