ERIC Number: EJ1076863
Record Type: Journal
Publication Date: 2015-Oct
Abstractor: As Provided
Reference Count: N/A
Required Collaborative Work in Online Courses: A Predictive Modeling Approach
Smith, Marlene A.; Kellogg, Deborah L.
Decision Sciences Journal of Innovative Education, v13 n4 p563-581 Oct 2015
This article describes a predictive model that assesses whether a student will have greater perceived learning in group assignments or in individual work. The model produces correct classifications 87.5% of the time. The research is notable in that it is the first in the education literature to adopt a predictive modeling methodology using data collected via a designed experiment. All subjects experienced both a collaborative and an individual assignment, thus mitigating uncontrolled external factors in the measurement of differences in perceived learning. The exploratory nature of the work prompted the use of Partial Least Squares Regression for estimation. The work serves as an illustration of how predictive modeling might enlighten those in educational and academic settings.
Descriptors: Group Activities, Assignments, Cooperative Learning, Individual Activities, Learning Processes, Prediction, Models, Data Collection, Research Design, Educational Experiments, Classification, Accuracy, Discovery Processes, Research Methodology, Least Squares Statistics, Regression (Statistics)
Wiley-Blackwell. 350 Main Street, Malden, MA 02148. Tel: 800-835-6770; Tel: 781-388-8598; Fax: 781-388-8232; e-mail: email@example.com; Web site: http://www.wiley.com/WileyCDA
Publication Type: Journal Articles; Reports - Research
Education Level: N/A
Authoring Institution: N/A