The interaction between groups and individuals: the challenge of statistically analysing cooperative learning

Authors:
Ulrike Cress
Affiliations:
Knowledge Media Research Center, Tübingen, Germany
Venue:
ICLS'08 Proceedings of the 8th international conference on International conference for the learning sciences - Volume 1
Year:
2008

Citing 2
Cited 0

Applied multivariate statistics for the social sciences

Applied multivariate statistics for the social sciences
Learning in asynchronous discussion groups: a multilevel approach to study the influence of student, group and task characteristics

Behaviour & Information Technology - Computer Support for Learning Communities

Quantified Score

Hi-index	0.00

Visualization

Abstract

Research about the effect of cooperative learning settings faces the challenge of dealing with hierarchical data where observations regarding the learners are not stochastically independent. Standard methods like ANOVAs cannot deal with such data adequately. The article introduces multilevel modelling (MLM) as a statistical approach adequate for nested data. MLM allows taking into account interactions between group-level variables and individual-level variables. But MLM requires large sample sizes, and thus many studies fail to adopt MLM. For such studies, it is proposed that some additional statistics be presented.