Difference between revisions of "Short-term Performance and Learning Gains Prediction"
Jump to navigation
Jump to search
| Line 3: | Line 3: | ||
*Both U.S. and combined model performed extremely poorly for Costa Rica | *Both U.S. and combined model performed extremely poorly for Costa Rica | ||
*U.S. model outperformed for Philippines than when trained with its own data set | *U.S. model outperformed for Philippines than when trained with its own data set | ||
Yudelson et al. (2014) [https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.659.872&rep=rep1&type=pdf pdf] | |||
* Models discovering generalizable sub-populations of students across different schools to predict students' learning with Carnegie Learning’s Cognitive Tutor (CLCT) | |||
*Models trained on schools with a high proportion of low-SES student performed worse than those trained with medium or low proportion | |||
*Models trained on schools with low, medium proportion of SES students performed similarly well for schools with high proportions of low-SES students | |||
Revision as of 06:55, 17 May 2022
Ogan and colleagues (2015) [pdf]
- Multi-national model predicting learning gains from student's help-seeking behavior
- Both U.S. and combined model performed extremely poorly for Costa Rica
- U.S. model outperformed for Philippines than when trained with its own data set
Yudelson et al. (2014) pdf
- Models discovering generalizable sub-populations of students across different schools to predict students' learning with Carnegie Learning’s Cognitive Tutor (CLCT)
- Models trained on schools with a high proportion of low-SES student performed worse than those trained with medium or low proportion
- Models trained on schools with low, medium proportion of SES students performed similarly well for schools with high proportions of low-SES students