Student well-being and mathematical literacy performance in PISA 2018: a machine-learning approach

Abstract

One of the goals of the educational system is to promote the well-being of students due to its associated on their academic performance. This research aims to shed light on the main role of well-being variables (introduced by PISA 2018 for the first time, as far as our knowledge) in the mathematical competence throughout of the PISA 2018 evaluation with a sample of 35,943 Spanish students. Students ranged in age from 15 to 16 years old (SD = 0.288). Supervised learning techniques such as decision tree methodology, random forest, and a linear hierarchical model have been used throughout this study. The criterion variable was competency performance in mathematics, while the independent variables consisted of a total of 83 items extracted from the student well-being questionnaire. These predictors are grouped into five domains: physical, psychological, material, cognitive and social. We have proved that well-being plays an important role in mathematical understanding in PISA 2018. Specifically, social well-being is the most important variable in our study. To conclude, we observe that social well-being, contextualised in terms of the relationships that the students maintain with their teachers, peers and families, plays a detrimental role in mathematics achievement.

Keywords:

• PISA
• mathematical literacy
• performance
• well-being
• machine learning

Disclosure statement

No potential conflict of interest was reported by the author(s).