A Bayesian Approach to Testing for Markov Switching in Univariate and Dynamic Factor Models

40 Pages Posted: 12 Mar 1999

See all articles by Chang-Jin Kim

Chang-Jin Kim

Dept. of Economics, University of Washington

Charles R. Nelson

Dept of Economics

Abstract

Though Hamilton's (1989) Markov switching model has been widely estimated in various contexts, formal testing for Markov switching is not straightforward. 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.

JEL Classification: C22, C32

Suggested Citation

Kim, Chang-Jin and Nelson, Charles R., A Bayesian Approach to Testing for Markov Switching in Univariate and Dynamic Factor Models. Available at SSRN: https://ssrn.com/abstract=148299 or http://dx.doi.org/10.2139/ssrn.148299

Chang-Jin Kim (Contact Author)

Dept. of Economics, University of Washington ( email )

Department of Economics (Box 353330)
University of Washington
Seattle, WA 98195-3330
United States

HOME PAGE: http://https://econ.washington.edu/people/chang-jin-kim

Charles R. Nelson

Dept of Economics ( email )

Box 353330
Seattle, WA 98195-3330
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
301
Abstract Views
1,777
rank
127,496
PlumX Metrics