Abstract
Dropout rates in university that uses distance learning methods are definitely higher than those in conventional
universities, including at Universitas Terbuka (UT) Indonesia. The term “drop out” is called non-active student in
UT. This research aims to investigating the best time to identify students who become non-active and the student
characteristics that have a higher risk of being non-active in distance learning. The data used in this study was
provided by UT's Academic Information System Database (secondary data). Email surveys collected additional data.
Logistic regression analysis was performed to identify students that are likely to drop out by Sociodemographic
characteristics and their academic performance of students. This study reveals that grade point average (GPA) is an
excellent predictor to identify students becoming non-active, especially in the first semester. We need to monitor
student GPA throughout the first semester to prevent non-completion of their study, and it will improve the prediction
accuracy.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright (c) 2023 Sri Utami, Inggit Winarni