mlmoderator
Provides a workflow for probing, plotting, and checking cross-level interaction effects in two-level mixed-effects models fitted with 'lme4' (Bates et al., 2015) <doi:10.18637/jss.v067.i01>. Implements simple slopes analysis following Aiken and West (1991, ISBN:9780761907121), Johnson-Neyman intervals following Johnson and Fay (1950) <doi:10.1007/BF02288864> and Bauer and Curran (2005) <doi:10.1207/s15327906mbr4003_5>, and grand- or group-mean centering as described in Enders and Tofighi (2007) <doi:10.1037/1082-989X.12.2.121>. Tests and intervals use Satterthwaite degrees of freedom via 'lmerTest' (Kuznetsova et al., 2017) <doi:10.18637/jss.v082.i13> by default, with Kenward-Roger and between-cluster alternatives. Also provides confidence and new-cluster prediction intervals for simple slopes in random-slope models, contour plots of predicted outcomes over the predictor-by-moderator space, and leave-one-cluster-out influence diagnostics for the interaction.
- Centering predictor variables in cross-sectional multilevel models: A new look at an old issue.
- Fitting Linear Mixed-Effects Models Usinglme4
- lmerTest Package: Tests in Linear Mixed Effects Models
- Probing Interactions in Fixed and Multilevel Regression: Inferential and Graphical Techniques
- The Johnson-Neyman Technique, its Theory and Application
This page was built for software: mlmoderator
