Hey everyone,
I run an insignificant direkt effect of my X and Y variable but I want to test for a mediation effect.
I know this isn't the best way to do normally but my Prof. wants me to do it for a learning effect of mediations.
I use this commands:
sem (Y<-M X) (M<-X), nocapslatent
*1. Strategy
medsem, indep(X) med(M) dep(Y) mcreps(355) rit rid
*2. Strategy
medsem, indep(X) med(M) dep(Y) mcreps(355) rit rid zlc
Now my results shows at "RIT":
RIT = (Indirect effect / Total effect)
(0.000 / 0.000) = 1.977
Meaning that about198 % of the effect of X
on Y is mediated by M!
How can I interpret this result and does it make any sense?
Kind regards
Jana
0 Response to Interpretation of 198% mediation effect
Post a Comment