Title: Date-stamping multiple bubble regimes
Authors: Dave Harvey - University of Nottingham (United Kingdom)
Steve Leybourne - University of Nottingham (United Kingdom)
Emily Whitehouse - Newcastle University (United Kingdom) [presenting]
Abstract: Identifying the start and end dates of explosive bubble regimes has become a prominent issue in the econometric literature. Recent research has demonstrated the advantage of a model-based minimum sum of squared residuals estimator, combined with Bayesian Information Criterion (BIC) model selection, over recursive unit root testing methods in providing accurate date estimates for a single bubble. However, in the context of multiple bubbles, a large number of models are possible, making such a model-based method unattractive to practitioners. We propose a two-step procedure for dating multiple bubbles. First, recursive unit root tests are used to identify a `date window' in which we believe a bubble starts and ends. Second, a model-based BIC approach is used to estimate the regime change points within each window. Monte Carlo simulations highlight the effectiveness of our procedure. In addition, our method allows us to distinguish between different types of bubble behaviour (such as whether or not each bubble crashes before reverting back to a unit root process) and date these crash regimes. The advantages of our procedure over existing methods of bubble dating are shown through empirical application to financial and macroeconomic time series.