Factors Associated with Dropout Intention in Engineering Education: A Learning Interpretable Modeling Approach

Area of Science:

• Higher Education Studies
• Educational Psychology
• Engineering Education Research

Background:

• Higher education dropout presents significant academic, institutional, and social challenges.
• Early identification of student dropout intention is crucial for developing effective preventive support strategies.
• Understanding factors influencing dropout intention in specific fields like engineering is essential for targeted interventions.

Purpose of the Study:

• To examine the predictors of dropout intention among undergraduate engineering students at a Chilean university.
• To identify key variables associated with students' likelihood to withdraw from their engineering programs.
• To provide empirical evidence for developing early warning systems and support mechanisms in higher education.

Main Methods:

• Survey data collected from 189 undergraduate engineering students.
• Operationalization of five key variables: personal self-regulation, mental health, institutional perception, socio-economic conditions, and academic motivation.
• Estimation of two predictive models: multivariable logistic regression and a shallow decision tree.

Main Results:

• Logistic regression identified socio-economic conditions and personal self-regulation as significant protective predictors of dropout intention.
• Mental health, institutional perception, and academic motivation were not significant predictors in the adjusted logistic regression model.
• The decision tree model corroborated the importance of socio-economic conditions and personal self-regulation, with a secondary role for mental health.

Conclusions:

• Dropout intention in engineering education is primarily influenced by structural factors (socio-economic conditions) and individual resources (self-regulation).
• Institutional perception and academic motivation alone were less significant in predicting dropout intention in this context.
• Findings support the development of targeted support strategies focusing on socio-economic factors and self-regulatory skills for engineering student retention.