Do leading indicators really predict Australian business cycle turning points?

In earlier work, Layton (1994) demonstrated how Hamilton's (1991) quasi-bayesian, markov (constant transition probability parameters), regime-switching model could be used to characterize the nature of the Australian business cycle. However, Diebold, Lee and Weinbach (1992), Durland and McCurdy (1994), and Filardo(1994) have suggested approaches which allow the markov transition probabilities to be non-constant. In this paper the Australian coincident index is employed as a summative measure of the business cycle and the transition probability parameters are allowed to vary. In particular, leading and long leading indexes are used as putative determinants of these transition probabilities to test whether, in this framework, these indexes systematically influence the probability of phase changes in the business cycle.