Moderating effect using MGA

PLS is broadly applied in modern business research. This forum is the right place for discussions on the use of PLS in the fields of Marketing, Strategic Management, Information Technology etc.
Post Reply
jklstw
PLS Junior User
Posts: 6
Joined: Mon Jun 28, 2010 5:17 am
Real name and title:

Moderating effect using MGA

Post by jklstw » Sat Mar 17, 2018 12:15 am

Hi everyone,

Please I need your help

I have a model includes 2 independent variables (A and B), a dependent variable (C) and a moderator G(gender).
A ---->B ----> C
A -----------> C

If I conduct GMA, does it mean that G moderating the effect of three paths(A--->B, B--->C and A--->C) simultaneously?

If I suppose G only moderating the B-->C and A--->C, I need to conduct two separate analysis B*G-->C and A*G--->C, right?

Then, if I conduct B*G-->C and A*G--->C in a model simultaneously, what are the differences comparing to the above separate two models?

Greetings

jmbecker
SmartPLS Developer
Posts: 820
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Moderating effect using MGA

Post by jmbecker » Sat Mar 17, 2018 6:11 pm

jklstw wrote:
Sat Mar 17, 2018 12:15 am
Hi everyone,

Please I need your help

I have a model includes 2 independent variables (A and B), a dependent variable (C) and a moderator G(gender).
A ---->B ----> C
A -----------> C

If I conduct GMA, does it mean that G moderating the effect of three paths(A--->B, B--->C and A--->C) simultaneously?
Yes
jklstw wrote:
Sat Mar 17, 2018 12:15 am
If I suppose G only moderating the B-->C and A--->C, I need to conduct two separate analysis B*G-->C and A*G--->C, right?
You can also include both interaction effects in the same model. You do not need to do this separately. See below.
jklstw wrote:
Sat Mar 17, 2018 12:15 am
Then, if I conduct B*G-->C and A*G--->C in a model simultaneously, what are the differences comparing to the above separate two models?

Greetings
It is a different assumption to test them both separately or together. Usually, if you assume both to be necessary you should test them together. However, multicollinearity could be a problem is such a model.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Ja ... v=hdr_xprf
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de

jklstw
PLS Junior User
Posts: 6
Joined: Mon Jun 28, 2010 5:17 am
Real name and title:

Re: Moderating effect using MGA

Post by jklstw » Wed Mar 21, 2018 4:54 am

Dr. Jmbecker, thank you so much!

Post Reply