Title: Rank-based change-point analysis for long-range dependent time series
Authors: Annika Betken - Ruhr-Universitat Bochum (Germany) [presenting]
Martin Wendler - Ernst Moritz Arndt Universitaet Greifswald (Germany)
Abstract: Change-point tests based on rank statistics are considered to test for structural changes in long-range dependent observations. Under the hypothesis of stationary time series as well as under the assumption of a structural change in the data, i.e. under (local) alternatives approaching the null hypothesis of no change, the asymptotic distributions of the corresponding test statistics are derived. For this, we prove a uniform reduction principle for the empirical process in a two-parameter Skorohod space equipped with a weighted supremum norm. Theoretical results are accompanied by simulation studies that are based on an approximation of the distribution of test statistics by subsampling procedures. The finite sample performance of change-point tests is compared for rank statistics resulting from different score functions.