A0813
Title: Improving the accuracy of bubble date estimators under time-varying volatility
Authors: Anton Skrobotov - Russian Presidential Academy of National Economy and Public Administration and SPBU (Russia) [presenting]
Eiji Kurozumi - Hitotsubashi University (Japan)
Abstract: A four-regime bubble model is considered under the assumption of time-varying volatility and the algorithm of estimating the break dates with volatility correction is proposed: first, the emerging date of the explosive bubble, its collapsing date, and the recovering date is estimated for the normal market under the assumption of homoskedasticity; second, the residuals are collected and then the WLS-based estimation of the bubble dates is employed. It is demonstrated by Monte Carlo simulations that the accuracy of the break dates estimators improve significantly by this two-step procedure in some cases compared to those based on the OLS method.
