Two-sample wilcoxon power over the pearson system and comparison with thet-test

A comparison of the power of the t test, Wilcoxon's test, and the approximate permutation test for the two‐sample location problem

“…This is in line with the evidence found in literature that the two-sample t test is robust with respect to departures from normality when sample sizes and variances are equal (e.g. Havlicek & Peterson, 1974;Posten, 1978). The influence of these differences on the rate of change of power of the t test was judged so small that the power of the t test is directly compared with the power of the other tests.…”

“…There is considerable theoretical support, particularly asymptotic efficiency levels, to recommend the Wilcoxon test as a general alternative to the t test (Lehmann, 1975). Blair & Higgins (1980) and Posten (1982) used computer simulations to study the relative power of the t and Wilcoxon statistics for small samples from normal and non-normal distributions. The results tend to at least partially support a Wilcoxon choice in a situation when the populations differ only by a shift parameter.…”

Serum androgen levels in healthy premenopausal women with and without sexual dysfunction: Part B: Reduced serum androgen levels in healthy premenopausal women with complaints of sexual dysfunction

“…However, the t-test does provide a robust comparison of mean values for small samples (410 per group) when there is heteroscedasticity of errors, equal group variances and an unknown standard error in the population. 24,25 Critical statistical assumptions were thoroughly examined and found intact during diagnostic analyses. Moreover, subjects were selected using multiple, explicit criteria, in order to eliminate confounding variables.…”

Scaffolding academic literacy using the Reading to Learn intervention: An evaluative study of a tertiary education context in South Africa

“…However, the Wilcoxon test allows for greater flexibility of statistical analysis. In other words, in statistical parlance, the Wilcoxon test is more robust (less susceptible) to violations in the distributional assumptions so important in parametric testing procedures -in layman's terms, under varying distributional properties and small sample sizes, the Wilcoxon test is more powerful at discerning the 'truth' in the data (see, for example, Posten, 1982). Although the method of analysis is not new, its application to the problem at hand (assessing academic literacy development) is novel.…”