Multilevel modelling of hierarchically clustered CSCL content-analysis data

Research Method · All research methods
Evidence · 2 claims (2 for) · 1 study (1 causal), q3 · 0 of 1 report an effect size · 2 claims rest on one study

Description

The article presents multilevel modelling as a statistical approach for hierarchically clustered data in collaborative learning research, in which messages are nested within students (and measurement occasions) within groups. It argues that traditional unilevel techniques violate the independence assumption, that "conventional modelling can result in underestimation of standard errors", and that multilevel modelling handles "the hierarchical nesting, the interdependency, and the unit of analysis problem in a natural way". The article demonstrates the framework through three-level and four-level random intercept models with roles, themes, and ASIMeC dimensions as predictors.

Accounts

• Multilevel modelling as the appropriate statistical framework for analysing content analysis data from CSCL environments: The article presents multilevel modelling as a statistical approach for hierarchically clustered data in collaborative learning research, in which messages are nested within students (and measurement occasions) within groups. It argues that traditional unilevel techniques violate the independence assumption, that "conventional modelling can result in underestimation of standard errors", and that multilevel modelling handles "the hierarchical nesting, the interdependency, and the unit of analysis problem in a natural way". The article demonstrates the framework through three-level and four-level random intercept models with roles, themes, and ASIMeC dimensions as predictors. (De Wever et al. (2007))

Claims

• In knowledge-construction content analysis data from discussion groups, the largest share of variance lies at the message level, with only small between-group and between-student variance. [+M]
• Unilevel OLS regression and four-level multilevel analysis of the same content analysis data yield differing p-values, especially for parameters that are not highly significant. [+M]

Related Research Methods

-

Key Sources

• De Wever, B., Van Keer, H., Schellens, T., & Valcke, M. (2007). Applying multilevel modelling to content analysis data: Methodological issues in the study of role assignment in asynchronous discussion groups. Learning and Instruction, 17, 436-447. https://doi.org/10.1016/j.learninstruc.2007.04.001

Page metadata

Field	Value
type	research-method
id	multilevel-modelling-of-hierarchically-clustered-cscl-content-analysis-data
title	Multilevel modelling of hierarchically clustered CSCL content-analysis data
description	The article presents multilevel modelling as a statistical approach for hierarchically clustered data in collaborative learning research, in which messages are nested within students (and measurement occasions) within groups.
status	review
generated	by process:settle-candidates on 2026-10-22
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.