Title: Optimal estimation of change-points in time series
Authors: Chun Yip Yau - Chinese University of Hong Kong (Hong Kong) [presenting]
Abstract: Asymptotic theory is established for the optimal estimation of change-points in time series. We show that the Bayes estimator is asymptotically efficient for change-point estimation under mean squared error loss. Two subsampling procedures are developed to construct confidence intervals for the change-points. Simulations and real data applications are presented to investigate the finite sample performance of the Bayes estimator and the two subsampling procedures.