Title: A change detection procedure for an ergodic diffusion process
Authors: Koji Tsukuda - The University of Tokyo (Japan) [presenting]
Abstract: A test procedure to detect a change in values of drift parameters of an ergodic diffusion process is considered under the setting of continuous observation. For this problem, there is an approach based on the weak convergence of a random process relating to an estimating equation. Asymptotic null distributions of some test statistics are established by using this weak convergence result and the continuous mapping theorem. We show the weak convergence of a weighted version of the random process and propose a weighted test statistic.