Specialized Tests for Detecting Treatment Effects in the Two-Sample Problem.

IF 2.2 4区教育学 Q1 Social Sciences

Journal of Experimental Education Pub Date : 1997-07-01 DOI:10.1080/00220973.1997.10806610

H. Keselman, R. Cribbie, B. Zumbo

{"title":"Specialized Tests for Detecting Treatment Effects in the Two-Sample Problem.","authors":"H. Keselman, R. Cribbie, B. Zumbo","doi":"10.1080/00220973.1997.10806610","DOIUrl":null,"url":null,"abstract":"Nonparametric and robust statistics (those using trimmed means and Winsorized variances) were compared for their ability to detect treatment effects in the 2-sample case. In particular, 2 specialized tests, tests designed to be sensitive to treatment effects when the distributions of the data are skewed to the right, were compared with 2 nonspecialized nonparametric (Wilcoxon-Mann-Whitney; Mann & Whitney, 1947; Wilcoxon, 1949) and trimmed (Yuen, 1974) tests for 6 nonnormal distributions that varied according to their measures of skewness and kurtosis. As expected, the specialized tests provided more power to detect treatment effects, particularly for the nonparametric comparison. However, when distributions were symmetric, the nonspecialized tests were more powerful; therefore, for all the distributions investigated, power differences did not favor the specialized tests. Consequently, the specialized tests are not recommended; researchers would have to know the shapes of the distributions that they work with in order to benefit from specialized tests. In addition, the nonparametric approach resulted in more power than the trimmed-means approach did.","PeriodicalId":47911,"journal":{"name":"Journal of Experimental Education","volume":"65 1","pages":"355-366"},"PeriodicalIF":2.2000,"publicationDate":"1997-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/00220973.1997.10806610","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Experimental Education","FirstCategoryId":"95","ListUrlMain":"https://doi.org/10.1080/00220973.1997.10806610","RegionNum":4,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Social Sciences","Score":null,"Total":0}

引用次数: 12

Abstract

Nonparametric and robust statistics (those using trimmed means and Winsorized variances) were compared for their ability to detect treatment effects in the 2-sample case. In particular, 2 specialized tests, tests designed to be sensitive to treatment effects when the distributions of the data are skewed to the right, were compared with 2 nonspecialized nonparametric (Wilcoxon-Mann-Whitney; Mann & Whitney, 1947; Wilcoxon, 1949) and trimmed (Yuen, 1974) tests for 6 nonnormal distributions that varied according to their measures of skewness and kurtosis. As expected, the specialized tests provided more power to detect treatment effects, particularly for the nonparametric comparison. However, when distributions were symmetric, the nonspecialized tests were more powerful; therefore, for all the distributions investigated, power differences did not favor the specialized tests. Consequently, the specialized tests are not recommended; researchers would have to know the shapes of the distributions that they work with in order to benefit from specialized tests. In addition, the nonparametric approach resulted in more power than the trimmed-means approach did.

查看原文本刊更多论文

检测双样本问题处理效果的专门检验。

比较非参数统计和稳健统计(使用裁剪均值和Winsorized方差的统计)在2个样本病例中检测治疗效果的能力。特别地，当数据分布向右偏斜时，2个专门的测试，设计为对治疗效果敏感的测试，与2个非专业的非参数(Wilcoxon-Mann-Whitney;曼&惠特尼，1947;Wilcoxon, 1949)和trim (Yuen, 1974)对6个非正态分布的检验，这些分布根据其偏度和峰度的测量而变化。正如预期的那样，专门的测试提供了更多的能力来检测治疗效果，特别是对于非参数比较。然而，当分布是对称的，非专业测试更强大;因此，对于所调查的所有分布，功率差异并不有利于专门的测试。因此，不建议进行专门的测试;研究人员必须知道他们研究的分布的形状，以便从专门的测试中受益。此外，非参数方法比裁剪均值方法产生更大的功率。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Experimental Education Multiple-

CiteScore

6.70

自引率

0.00%

发文量

期刊介绍： The Journal of Experimental Education publishes theoretical, laboratory, and classroom research studies that use the range of quantitative and qualitative methodologies. Recent articles have explored the correlation between test preparation and performance, enhancing students" self-efficacy, the effects of peer collaboration among students, and arguments about statistical significance and effect size reporting. In recent issues, JXE has published examinations of statistical methodologies and editorial practices used in several educational research journals.