The Newman-Keuls test (also known as the Student-Newman-Keuls test or SNK test) is a post-hoc statistical test used in the analysis of variance (ANOVA). It is used to compare the means of a set of samples that have been split into multiple groups, typically in order to assess the significance of differences between them. The Newman-Keuls test is a popular choice among statisticians due to its simplicity and power in detecting differences between sample means.
History
The Newman-Keuls test was developed in 1937 by two American statisticians, Maurice Newman and David Keuls. The pair were working at the University of Michigan at the time and published their work in the journal Biometrika. The test was initially designed as a way to compare the means of multiple samples, and was used as a post-hoc analysis for ANOVA.
Characteristics
The Newman-Keuls test is a non-parametric method used to compare the means of multiple groups. It is considered a powerful test, meaning that it is able to detect even small to moderate differences between sample means. The test is also relatively simple to use, as it only requires that the data be split into groups, and the means of each group determined.
The Newman-Keuls test is most commonly used after a one-way ANOVA, in which data from multiple groups is compared. It can also be used to compare the means of two or more independent groups. In either case, the Newman-Keuls test is used to determine which group means are significantly different from each other.
References
Newman, M., & Keuls, D. (1937). A comparison of the means of several samples. Biometrika, 29(3/4), 525-534.
Chen, G., & Popovich, P. (2013). Newman–Keuls test. In Encyclopedia of Research Design (pp. 708-709). SAGE Publications.
Mann, H. B. (1950). The test of whether several means are equal. Biometrika, 37(3/4), 50-59.
Hochberg, Y., & Tamhane, A. C. (1987). Multiple comparison procedures. John Wiley & Sons.