|
Title:
|
USING BIG DATA TO PREDICT STUDENT DROPOUTS: TECHNOLOGY AFFORDANCES FOR RESEARCH |
|
Author(s):
|
David Niemi, Elena Gitin |
|
ISBN:
|
978-989-8533-12-8 |
|
Editors:
|
Demetrios G Sampson, J. Michael Spector, Dirk Ifenthaler and Pedro Isaías |
|
Year:
|
2012 |
|
Edition:
|
Single |
|
Keywords:
|
Virtual education, Online learning, Technology |
|
Type:
|
Short Paper |
|
First Page:
|
261 |
|
Last Page:
|
264 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
An underlying theme of this paper is that it can be easier and more efficient to conduct valid and effective research studies in online environments than in traditional classrooms. Taking advantage of the big data available in an online university, we conducted a study in which a massive online database was used to predict student successes and failures. We found that a pattern of declining performance over time is a good predictor of the likelihood of dropping out, and that having dependents or being married or in the military reduces the risk of dropping out. The risk of dropping out was higher for older students, females, and students with previous college education or transfer credits. These results provide a foundation for testing interventions to help students who are at risk and will also help to inform the development of a research pipeline that will enable rapid experimental studies of new tools and strategies. |
|
|
|
|
|
|
