Measurement invariance in the social sciences: Historical development, methodological challenges, state of the art, and future perspectives

被引：106

作者：

Leitgoeb, Heinz ^{[1
,2
,17
]}

Seddig, Daniel ^{[3
,4
]}

Asparouhov, Tihomir ^{[5
]}

Behr, Dorothee ^{[6
]}

Davidov, Eldad ^{[3
,7
]}

De Roover, Kim ^{[8
,9
]}

Jak, Suzanne ^{[10
]}

Meitinger, Katharina ^{[11
]}

Menold, Natalja ^{[12
]}

Muthen, Bengt ^{[13
]}

Rudnev, Maksim ^{[14
]}

Schmidt, Peter ^{[15
,16
]}

van de Schoot, Rens ^{[11
]}

机构：

[1] Univ Leipzig, Leipzig, Germany

[2] Goethe Univ Frankfurt, Frankfurt, Germany

[3] Univ Cologne, Cologne, Germany

[4] Univ Munster, Munster, Germany

[5] Mplus, Houston, TX USA

[6] GESIS Leibniz Inst Social Sci, Mannheim, Germany

[7] Univ Zurich, URPP Social Networks, Zurich, Switzerland

[8] Tilburg Univ, Tilburg, Netherlands

[9] Katholieke Univ Leuven, Leuven, Belgium

[10] Univ Amsterdam, Amsterdam, Netherlands

[11] Univ Utrecht, Utrecht, Netherlands

[12] Tech Univ Dresden, Dresden, Germany

[13] Univ Calif Los Angeles, Los Angeles, CA USA

[14] Univ Waterloo, Waterloo, ON, Canada

[15] Univ Giessen, Giessen, Germany

[16] Johannes Gutenberg Univ Mainz, Mainz, Germany

[17] Univ Leipzig, Beethovenstr 15, D-04107 Leipzig, Germany

来源：

SOCIAL SCIENCE RESEARCH | 2023年 / 110卷

基金：

荷兰研究理事会;

关键词：

Comparative research; Measurement invariance; Item bias; Noninvariance detection; Multiple group confirmatory factor analysis; Scale construction; TESTING MEASUREMENT INVARIANCE; CONFIRMATORY FACTOR-ANALYSIS; FACE-TO-FACE; MEASUREMENT EQUIVALENCE; FACTORIAL INVARIANCE; LATENT-VARIABLES; FIT INDEXES; MEASUREMENT BIAS; RESPONSE SHIFT; HUMAN-VALUES;

D O I：

10.1016/j.ssresearch.2022.102805

中图分类号：

C91 [社会学];

学科分类号：

030301 ; 1204 ;

摘要：

This review summarizes the current state of the art of statistical and (survey) methodological research on measurement (non)invariance, which is considered a core challenge for the comparative social sciences. After outlining the historical roots, conceptual details, and standard procedures for measurement invariance testing, the paper focuses in particular on the statistical developments that have been achieved in the last 10 years. These include Bayesian approximate measurement invariance, the alignment method, measurement invariance testing within the multilevel modeling framework, mixture multigroup factor analysis, the measurement invariance explorer, and the response shift-true change decomposition approach. Furthermore, the contri-bution of survey methodological research to the construction of invariant measurement in-struments is explicitly addressed and highlighted, including the issues of design decisions, pretesting, scale adoption, and translation. The paper ends with an outlook on future research perspectives.

引用

页数：30

共 320 条

[1] Measurement invariance within and between individuals: a distinct problem in testing the equivalence of intra- and inter-individual model structures
Adolf, Janne
Schuurman, Noemi K.
Borkenau, Peter
Borsboom, Denny
Dolan, Conor V.
[J]. FRONTIERS IN PSYCHOLOGY, 2014, 5
[2] Aizpurua E., 2020, ESSENTIAL ROLE LANGU, P129
[3] Alwin DuaneF., 2007, Margins of Error: A Study of Reliability in Survey Measurement
[4] [Anonymous], 2007, PRACTICAL ASSESSMENT, DOI DOI 10.7275/MHQA-CD89
[5] [Anonymous], 2012, METHODS THEORIES EMP
[6] [Anonymous], 2004, Methods for testing and evaluating survey questionnaires
[7] [Anonymous], 1945, Psychometrika
[8] [Anonymous], 2016, ITC GUID TRANSL AD T
[9] [Anonymous], 2012, ONLINE READINGS PSYC, DOI DOI 10.9707/2307-0919.1111
[10] [Anonymous], 2012, Applications of Item Response Theory to Practical Testing Problems

← 1 2 3 4 5 6 7 8 9 10 →