Dear group,
medsens() is a fantastic method for testing sensitivity of mediation
models estimated by the mediate(). (mediation package by Tingley et al;
Version 4.4.5).
However, I'm wondering whether medsens() is also appropriate for
moderated mediation? And if not, is there an alternative procedure that
allows to test sensitivity of moderated mediation analysis?
In one of my study, I find strong theoretical and empirical support for
moderated mediation (moderator is a dummy var; otherwise the model specs
are similar to chapter 3.2
ftp://cran.r-project.org/pub/R/web/packages/mediation/vignettes/mediation.pdf).
However, my medsens() analysis finds only very poor Rho and R2 values.
Before throwing away the model, I wonder whether medsens is appropriate
for estimating sensitivity of moderated mediation models, normally
entailing a moderation*mediator interaction term.
And if medsens is not appropriate for moderated mediation: Would it be
enough enlightening to test sensitivity of two unmoderated mediation
models ran over two sub-datasets, split along the moderation dummy?
many thanks for any advice.
Dominik
______________________________________________
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
