Scale length does matter: Recommendations for measurement invariance testing with categorical factor analysis and item response theory approaches.
Scale length does matter: Recommendations for measurement invariance testing with categorical factor analysis and item response theory approaches.
复制标题
DOI：
10.3758/s13428-021-01690-7
复制
发表时间：
2022-10
影响因子：
5.4
通讯作者：
Tijmstra J
中科院分区：
文献类型：
--
作者：
D'Urso ED;De Roover K;Vermunt JK;Tijmstra J
在社会科学中，关于潜在结构的群体差异的研究无处不在。这些结构通常通过由有序项目组成的量表来测量。为了在各组之间比较这些结构，一个关键的要求是它们被等效地测量，或者用技术术语来说，测量不变性（MI）在各组之间保持不变。本研究比较了基于多组分类验证性因素分析（MG-CCFA）和多组项目反应理论（MG-IRT）的量表水平和项目水平方法在有序数据检验MI中的性能。一般来说，模拟研究的结果表明，当在量表水平上测试MI时，基于MG-CCFA的方法优于基于MG-IRT的方法，而在项目水平上，最佳表现方法取决于测试参数（即，负载或阈值）。即，在检验载荷等效性时，似然比检验在真阳性率和假阳性率之间提供了最佳折衷，而在检验阈值等效性时，χ2检验优于其他检验策略。此外，MG-CCFA的适合措施，如RMSEA和CFI的性能，似乎在很大程度上取决于规模的长度，特别是当MI在项目水平上进行测试。建议在使用这些措施时，特别是在单独测试每个项目的MI时，应谨慎。
In social sciences, the study of group differences concerning latent constructs is ubiquitous. These constructs are generally measured by means of scales composed of ordinal items. In order to compare these constructs across groups, one crucial requirement is that they are measured equivalently or, in technical jargon, that measurement invariance (MI) holds across the groups. This study compared the performance of scale- and item-level approaches based on multiple group categorical confirmatory factor analysis (MG-CCFA) and multiple group item response theory (MG-IRT) in testing MI with ordinal data. In general, the results of the simulation studies showed that MG-CCFA-based approaches outperformed MG-IRT-based approaches when testing MI at the scale level, whereas, at the item level, the best performing approach depends on the tested parameter (i.e., loadings or thresholds). That is, when testing loadings equivalence, the likelihood ratio test provided the best trade-off between true-positive rate and false-positive rate, whereas, when testing thresholds equivalence, the χ2 test outperformed the other testing strategies. In addition, the performance of MG-CCFA’s fit measures, such as RMSEA and CFI, seemed to depend largely on the length of the scale, especially when MI was tested at the item level. General caution is recommended when using these measures, especially when MI is tested for each item individually.
登录
查看更多内容
DOI：
10.1080/10705510701301834
发表时间：
2005-01-01
影响因子：
6
作者：
Chen, FF;Sousa, KH;West, SG
通讯作者：
West, SG
DOI：
10.1080/10705510701758349
发表时间：
2008-01-01
影响因子：
6
作者：
French, Brian F.;Finch, W. Holmes
通讯作者：
Finch, W. Holmes
DOI：
10.1093/geronb/57.6.p548
发表时间：
2002-11-01
影响因子：
6.2
作者：
Jones, RN;Gallo, JJ
通讯作者：
Gallo, JJ
DOI：
10.1080/10705510701758406
发表时间：
2008-01-01
影响因子：
6
作者：
Kamata, Akihito;Bauer, Daniel J.
通讯作者：
Bauer, Daniel J.
影响因子：
1.2
作者：
Kim, SH;Cohen, AS
通讯作者：
Cohen, AS