Ghent University Academic Bibliography

Advanced

A Mann-Whitney type effect measure of interaction for factorial designs

Jan De Neve UGent and Olivier Thas UGent (2017) COMMUNICATIONS IN STATISTICS-THEORY AND METHODS. 46(22). p.11243-11260
abstract
We propose a measure for interaction for factorial designs that is formulated in terms of a probability similar to the effect size of the Mann-Whitney test. It is shown how asymptotic confidence intervals can be obtained for the effect size and how a statistical test can be constructed. We further show how the test is related to the test proposed by Bhapkar and Gore [Sankhya A, 36:261-272 (1974)]. The results of a simulation study indicate that the test has good power properties and illustrate when the asymptotic approximations are adequate. The effect size is demonstrated on an example dataset.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
Factorial designs, interaction, probability of superiority, rank test, Wilcoxon-Mann-Whitney, INTUITIVE NONPARAMETRIC APPROACH, PROBABILISTIC INDEX, RANK-TESTS, CONFIDENCE-INTERVALS, 2-WAY LAYOUTS, HYPOTHESES, STATISTICS, SIZE, TRANSFORM, MEDICINE
journal title
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
Commun. Stat.-Theory Methods
volume
46
issue
22
pages
11243 - 11260
Web of Science type
Article
Web of Science id
000412555500024
ISSN
0361-0926
DOI
10.1080/03610926.2016.1263739
language
English
UGent publication?
yes
classification
A1
copyright statement
I don't know the status of the copyright for this publication
id
8161041
handle
http://hdl.handle.net/1854/LU-8161041
date created
2016-11-21 09:38:56
date last changed
2018-02-22 10:08:42
@article{8161041,
  abstract     = {We propose a measure for interaction for factorial designs that is formulated in terms of a probability similar to the effect size of the Mann-Whitney test. It is shown how asymptotic confidence intervals can be obtained for the effect size and how a statistical test can be constructed. We further show how the test is related to the test proposed by Bhapkar and Gore [Sankhya A, 36:261-272 (1974)]. The results of a simulation study indicate that the test has good power properties and illustrate when the asymptotic approximations are adequate. The effect size is demonstrated on an example dataset.},
  author       = {De Neve, Jan and Thas, Olivier},
  issn         = {0361-0926},
  journal      = {COMMUNICATIONS IN STATISTICS-THEORY AND METHODS},
  keyword      = {Factorial designs,interaction,probability of superiority,rank test,Wilcoxon-Mann-Whitney,INTUITIVE NONPARAMETRIC APPROACH,PROBABILISTIC INDEX,RANK-TESTS,CONFIDENCE-INTERVALS,2-WAY LAYOUTS,HYPOTHESES,STATISTICS,SIZE,TRANSFORM,MEDICINE},
  language     = {eng},
  number       = {22},
  pages        = {11243--11260},
  title        = {A Mann-Whitney type effect measure of interaction for factorial designs},
  url          = {http://dx.doi.org/10.1080/03610926.2016.1263739},
  volume       = {46},
  year         = {2017},
}

Chicago
De Neve, Jan, and Olivier Thas. 2017. “A Mann-Whitney Type Effect Measure of Interaction for Factorial Designs.” Communications in Statistics-theory and Methods 46 (22): 11243–11260.
APA
De Neve, Jan, & Thas, O. (2017). A Mann-Whitney type effect measure of interaction for factorial designs. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 46(22), 11243–11260.
Vancouver
1.
De Neve J, Thas O. A Mann-Whitney type effect measure of interaction for factorial designs. COMMUNICATIONS IN STATISTICS-THEORY AND METHODS. 2017;46(22):11243–60.
MLA
De Neve, Jan, and Olivier Thas. “A Mann-Whitney Type Effect Measure of Interaction for Factorial Designs.” COMMUNICATIONS IN STATISTICS-THEORY AND METHODS 46.22 (2017): 11243–11260. Print.