Moderation

An introduction to testing moderation hypotheses using interaction effects

Topics

• interpreting the itnteraction coefficient 

• interpreting conditional effects (the ones frequently misnamed "main" effects) with and without centering

• Johnson-Neyman (floodlighting) analysis

• Using interaction terms to test curvilineality

Readings

• Spiller, S. A., Fitzsimons, G. J., Lynch Jr, J. G., & McClelland, G. H. (2013). Spotlights, floodlights, and the magic number zero: Simple effects tests in moderated regression. Journal of Marketing Research, 50(2), 277-288. [pdf]

• Ajay Mehra, Martin Kilduff and Daniel J. Brass. The Social Networks of High and Low Self-Monitors: Implications for Workplace Performance. Administrative Science Quarterly. Vol. 46, No. 1 (Mar., 2001), pp. 121-146 [pdf]

Handouts

• Kenny, David. Handout on moderation [html]

• UCLA handout on curvilinear relationships [html]

• Variety of PROCESS models; another Process table

Datasets

• protest

• dbco node measures

• bank

Class notes

• Notes | Moderation