MGA analysis for Serial Mediation model

Frequently asked questions about PLS path modeling.
Post Reply
lilyv
PLS User
Posts: 11
Joined: Thu Apr 04, 2019 5:07 pm
Real name and title: Lily Vu

MGA analysis for Serial Mediation model

Post by lilyv »

Hi,

My serial mediation model is presented in the graph model below. It has 2 mediation effects : X -> M1 -> Y and X -> M1 -> M2 -> Y.
I intend to run PLS-MGA to see if there is different between 2 groups of clients.

The results of Indirect effects in PLS-MGA are about the indirect effect from X to Y and from X to M2. In this case, how to interpret it ?

Could anyone give me some instructions or guideline to analyze this kind of model ?

Many thanks.
Attachments
serial mediation model.png
serial mediation model.png (10.35 KiB) Viewed 2292 times
jmbecker
SmartPLS Developer
Posts: 1129
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: MGA analysis for Serial Mediation model

Post by jmbecker »

Could you be a bit more specific about your problem? What exactly is unclear in the interpretation of the effects?
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
lilyv
PLS User
Posts: 11
Joined: Thu Apr 04, 2019 5:07 pm
Real name and title: Lily Vu

Re: MGA analysis for Serial Mediation model

Post by lilyv »

Dear Mr. Becker,

Actually my question is about how to interpret the PLS-MGA results showed in "Indirect effects" section ?

In the case of direct effect (ex : from X to Y), we can see whether this path coefficient if significantly larger in the first group than in the 2nd group.
In my model, we have two cases of indirect effect : from X -> M1 -> Y and from X-> M1 -> M2 -> Y. The PLS-MGA result only shows the indirect effect from X -> Y : Path-coeff. difference groups = 0.086; p-value = 0.084.

Best regards,
jmbecker
SmartPLS Developer
Posts: 1129
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: MGA analysis for Serial Mediation model

Post by jmbecker »

The PLS-MGA currently does not include specific indirect effects, but only total indirect effects. We will add specific indirect effects in the next release.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
Post Reply