Performance of Coefficient Alpha and Its Alternatives: Effects of Different Types of Non-Normality.

IF 2.1 3区 心理学 Q2 MATHEMATICS, INTERDISCIPLINARY APPLICATIONS
Educational and Psychological Measurement Pub Date : 2023-02-01 Epub Date: 2022-04-11 DOI:10.1177/00131644221088240
Leifeng Xiao, Kit-Tai Hau
{"title":"Performance of Coefficient Alpha and Its Alternatives: Effects of Different Types of Non-Normality.","authors":"Leifeng Xiao, Kit-Tai Hau","doi":"10.1177/00131644221088240","DOIUrl":null,"url":null,"abstract":"<p><p>We examined the performance of coefficient alpha and its potential competitors (ordinal alpha, omega total, Revelle's omega total [omega RT], omega hierarchical [omega h], greatest lower bound [GLB], and coefficient <i>H</i>) with continuous and discrete data having different types of non-normality. Results showed the estimation bias was acceptable for continuous data with varying degrees of non-normality when the scales were strong (high loadings). This bias, however, became quite large with moderate strength scales and increased with increasing non-normality. For Likert-type scales, other than omega h, most indices were acceptable with non-normal data having at least four points, and more points were better. For different exponential distributed data, omega RT and GLB were robust, whereas the bias of other indices for binomial-beta distribution was generally large. An examination of an authentic large-scale international survey suggested that its items were at worst moderately non-normal; hence, non-normality was not a big concern. We recommend (a) the demand for continuous and normally distributed data for alpha may not be necessary for less severely non-normal data; (b) for severely non-normal data, we should have at least four scale points, and more points are better; and (c) there is no single golden standard for all data types, other issues such as scale loading, model structure, or scale length are also important.</p>","PeriodicalId":11502,"journal":{"name":"Educational and Psychological Measurement","volume":"83 1","pages":"5-27"},"PeriodicalIF":2.1000,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9806521/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Educational and Psychological Measurement","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1177/00131644221088240","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/4/11 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

Abstract

We examined the performance of coefficient alpha and its potential competitors (ordinal alpha, omega total, Revelle's omega total [omega RT], omega hierarchical [omega h], greatest lower bound [GLB], and coefficient H) with continuous and discrete data having different types of non-normality. Results showed the estimation bias was acceptable for continuous data with varying degrees of non-normality when the scales were strong (high loadings). This bias, however, became quite large with moderate strength scales and increased with increasing non-normality. For Likert-type scales, other than omega h, most indices were acceptable with non-normal data having at least four points, and more points were better. For different exponential distributed data, omega RT and GLB were robust, whereas the bias of other indices for binomial-beta distribution was generally large. An examination of an authentic large-scale international survey suggested that its items were at worst moderately non-normal; hence, non-normality was not a big concern. We recommend (a) the demand for continuous and normally distributed data for alpha may not be necessary for less severely non-normal data; (b) for severely non-normal data, we should have at least four scale points, and more points are better; and (c) there is no single golden standard for all data types, other issues such as scale loading, model structure, or scale length are also important.

系数 Alpha 及其替代方法的性能:不同类型非正态性的影响。
我们研究了系数 alpha 及其潜在竞争者(顺序 alpha、欧米茄总值、Revelle 欧米茄总值 [欧米茄 RT]、欧米茄分层 [欧米茄 h]、最大下限 [GLB] 和系数 H)在具有不同类型非正态性的连续数据和离散数据中的表现。结果表明,对于具有不同程度非正态性的连续数据,当量表较强(高负荷)时,估计偏差是可以接受的。然而,对于中等强度的量表,估计偏差会变得相当大,并且随着非正态性的增加而增大。对于李克特量表,除欧米茄 h 外,大多数指数在非正态数据至少有四个点的情况下是可以接受的,点数越多越好。对于不同指数分布的数据,欧米茄 RT 和 GLB 是稳健的,而对于二项-贝塔分布,其他指数的偏差通常较大。对一项真实的大规模国际调查的研究表明,其项目最差也是中度非正态性;因此,非正态性并不是一个大问题。我们建议:(a) 对于不太严重的非正态数据,α 指数不一定需要连续的正态分布数据;(b) 对于严重的非正态数据,我们至少应该有四个量表点,点数越多越好;(c) 没有一个适用于所有数据类型的黄金标准,其他问题如量表负荷、模型结构或量表长度也很重要。
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
Educational and Psychological Measurement
Educational and Psychological Measurement 医学-数学跨学科应用
CiteScore
5.50
自引率
7.40%
发文量
49
审稿时长
6-12 weeks
期刊介绍: Educational and Psychological Measurement (EPM) publishes referred scholarly work from all academic disciplines interested in the study of measurement theory, problems, and issues. Theoretical articles address new developments and techniques, and applied articles deal with innovation applications.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信