The impact of an extreme observation in a paired samples design

Derrick, Ben; Broad, Antonia; Toher, Deirdre; White, Paul

Abstract

The effect of systematically altering the value of a single observation within a paired differences design is considered. A paradox is observed for the paired samples t-test, where increasing the value of an observation in the direction of the true mean difference results in a higher p-value. Using simulation, deviations from robustness of the paired samples t-test is demonstrated, and is contrasted with Yuen’s paired samples t-test and the Wilcoxon signed rank sum test.

• Journal Article Type: Article
• Acceptance Date: Oct 23, 2017
• Publication Date: Dec 31, 2017
• Deposit Date: Oct 25, 2017
• Publicly Available Date: Oct 25, 2017
• Journal: Metodološki Zvezki - Advances in Methodology and Statistics
• Print ISSN: 1854-0031
• Peer Reviewed: Peer Reviewed
• Volume: 14
• Issue: 2
• Pages: 1-17
• Keywords: impact, extreme, observation, paired samples design
• Public URL: https://uwe-repository.worktribe.com/output/901648
• Publisher URL: http://www.stat-d.si/mz/
• Contract Date: Oct 25, 2017