Total Effects PreviousNext
Mplus Discussion > Structural Equation Modeling >
 learningmplus posted on Sunday, October 02, 2011 - 3:43 pm

I am testing a mediation model. In the model I am controlling for 2 variables that have been previously shown to have an effect on the outcome. I want to show that relations hold controlling for the covariates (which I found that it is the case).

My question is -- Do I need to report the total effects or will it be okay to report paths a to b and b to c as in mediation?

I struggle if to report the total effect given my research question. I initially submitted a paper with the total effects in, but I need to resubmit it with a word limit and I thought the total effects is something I can cut out. Please advise if this is okay to do.

Thank you!
 Linda K. Muthen posted on Monday, October 03, 2011 - 11:33 am
I would report both the direct and indirect effects. Without both, you can't get a clear picture of what is happening.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message