Exploring Measurement Invariance: Political Trust in National Institutions Across Social Groups

A prerequisite for meaningful cross-national comparisons of scale scores is establishing the scale’s measurement invariance. In parallel, scaling theory presupposes that the structure of the construct (scale) is determined and its psychometric properties are assessed before its application. In this study, the psychometric properties and measurement invariance of a five-item scale measuring political trust in national institutions from the 2018 European Social Survey (ESS) were investigated for four European countries: France, Poland, Spain and the UK. First, factor analytic theory indicated that only a unidimensional model could be tested. Therefore, only Confirmatory Factor Analysis (CFA) was applied on the full samples of all countries and only models of acceptable or adequate model fit were considered. Then, based on reliable and valid scales, multiple-groups CFA was performed for testing the scales’ measurement invariance across countries. Measurement invariance was confirmed for the social groups defined by the level of educational attainment and the Left/Right self-placement scale for a combined sample of those four countries. Based on the mean scores, the findings showed that the higher the level of educational attainment, the greater the political trust in national institutions, with the exception of Poland. Higher levels of political trust in national institutions were observed for those inclined to the right end of the Left/Right self-placement scale, with the exception of France. This work could be extended to cover more countries of this or other Rounds of the ESS and other socio-demographic groups.