|
![](http://www.statmodel.com/discussion/icons/csc/1px.gif) |
Indirect effects in models with multi... |
![Previous](http://www.statmodel.com/discussion/icons/csc/navgen_arrow_left.gif) ![](http://www.statmodel.com/discussion/icons/csc/1px.gif)
|
Message/Author |
|
|
I'm analyzing a model that uses multiple mediators, and I'm having trouble understanding interpretation for some of that analysis, and how I would report it. If my model has a path that looks like this: a-->b-->c-->d And the indirect effect from a->d was non significant, but the paths from a->c and b->d ARE significant, what's the most suitable interpretation of the mediation effect? Thanks! |
|
|
It sounds like the effects get diluted over time. There may also be some model misspecification causing this. |
|
Back to top |
|
|