Nový přístup v testování ekvivalence na příkladu měření subjektivního blahobytu

Abstract

Survey-based measures of subjective well-being are more and more often analyzed cross-culturally. However, international comparison of these measures requires measurement invariance. Therefore, the major goal of this study was to investigate the cross-country comparability of the five-item subjective well-being scales used in the International Social Survey Programme (2011, 2017). This study applied both the traditional exact and the more recent Bayesian approximate approach to assess whether the subjective well-being scales were measurement invariant. The Bayesian approach detected several non‑invariant items that were problematic for cross-national comparison and could be dropped from the scales. Consequently, measurement invariance was established in all countries for the reduced scales, allowing researchers to meaningfully compare their latent mean scores and the relationships with other theoretical constructs of interest. Thus, the study highlighted the advantages of using multiple indicators and the necessity of measurement invariance testing in subjective well-being research.