Difference between revisions of "Gender: Male/Female"
Jump to navigation
Jump to search
| Line 23: | Line 23: | ||
* Inconsistent in direction between algorithms. | * Inconsistent in direction between algorithms. | ||
Lee and Kizilcec (2020) [pdf] | Lee and Kizilcec (2020) [[https://arxiv.org/pdf/2007.00088.pdf pdf]] | ||
* Model predicting college course grade of median or above | * Model predicting college course grade of median or above | ||
* Unmodified algorithm, before correction, performed worse for male students than for female students | * Unmodified algorithm, before correction, performed worse for male students than for female students | ||
Revision as of 02:04, 24 January 2022
Kai et al. (2017) pdf
- Models predicting student retention in an online college program
- performance was very good for both groups
- JRip decision tree model performed more equitably than a J48 decision tree model for both male and female students.
- JRip model had moderately better performance for female students than male students
Hu and Rangwala (2020) pdf
- Models predicting if student at-risk for failing a course
- Performed worse for male students, but that this result is inconsistent across university courses
Anderson et al. (2019) pdf
- Models predicting six-year college graduation
- Algorithms had higher false negative rates for male students
Gardner, Brooks and Baker (2019) [pdf]
- Model predicting MOOC dropout
- Some algorithms studied performed worse for female students than male students, particularly in courses with 45% or less male presence
Riazy et al. (2020) [pdf]
- Model predicting course outcome
- Fairly marginal differences were found for prediction quality and in overall proportion of predicted pass between groups
- Inconsistent in direction between algorithms.
Lee and Kizilcec (2020) [pdf]
- Model predicting college course grade of median or above
- Unmodified algorithm, before correction, performed worse for male students than for female students