Comparing the performance of nonparametric tests for equality of location against ordered alternatives


ALTUNKAYNAK B., GAMGAM H.

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, vol.50, no.1, pp.63-84, 2021 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 50 Issue: 1
  • Publication Date: 2021
  • Doi Number: 10.1080/03610918.2018.1547403
  • Journal Name: COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Business Source Elite, Business Source Premier, CAB Abstracts, Compendex, Computer & Applied Sciences, Veterinary Science Database, zbMATH, Civil Engineering Abstracts
  • Page Numbers: pp.63-84
  • Gazi University Affiliated: Yes

Abstract

This study evaluated the performance of 8 tests that are found to be better than others in the previous simulation studies for some subset of proposed tests. As an innovation, in order to determine which design factor was more effective on the power values and which test was appropriate for which design, a decision tree was established. If there is a prior knowledge of the shape of ordered alternative, the Adaptive Test for the linear ordered alternative, and the Shan's S test for the convex ordered alternative, is recommended. However, the Terpstra-Page test is proposed for the concave ordered alternatives.