All Rights Reserved
AccessEcon LLC 2006, 2008.
Powered by MinhViet JSC

Katsuhiro Sugita
''Bayesian inference in Markov switching vector error correction model''
( 2016, Vol. 36 No.3 )
In this paper we consider a Bayesian approach to a Markov switching vector error correction model that allows for regime shifts in the number of cointegrating rank, the cointegrating vectors, the adjustment terms, the deterministic terms, the lag terms and the variance-covariance matrix. We use a valid prior for the cointegrating space, and sample the state variable by employing the multi-move Gibbs sampler, and estimate the cointegrating vectors by a collapsed Gibbs sampler. We also drive the posterior densities for the model where cointegrating vectors are regime-independent.
Keywords: Bayesian, Markov switching, cointegration
JEL: C4 - Econometric and Statistical Methods: Special Topics
C5 - Econometric Modeling: General
Manuscript Received : Feb 24 2016 Manuscript Accepted : Aug 11 2016

  This abstract has been downloaded 1315 times                The Full PDF of this paper has been downloaded 153793 times