Problem: Moderating Effects and the "total effects"

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
KatrinF
PLS Junior User
Posts: 3
Joined: Wed Mar 02, 2011 2:44 pm
Real name and title:

Problem: Moderating Effects and the "total effects"

Post by KatrinF »

Dear all,
at the moment i am writing my master thesis. As i am quite new to PLS Pathmodelling i'm facing some problems.

I have a question concerning moderating effects in my model and the total effects output.


My model looks like this:

X ---------> Y
X --> A --> Y
X --> B --> Y
X --> C --> Y
X --> D --> Y
E --> Y
F --> Y
G--> Y
H --> Y


X has an influence on A, B, C, D and Y. Besides this, A, B, C and D as well have an influence on Y. So A - D are my mediators.
Then there are some influencing variables ( E, F, G and H) which have an influence on Y as well.
I want to use the Variables E-H to create moderating effects concerning the relationship between X and Y.

When I look at the results in the total effects output, all the moderating effects (e.g. X*E -> Y), appear 5 times. I dont understand why that happens and I don't know how to interpret this.

By the way: Is it right to use the total effects for interpretation of my model or should i use path coefficients anyway?

I would be really thankfull if anybody could give me a little hint ;)
Katrin
Post Reply