Effects of Early Warning Emails on Student Performance

Abstract

We use learning data of an e-assessment platform for an introductory mathematical statistics course to predict the probability of passing the final exam for each student. Subsequently, we send warning emails to students with a low predicted probability to pass the exam. We detect a positive but imprecisely estimated effect of this treatment, suggesting the effectiveness of such interventions only when administered more intensively.

arXiv admin note: text overlap with arXiv:1906.09864