Short-term Performance and Learning Gains Prediction - Revision history

Ryan: Edit for clarity on Ogan paper

2022-05-19T10:23:10Z

Edit for clarity on Ogan paper

← Older revision		Revision as of 06:23, 19 May 2022
Line 2:		Line 2:
	*Multi-national models predicting learning gains from student's help-seeking behavior		*Multi-national models predicting learning gains from student's help-seeking behavior
	*Models built on only U.S.or combined data sets performed extremely poorly for Costa Rica		*Models built on only U.S.or combined data sets performed extremely poorly for Costa Rica
	*Models performed better when built on and applied for the ~~dataset~~, except for Philippines which was outperformed slightly by U.S. ~~model~~		*Models performed better when built on and applied for the same country, except for Philippines where model built on that country which was outperformed slightly by model built on U.S. data

Seiyon at 12:26, 18 May 2022

2022-05-18T12:26:11Z

← Older revision		Revision as of 08:26, 18 May 2022
Line 3:		Line 3:
	*Models built on only U.S.or combined data sets performed extremely poorly for Costa Rica		*Models built on only U.S.or combined data sets performed extremely poorly for Costa Rica
	*Models performed better when built on and applied for the dataset, except for Philippines which was outperformed slightly by U.S. model		*Models performed better when built on and applied for the dataset, except for Philippines which was outperformed slightly by U.S. model


	~~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

Seiyon at 11:22, 18 May 2022

2022-05-18T11:22:06Z

← Older revision		Revision as of 07:22, 18 May 2022
Line 1:		Line 1:
	Ogan et al. (2015) [https://link.springer.com/content/pdf/10.1007/s40593-014-0034-8.pdf pdf]		Ogan et al. (2015) [https://link.springer.com/content/pdf/10.1007/s40593-014-0034-8.pdf pdf]
	*Multi-national ~~model~~ predicting learning gains from student's help-seeking behavior		*Multi-national models predicting learning gains from student's help-seeking behavior
	*~~Both~~ U.S. ~~and~~ combined ~~model~~ performed extremely poorly for Costa Rica		*Models built on only U.S.or combined data sets performed extremely poorly for Costa Rica
	*U.S. model ~~outperformed for Philippines than when trained with its own data set~~		*Models performed better when built on and applied for the dataset, except for Philippines which was outperformed slightly by U.S. model

Seiyon at 00:44, 18 May 2022

2022-05-18T00:44:52Z

← Older revision		Revision as of 20:44, 17 May 2022
Line 1:		Line 1:
	Ogan ~~and colleagues~~ (2015) [[https://link.springer.com/content/pdf/10.1007/s40593-014-0034-8.pdf pdf]]		Ogan et al. (2015) [https://link.springer.com/content/pdf/10.1007/s40593-014-0034-8.pdf pdf]
	*Multi-national model predicting learning gains from student's help-seeking behavior		*Multi-national model predicting learning gains from student's help-seeking behavior
	*Both U.S. and combined model performed extremely poorly for Costa Rica		*Both U.S. and combined model performed extremely poorly for Costa Rica

Seiyon at 11:55, 17 May 2022

2022-05-17T11:55:07Z

← Older revision		Revision as of 07:55, 17 May 2022
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

Seiyon at 09:01, 24 January 2022

2022-01-24T09:01:19Z

← Older revision		Revision as of 05:01, 24 January 2022
Line 1:		Line 1:
	Ogan and colleagues (2015) [[https://link.springer.com/content/pdf/10.1007/s40593-014-0034-8.pdf pdf]]		Ogan and colleagues (2015) [[https://link.springer.com/content/pdf/10.1007/s40593-014-0034-8.pdf pdf]]
			*Multi-national model predicting learning gains from student's help-seeking behavior
	* ~~models~~ predicting ~~student~~ learning gains from ~~a mixture of their behaviors related to~~ help-seeking		*Both U.S. and combined model performed extremely poorly for Costa Rica
	* ~~Models built using data from learners in the Philippines,~~ Costa Rica~~, and the United States were each more accurate on students from their~~ own ~~countries than for students from other countries.~~		*U.S. model outperformed for Philippines than when trained with its own data set

Seiyon at 06:36, 24 January 2022

2022-01-24T06:36:24Z

← Older revision		Revision as of 02:36, 24 January 2022
Line 1:		Line 1:
	Ogan and colleagues (2015) [pdf]		Ogan and colleagues (2015) [[https://link.springer.com/content/pdf/10.1007/s40593-014-0034-8.pdf pdf]]

	* models predicting student learning gains from a mixture of their behaviors related to help-seeking		* models predicting student learning gains from a mixture of their behaviors related to help-seeking
	* Models built using data from learners in the Philippines, Costa Rica, and the United States were each more accurate on students from their own countries than for students from other countries.		* Models built using data from learners in the Philippines, Costa Rica, and the United States were each more accurate on students from their own countries than for students from other countries.

Seiyon: Created page with "Ogan and colleagues (2015) [pdf] * models predicting student learning gains from a mixture of their behaviors related to help-seeking * Models built using data from learners in the Philippines, Costa Rica, and the United States were each more accurate on students from their own countries than for students from other countries."

2022-01-24T06:36:07Z

Created page with "Ogan and colleagues (2015) [pdf] * models predicting student learning gains from a mixture of their behaviors related to help-seeking * Models built using data from learners in the Philippines, Costa Rica, and the United States were each more accurate on students from their own countries than for students from other countries."

New page

Ogan and colleagues (2015) [pdf]

* models predicting student learning gains from a mixture of their behaviors related to help-seeking
* Models built using data from learners in the Philippines, Costa Rica, and the United States were each more accurate on students from their own countries than for students from other countries.