When data for a completely randomised design are categorical rather than continuous, the Cochran–Mantel–Haenszel suite of tests may be applied, albeit that there is only one stratum. In introductory design courses this design, and the randomised block design, are usually the first designs introduced. Using the completely randomised design instead of the randomised block design ignores blocks (strata) and results in expressions for the tests statistics that are simpler than if the usual general test statistics are applied. Based on models given here, the usual Cochran–Mantel–Haenszel tests for the completely randomised design are shown to be Wald-type tests.
History
Journal title
Journal of the Korean Statistical Society
Volume
50
Issue
1
Pagination
185-197
Publisher
Springer
Language
en, English
College/Research Centre
Faculty of Science
School
School of Mathematical and Physical Sciences
Rights statement
This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: http://dx.doi.org/10.1007/s42952-020-00068-3.