EMPIRICAL COMPARISON OF ANOVA F-TEST, NORMAL SCORES TEST AND KRUSKAL-WALLIS TEST UNDER VIOLATION OF ASSUMPTIONS
EMPIRICAL COMPARISON OF ANOVA F-TEST, NORMAL SCORES TEST AND KRUSKAL-WALLIS TEST UNDER VIOLATION OF ASSUMPTIONS
复制标题
DOI：
10.1177/001316447403400406
复制
发表时间：
1974-01-01
影响因子：
2.7
通讯作者：
TOOTHAKER, LE
中科院分区：
文献类型：
--
作者：
FEIRWALS.BJ;TOOTHAKER, LE
本研究使用正态分布和两个指数分布的样本，在经验 alpha 和经验功效方面比较了 ANOVAF 检验、Kruskal-Wallis 检验和正态分数检验。经验证据支持在检验均值假设时即使在违反假设的情况下也可以使用方差分析 (ANOVAF) 检验。如果研究人员愿意检验有关中位数的假设，则 Kruskal-Wallis 检验被发现比 F 检验更具竞争力。然而，在调查的案例中，正态分数检验并不总是优于 F 检验或 Kruskal-Wallis 检验，因此不能根据本研究推荐。
The present research compares the ANOVAF-test, the Kruskal-Wallis test, and the normal scores test in terms of empirical alpha and empirical power with samples from the normal distribution and two exponential distributions. Empirical evidence supports the use of the ANOVAF-test even under violation of assumptions when testing hypotheses about means. If the researcher is willing to test hypotheses about medians, the Kruskal-Wallis test was found to be competitive to theF-test. However, in the cases investigated, the normal scores test was not consistently better than theF-test or the Kruskal-Wallis test and could not be recommended on the basis of this research.