On rank tests for shift detection in time series

Robustified rank tests, applying a robust scale estimator, are investigated for reliable and fast shift detection in time series. The tests show good power for sufficiently large shifts, low false detection rates for Gaussian noise and high robustness against outliers. Wilcoxon scores in combination with a robust and efficient scale estimator achieve good performance in many situations. © 2007 Elsevier B.V. All rights reserved.

• Type: Journal
• Year: 2007
• Where: CSDA
• Authors: Roland Fried, Ursula Gather
• Keywords: CSDA 2007, Fast Shift Detection, Low False Detection, Robust Scale Estimator