Premium
Comment on ‘Type I error and test power of different tests for testing interaction effects in factorial experiments’
Author(s) -
Konietschke Frank,
Gao Xin,
Bathke Arne C.
Publication year - 2013
Publication title -
statistica neerlandica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.52
H-Index - 39
eISSN - 1467-9574
pISSN - 0039-0402
DOI - 10.1111/stan.12014
Subject(s) - type i and type ii errors , factorial , factorial experiment , rank (graph theory) , mathematics , transformation (genetics) , statistics , fractional factorial design , type (biology) , test (biology) , power (physics) , combinatorics , mathematical analysis , ecology , paleontology , biology , biochemistry , chemistry , physics , quantum mechanics , gene
We discuss the rank transform method and particularly the hypotheses being tested. Some counter examples show that the rank transformation method is invalid in factorial designs.