A comment on Mendes and Yiit (2013), 'Type I error and test power of different tests for testing interaction effects in factorial experiments', Statistica Neerlandica, 67:1-26

• Published in: Statistica Neerlandica Vol. 67; no. 4; p. 397
• Main Authors: Shah, Denis A, Madden, Laurence V
• Format: Journal Article
• Language: English
• Published: Oxford Blackwell Publishing Ltd 01-11-2013
• Subjects: Factorial experiments; Statistical analysis; Studies
• ISSN: 0039-0402; 1467-9574
• DOI: 10.1111/stan.12013

In their advocacy of the rank-transformation (RT) technique for analysis of data from factorial designs, Mendes and Yiit (Statistica Neerlandica, 67, 2013, 1-26) missed important analytical studies identifying the statistical shortcomings of the RT technique, the recommendation that the RT technique not be used, and important advances that have been made for properly analyzing data in a non-parametric setting. Applied data analysts are at risk of being misled by Mendes and Yiit, when statistically sound techniques are available for the proper non-parametric analysis of data from factorial designs. The appropriate methods express hypotheses in terms of normalized distribution functions, and the test statistics account for variance heterogeneity. [PUBLICATION ABSTRACT]