- Title
- Comparing nonparametric tests of equality of means for randomized block designs
- Creator
- Best, D. J.; Rayner, J. C. W.; Thas, O.; De Neve, Jan; Allingham, David
- Relation
- Communications in Statistics: Simulation and Computation Vol. 45, Issue 5, p. 1718-1730
- Publisher Link
- http://dx.doi.org/10.1080/03610918.2013.861483
- Publisher
- Taylor & Francis
- Resource Type
- journal article
- Date
- 2016
- Description
- A number of nonparametric tests are compared empirically for a randomized block layout. We assess tests appropriate for when the data are not consistent with normality or when outliers invalidate traditional analysis of variance (ANOVA) tests. The objective is to assess, within this setting, tests that use ranks within blocks, the rank transform procedure that ranks the complete sample and continuous analogs of the Cochran-Mantel-Haenszel tests. The usual linear model is assumed, and our primary foci are tests of equality of means and component tests that assess linear and quadratic trends in the means. These tests include the traditional Page and Friedman tests. We conclude that the rank transform tests have competitive power and warrant greater use than is currently apparent.
- Subject
- alignment; nonnormal errors; nonparametric analysis; randomized blocks layout; simulation study
- Identifier
- http://hdl.handle.net/1959.13/1322294
- Identifier
- uon:24553
- Identifier
- ISSN:0361-0918
- Rights
- This is an Accepted Manuscript of an article published by Taylor and Francis in Communications in Statistics: Simulation and Computation on 9 June 2014, available online: https://www.tandfonline.com/doi/full/10.1080/03610918.2013.861483.
- Language
- eng
- Full Text
- Reviewed
- Hits: 7432
- Visitors: 3955
- Downloads: 297
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | ATTACHMENT02 | Author final version | 472 KB | Adobe Acrobat PDF | View Details Download |