An integrated test of multidimensionality, convergent, discriminant and criterion validity of the course experience questionnaire: an exploratory structural equation modelling

Abstract

Most research on the course experience questionnaire (CEQ) has been conducted through conventional exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) within the independent cluster model framework (ICM-CFA). However, very few studies have focused on examining its multidimensionality using more flexible psychometric frameworks such as exploratory structural equation modelling (ESEM). This study aims to conduct an integrated test of multidimensionality on the short, 23-item version of the CEQ (CEQ23) by using ESEM, to test its construct and criterion-related validity and contribute to the current debate on its validity. The participants comprised 620 undergraduate psychology students. CEQ23 scores were examined through ESEM to identify two sources of construct-multidimensionality. This entailed contrasting ICM-CFA and ESEM solutions and comparing three alternative models. Construct and criterion-related validity were then analysed using common and emerging techniques. The results (a) confirmed the presence of a superior construct: students’ perceptions of teaching quality, which is multifaceted and hierarchically structured; (b) supported a generally acceptable construct and criterion-related validity; and (c) highlighted some methodological weaknesses of conventional statistical techniques, which may underly the debate on the validity of the CEQ23.