The interaction terms in the path model.

Frequently asked questions about PLS path modeling.
Post Reply
asasi.kamal
PLS Junior User
Posts: 7
Joined: Wed Apr 05, 2017 3:49 pm
Real name and title: Kamal Karkonasasi

The interaction terms in the path model.

Post by asasi.kamal » Thu Nov 08, 2018 11:08 am

Dear experts,

My path model consisting of 13 reflective constructs as shown in the figure below.
path model.png
path model.png (78.38 KiB) Viewed 75 times
7 exogenous constructs, 1 mediator, 4 moderators, and 1 endogenous construct form my path model.
The calculation method for moderating effects is two stage.

should I add the interaction terms of the 4 moderators in my path model before I check for assessment of the reflective measurement items and also assessing the indirect and direct effects between the constructs?

Thank you,
Best wishes,
Kamal Karkonasasi

jmbecker
SmartPLS Developer
Posts: 879
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: The interaction terms in the path model.

Post by jmbecker » Thu Nov 08, 2018 12:51 pm

The assessment of the measurement model should not be affected by moderators if you use the two-stage approach, because it is fixed in the second-stage and estimated in the first stage (without the moderator) anyway.

The assessment of direct and indirect paths strongly depends on the moderator. Therefore, you should assess that after including them.
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

asasi.kamal
PLS Junior User
Posts: 7
Joined: Wed Apr 05, 2017 3:49 pm
Real name and title: Kamal Karkonasasi

Re: The interaction terms in the path model.

Post by asasi.kamal » Thu Nov 08, 2018 12:59 pm

Dear Dr. Jan-Michael Becker,

Thank you for your reply.
Would it be possible to elaborate further?

Warm regards,
Kamal Karkonasasi

jmbecker
SmartPLS Developer
Posts: 879
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: The interaction terms in the path model.

Post by jmbecker » Thu Nov 08, 2018 1:02 pm

What do you not understand?
Measurement model --> does not matter with two-stage.
Direct & indirect effects --> assess them in the moderator 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

asasi.kamal
PLS Junior User
Posts: 7
Joined: Wed Apr 05, 2017 3:49 pm
Real name and title: Kamal Karkonasasi

Re: The interaction terms in the path model.

Post by asasi.kamal » Thu Nov 08, 2018 1:25 pm

jmbecker wrote:
Thu Nov 08, 2018 1:02 pm
What do you not understand?
Measurement model --> does not matter with two-stage.
Direct & indirect effects --> assess them in the moderator model.
Thank you for your fast reply dear, Dr. Jan-Michael Becker.

Therefore, because I used the two-stage approach for moderating effects, I should have first added moderating effects (using the 2-stage approach) to my path model and then I could assess my constructs' measurement items and the direct and indirect effects.

What is your opinion about the above statement, dear Dr. Jan-Michael Becker?

Thank you.

jmbecker
SmartPLS Developer
Posts: 879
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: The interaction terms in the path model.

Post by jmbecker » Sat Nov 10, 2018 10:18 am

Is ok
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

Post Reply