Balancing Trade-Offs in the Detection of Primary Schools at Risk

Abstract

The quality assurance and evaluation of schools requires early risk-detection; a daunting task since school failures are typically rare and their origins complex. In the Netherlands, the Inspectorate of Education monitors the regulatory compliance of roughly 6000 primary schools, with limited resources and capacity, and a desire for proportionality. In order to aid their risk-based inspection method, we evaluate various case-based prediction models, and propose a principled exploit-explore procedure for organizing school inspections. This approach has the potential to balance the benefits of prioritizing inspections of presumed high-risk schools on the one hand, with the benefits of verifying predicted risks and causal impact evaluations of school inspections on the other.

Computer or teacher: Who predicts dropout best?

“…A higher precision @% signifies a better proportionality and a higher sensitivity @% signifies a better coverage of the students at risk. In the ideal scenario, precision remains 100% with every increase in the percentage of invited students, and sensitivity increases with every increase in the percentage of invited students until sensitivity also reaches 100% (Savi et al, 2020). The advantage of this approach is that the ratio between the decrease in precision and gain in sensitivity also incorporates specificity information (i.e., if inviting additional students does not result in sensitivity gains and precision loss, then this indicates that more students who were not at risk were incorrectly identified as at-risk and invited).…”