Causal Analysis of First-Year Course Approval Delays in a Engineering Major Through Inference Techniques

• Autor(a) principal: Paz, Hugo
• Data de Publicação: 2023
• Tipo de documento: preprint
• Idioma: spa
• Título da fonte: SciELO Preprints
• Texto Completo: https://preprints.scielo.org/index.php/scielo/preprint/view/6674
• topic: Causal Inference; Course Approval Delays; Engineering Education; Inferencia causal; retrasos en la aprobación de cursos; educación en ingeniería

This work presents the analyses conducted to discover the underlying factors that contribute to the prolonged delays in the approval of first-year courses observed in the Civil Engineering Career of the Faculty of Exact Sciences and Technology (FACET) of the National University of Tucumán (UNT), Argentina. Until the year 2019, students take an average of 5 years to pass their first-year courses. Determining the causes of this delay was the reason for the present investigation. Our analysis was based on the implementation of the DoWhy framework (Blöbaum et al., 2022; Sharma y Kiciman, 2020) and Causal Discovery Toollbox (CDT) (Kalainathan et al., 2020), a tools designed for causal inference. Our goal was to unravel the web of variables that influence course approval times. The study findings illuminate a fundamental causal factor leading to a statistically significant increase in length of approval. Precisely, our findings unveiled the pivotal influence of the regulatory framework governing the academic program, as well as the methodologies employed for evaluation. Notably, the accumulation of core subjects that remain pending for a final examination emerged as a central determining factor. This knowledge has the potential to guide targeted interventions, improving both student success rates and the overall effectiveness of the education system.