Testing for measurement invariance by detecting local misspecification and an illustration across online and paper-and-pencil samples

J. Cieciuch, E. Davidov, D.L. Oberski, R. Algesheimer

Research output: Contribution to journalArticleScientificpeer-review


Political scientists often need to evaluate whether samples are comparable, for example, when analysing different countries or time points or when comparing data collected using different methods. A necessary condition for conducting such meaningful cross-group comparisons is the establishment of measurement invariance. One of the most frequently used procedures for establishing measurement invariance is the multigroup confirmatory factor analysis. This method was criticised in the literature because it may suggest that a model fits the data although it may contain serious misspecifications. We present an alternative method to test for measurement invariance using detection of local misspecifications and illustrate its use on two data sets assessing value priorities that are often analysed in political science and collected using paper-and-pencil and web modes of data collection.
Keywords: measurement invariance, detection for misspecification, multigroup confirmatory factor analysis (MGCFA), human values, statistical power, mode effects
Original languageEnglish
Pages (from-to)521-538
JournalEuropean Political Science
Issue number4
Publication statusPublished - 2015


Cite this