%0 Journal Article %1 Villano2018 %A Villano, Renato %A Harrison, Scott %A Lynch, Grace %A Chen, George %D 2018 %J Higher Education %K learninganalytics predictivemodeling retention students %R 10.1007/s10734-018-0249-y %T Linking early alert systems and student retention: a survival analysis approach %U https://doi.org/10.1007/s10734-018-0249-y %X Higher education institutions are increasingly seeking technological solutions to not only enhance the learning environment but also support students. In this study, we explored the case of an early alert system (EAS) at a regional university engaged in both on-campus and online teaching. Using a total of 16,142 observations captured between 2011 and 2013, we examined the relationship between EAS and the student retention rate. The results indicate that when controlling for demographic, institution, student performance and workload variables, the EAS is able to identify students who have a significantly higher risk of discontinuing from their studies. This implies that early intervention strategies are effective in addressing student retention, and thus an EAS is able to provide actionable information to the student support team.

@article{Villano2018, abstract = {Higher education institutions are increasingly seeking technological solutions to not only enhance the learning environment but also support students. In this study, we explored the case of an early alert system (EAS) at a regional university engaged in both on-campus and online teaching. Using a total of 16,142 observations captured between 2011 and 2013, we examined the relationship between EAS and the student retention rate. The results indicate that when controlling for demographic, institution, student performance and workload variables, the EAS is able to identify students who have a significantly higher risk of discontinuing from their studies. This implies that early intervention strategies are effective in addressing student retention, and thus an EAS is able to provide actionable information to the student support team.}, added-at = {2018-03-10T11:32:37.000+0100}, author = {Villano, Renato and Harrison, Scott and Lynch, Grace and Chen, George}, biburl = {https://www.bibsonomy.org/bibtex/2a2fcb73e7063f25bdd577effca71ad7b/ereidt}, day = 03, doi = {10.1007/s10734-018-0249-y}, interhash = {ce10d348e45d6272f42f402a931c56d8}, intrahash = {a2fcb73e7063f25bdd577effca71ad7b}, issn = {1573-174X}, journal = {Higher Education}, keywords = {learninganalytics predictivemodeling retention students}, month = mar, timestamp = {2018-03-10T11:32:37.000+0100}, title = {Linking early alert systems and student retention: a survival analysis approach}, url = {https://doi.org/10.1007/s10734-018-0249-y}, year = 2018 }