TITLE:
A New Maximum Test via the Dependent Samples t-Test and the Wilcoxon Signed-Ranks Test
AUTHORS:
Saverpierre Maggio, Shlomo S. Sawilowsky
KEYWORDS:
Maximum Test; Dependent Samples t-Test; Wilcoxon Signed-Ranks Test; Bonferroni-Dunn Adjustment; Experiment-Wise Type I Error; Inferential Statistics; Monte Carlo Method
JOURNAL NAME:
Applied Mathematics,
Vol.5 No.1,
January
10,
2014
ABSTRACT:
A maximum test in lieu of
forcing a choice between the two dependent samples t-test and Wilcoxon
signed-ranks test is proposed. The maximum test, which requires a new table of
critical values, maintains nominal α while guaranteeing the maximum
power of the two constituent tests. Critical values, obtained via Monte Carlo
methods, are uniformly smaller than the Bonferroni-Dunn adjustment, giving it
power superiority when testing for treatment alternatives of shift in location parameter when data are
sampled from non-normal distributions.