TY - JOUR
T1 - A Bayesian approach to testing for Markov-switching in univariate and dynamic factor models
AU - Kim, Chang Jin
AU - Nelson, Charles R.
PY - 2001/11
Y1 - 2001/11
N2 - Though Hamilton's (1989) Markov-switching model has been widely estimated in various contexts, formal testing for Markov-switching is not straight-forward. Univariate tests in the classical framework by Hansen (1992) and Garcia (1998) do not reject the linear model for GDP. We present Bayesian tests for Markov-switching in both univariate and multivariate settings based on sensitivity of the posterior probability to the prior. We find that evidence for Markov-switching, and thus the business cycle asymmetry, is stronger in a switching version of the dynamic factor model of Stock and Watson (1991) than it is for GDP by itself.
AB - Though Hamilton's (1989) Markov-switching model has been widely estimated in various contexts, formal testing for Markov-switching is not straight-forward. Univariate tests in the classical framework by Hansen (1992) and Garcia (1998) do not reject the linear model for GDP. We present Bayesian tests for Markov-switching in both univariate and multivariate settings based on sensitivity of the posterior probability to the prior. We find that evidence for Markov-switching, and thus the business cycle asymmetry, is stronger in a switching version of the dynamic factor model of Stock and Watson (1991) than it is for GDP by itself.
UR - http://www.scopus.com/inward/record.url?scp=0347751009&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0347751009&partnerID=8YFLogxK
U2 - 10.1111/1468-2354.00143
DO - 10.1111/1468-2354.00143
M3 - Article
AN - SCOPUS:0347751009
SN - 0020-6598
VL - 42
SP - 989
EP - 1013
JO - International Economic Review
JF - International Economic Review
IS - 4
ER -