A Markov Switching Model of GNP Growth With Duration Dependence

We use a regime-switching model of real GNP growth to examine the duration dependence of business cycles. The model extends Hamilton (1989) and Durland and McCurdy (1994) and is estimated using both the postwar NIPA data and the secular data constructed by Balke-Gordon. We find that an expansion is more likely to end at a young age, that a contraction is more likely to end at an old age, that output growth slows over the course of an expansion, that a decline in output is mild at the beginning of a contraction, and that long expansions are followed by long contractions. This evidence taken together provides no support for the clustering of the whole-cycle around seven-to-ten year durations. *This work was initiated while the author was a visiting scholar at the Institute For Empirical Macroeconomics, Federal Reserve Bank of Minneapolis, from July 2 to August 15, 1995. The author would like to thank the Institute for its hospitality and financial support. The paper has benefited from comments received from Stephen Cecchetti, G. S. Maddala, Nelson Mark, Huston McCulloch, Bruce Weinberg and the participants of a brown bag lunch at the Institute For Empirical Macroeconomics. The remaining shortcomings are solely those of the author. The views expressed herein are those of the author and not necessarily those of the Federal Reserve Bank of Minneapolis or the Federal Reserve System.