Difference between revisions of "Parental Educational Background"
Jump to navigation
Jump to search
| Line 8: | Line 8: | ||
*Models predicting undergraduate course grades and average GPA | *Models predicting undergraduate course grades and average GPA | ||
* First-generation college students were inaccurately predicted to lower than class | * First-generation college students were inaccurately predicted to lower than class median final course grade and lower average GPA | ||
* Fairness of models improved with the inclusion of clickstream and survey data | * Fairness of models improved with the inclusion of clickstream and survey data | ||
Revision as of 15:39, 28 March 2022
Kai et al. (2017) pdf
- Models predicting student retention in an online college program
- J-48 decision trees achieved much higher Kappa and AUC for students whose parents did not attend college than those whose parents did
- J-Rip decision rules achieved much higher Kappa and AUC for students whose parents did not attended college than those whose parents did
Yu et al. (2020) pdf
- Models predicting undergraduate course grades and average GPA
- First-generation college students were inaccurately predicted to lower than class median final course grade and lower average GPA
- Fairness of models improved with the inclusion of clickstream and survey data
Yu et al. (2021) pdf
- Models predicting college dropout
- Models for first-generation residential students showed worse accuracy and true negative rate (i.e., predicting power of sophomore year persistence on college persistence)
- Models for first-generation residential students showed significantly better recall (i.e., proportion of correctly identified dropouts) than online peers, whether the attribute were made aware or not