Mann-Whitney test

(redirected from Mann-Whitney U)
Also found in: Medical, Encyclopedia, Wikipedia.

Mann-Whitney test

(ˈmænˈwɪtnɪ)
n
(Statistics) a statistical test of the difference between the distributions of data collected in two experimental conditions applied to unmatched groups of subjects but comparing the distributions of the ranks of the scores. Also called: Wilcoxon Mann-Whitney test
Mentioned in ?
References in periodicals archive ?
We used the Mann-Whitney U test or Wilcoxon rank-sum test (Hart, 2001) which is a non-parametric alternative test to the independent sample t-test.
First, the Mann-Whitney U test was used to analyze the data.
Evaluation of the statistical significance between mean ranks of different parameters of two groups were performed using Mann-Whitney U test.
Table 4 shows the mean ranks of each of the five skills found to be significant through the Mann-Whitney U test.
To explore the impact of demographic factor (professional qualification), Mann-Whitney U was applied.
Proportions were calculated for different options and among male and female differences in opinion Mann-Whitney U test was applied.
As seen in the Table 1, the Mann-Whitney U test results show that the fluent writing levels of the 5th and 6th grade pupils differ significantly depending on whether they are placed in setting with or without music (U=69,500, p<.
The reason why an experimenter uses Kruskal-Wallis and Mann-Whitney U tests instead of ANOVA and t-tests is decided by what kind of data they are examining.
For a pair-wise comparison of qualitative data, the chi-square and Fisher's absolute chi-square tests were run, whereas the Mann-Whitney U test was used for the pair-wise comparison of quantitative and non-normally distributed data.
Table 1 Test statistics--Physical activity index -final Physical activity index--final Mann-Whitney U 0,000 Z -5,542 P (bilateral testing) 0,000
Maximum; ([dagger])(a) For comparisons between males and females within age groups, Mann-Whitney U test was used and Bonferroni corrected values of p<0.