Table 3 Rejection rates (%) of the t- and WMW tests for data drawn from gamma distributions using 1000 subjects in each group
From: t-tests, non-parametric tests, and large studies—a paradox of statistical practice?
WMW test | t-test | ||||||||
|---|---|---|---|---|---|---|---|---|---|
Skewness | Skewness | ||||||||
Std.ratio | 1.0 | 2.0 | 3.0 | 4.0 | 1.0 | 2.0 | 3.0 | 4.0 | |
1.05 | 5.8 | 14.4 | 78.6 | 100 | 4.8 | 4.4 | 4.9 | 4.8 | |
1.10 | 8.6 | 39.1 | 98.8 | 100 | 4.8 | 5.0 | 5.1 | 4.9 | |
1.15 | 13.6 | 65.7 | 100 | 100 | 5.5 | 4.8 | 5.1 | 5.2 | |
1.20 | 19.6 | 83.7 | 100 | 100 | 5.0 | 4.7 | 5.2 | 5.2 | |
1.25 | 26.1 | 93.8 | 100 | 100 | 5.7 | 4.7 | 5.0 | 5.1 | |
1.30 | 33.9 | 97.7 | 100 | 100 | 4.9 | 5.0 | 4.4 | 5.1 | |
1.40 | 48.9 | 99.8 | 100 | 100 | 4.9 | 5.0 | 5.0 | 4.8 | |
1.50 | 61.7 | 100 | 100 | 100 | 4.7 | 5.0 | 4.9 | 5.3 | |