Who Belongs in School? Using Statistical Learning Techniques to Identify Linear, Nonlinear and Interactive Effects

• Main Author: Quintana, Rafael
• Format: Article
• Language: English
• Published: Université d'Ottawa 2021-09-01
• Series: Tutorials in Quantitative Methods for Psychology
• Subjects: school belonging; statistical learning; lasso; mars
• Online Access: https://www.tqmp.org/RegularArticles/vol17-3/p312/p312.pdf

The sense of school belonging refers to students' feelings of being accepted and connected to their particular school. School belonging has been considered an important determinant of a range of academic and socioemotional outcomes. Yet despite an extensive literature on the topic, it is not clear what factors are more strongly related to the students' sense of school belonging. Using a nationally representative dataset, we investigated the extent to which school belonging in fifth grade can be predicted by a wide range of individual and contextual-level factors using two statistical learning techniques (Lasso and MARS). The strongest predictor of school belonging across all models was students' feelings of peer social support, followed by students' feelings of loneliness at school. These results suggest that peer social relationships are a key component of students feeling of being connected to their school.