Difference between revisions of "At-risk/Dropout/Stopout/Graduation Prediction"

Revision as of 06:17, 24 January 2022

Hu and Rangwala (2020) pdf

Kai et al. (2017) pdf

Models predicting student retention in an online college program
J48 decision trees achieved much lower Kappa and AUC for Black students than White students
JRip decision rules achieved almost identical Kappa and AUC for Black students and White students
JRip decision rules achieved moderately higher Kappa and AUC for female students than male students

Anderson et al. (2019) pdf

Models predicting six-year college graduation
Performance for African-American students comparable to performance for students in other races.

Yu, Lee, and Kizilcec (2021)[pdf]

Model predicting college dropout
worse true negative rates and better recall for students who are not White or Asian, and also worse accuracy if the student is studying in person

Gardner, Brooks and Baker (2019) [pdf]

Model predicting MOOC dropout, specifically through slicing analysis
Some algorithms performed worse for female students than male students, particularly in courses with 45% or less male presence

@@ Line 7: / Line 7: @@
 * J48 decision trees achieved much lower Kappa and AUC for Black students than White students
 * JRip decision rules achieved almost identical Kappa and AUC for Black students and White students
-* J-Rip model performed moderately better for female students than male students
+* JRip decision rules achieved moderately higher Kappa and AUC for female students than male students
-* J-Rip decision tree model performed more equitably than a J-48 decision tree model for both male and female students.
 Anderson et al. (2019) [https://www.upenn.edu/learninganalytics/ryanbaker/EDM2019_paper56.pdf pdf]