What are the top predictors of students’ well-being across cultures? Combining machine learning and conventional statistics

Abstract

Abstract Alongside academic learning, there is increasing recognition that educational systems must also cater to students’ well-being. Hence, understanding the different factors that predict students’ well-being is a critical educational issue. The objective of this study is to examine the key factors that predict students’ subjective well-being, indexed by life satisfaction, positive affect, and negative affect across the globe. Data from 522,836 secondary school students from 71 countries across eight different cultural contexts were analyzed. Underpinned by Bronfenbrenner’s ecological system theory, both machine learning (i.e., light gradient-boosting machine) and conventional statistics (i.e., hierarchical linear modeling) were used to examine the roles of person, process, and context factors in predicting students’ well-being. Results indicated that life satisfaction was best predicted by the sense of meaning, school belonging, parental support, fear of failure, and country affluence. Positive affect was most influenced by resilience, sense of meaning, belonging, parental support, and country wealth. Negative affect was most strongly predicted by the general fear of failure, gender, being bullied, school belonging, and sense of meaning. Supplementary analyses indicated that the determinants of student well-being demonstrated remarkable cross-cultural similarity across the world.