Munich Personal RePEc Archive

Conditional Markov chain and its application in economic time series analysis

Bai, Jushan and Wang, Peng (2011): Conditional Markov chain and its application in economic time series analysis. Published in: Journal of Applied Econometrics , Vol. 26, No. 5 (August 2011): pp. 715-734.

[img]
Preview
PDF
MPRA_paper_33369.pdf

Download (266kB) | Preview

Abstract

Motivated by the great moderation in major U.S. macroeconomic time series, we formulate the regime switching problem through a conditional Markov chain. We model the long-run volatility change as a recurrent structure change, while short-run changes in the mean growth rate as regime switches. Both structure and regime are unobserved. The structure is assumed to be Markovian. Conditioning on the structure, the regime is also Markovian, whose transition matrix is structure-dependent. This formulation imposes interpretable restrictions on the Hamilton Markov switching model. Empirical studies show that this restricted model well identifies both short-run regime switches and long-run structure changes in the U.S. macroeconomic data.

UB_LMU-Logo
MPRA is a RePEc service hosted by
the Munich University Library in Germany.