Analyzing the latent structures of social emotional learning using structural equation models

Abstract

Several techniques exist in statistics to identify latent structures in a data set. Explanatory factor analysis (EFA) is the traditional method to explore the data structure and identify latent variables. However, other more sophisticated techniques exist; including confirmatory factor analysis (CFA) and structural equation modeling (SEM). Although these three statistical techniques share some similarities, they have distinct purposes and applications. CFA is a subset of SEM and focuses specifically on the measurement model, which involves assessing the relationships between observed variables and their latent constructs or factors. It aims to determine the extent to which the observed variables adequately reflect the underlying constructs. CFA allows researchers to confirm or test a predefined factor structure and evaluate the convergent and discriminant validity of the measurement model. SEM is a broader framework that encompasses CFA. It allows researchers to test complex structural models that include both measurement and structural components. In addition to examining the direct relationships between variables, SEM also allows for the evaluation of indirect relationships and mediating effects. It provides a comprehensive analysis of the relationships between observed and latent variables, offering insights into both measurement and structural aspects of the model. EFA, CFA and SEM are used in this paper to analyse the latent structure of a data set which is related to the students’ social emotional learning (SEL). This tool consists of twenty items, which assess five subscales (self-awareness, self-management, social awareness, relationship skills, and responsible decision making). Each subscale is assessed by four items which are each measured on a 4-point scale ranging from 0 to 3, where 0 corresponds to ‘never’ and 3 corresponds to ‘almost always’. The score of each subscale ranges from 0 to 12, where children scoring high on these five subscales are self-aware, caring, responsible, engaged, and lifelong learnings to work together to achieve their goals. The data comprises the responses of 330 school children aged 11 to 16 years selected from various Maltese schools. These statistical techniques will be implemented using the facilities of STATA.