Publication at Faculty of Mathematics and Physics |
2009
Abstract
We study test procedures that detect structural breaks in underlying data sequences. In particular, we wish to discriminate between reasons for these changes, such as shifting means, random walk behavior, and constant means but innovations switching from stationary to difference stationary behavior.
Almost all procedures presently available in the literature are simlutaneously sensitive to all these types of alternatives. The results are underlined by a simulation study and an application to returns of the German stock index DAX.