Abstract
The goal of this article is to present a series of conceptual, statistical, and practical issues in the modeling of multi-level dyadic data. Distinctions are made between distinguishable and undistinguishable dyads and several types of independent variables modeled at the dyadic level of analysis. Multi-level modeling equations are explained in a non-technical manner. A database of 66 athletes regrouped in 33 undistinguishable dyads is used to illustrate the steps from initial preparation of multi-level databases to the interpretations of output files. The data are used to examine null, intercept-as-outcome, and slope-as-outcome models, as well as to present a formula to calculate percentage of variance explained at different levels of analysis. A simple slopes procedure is showed to probe significant cross-level interactions (slope-as-outcome model) in a manner consistent with the approach generally used in ordinary least square regression. Potential extensions and limitations of this multi-level approach are presented in the discussion.
Key words:
ACKNOWLEDGMENTS
This article was supported by a grant that was awarded to Patrick Gaudreau from the Social Sciences and Humanities Research Council of Canada.