CMStatistics 2017: Start Registration
View Submission - CMStatistics
Title: Robust change-point estimation Authors:  Carina Gerstenberger - Ruhr-Universitaet Bochum (Germany) [presenting]
Abstract: In many applications it cannot be assumed that observed data have a constant mean over time. Therefore, extensive research has been done in testing for change-points and estimation of the change-point location. However, just a few procedures are robust against outliers in the data. We introduce estimators of the location parameter for the change-point in the mean based on U-statistics and establish consistency under short-range dependence. In a simulation study we will see that a suitable choice of the kernel function yields estimators that are robust to outliers and heavy-tailed distributions.