Need Help on Mediator Effect

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
shash
PLS Junior User
Posts: 5
Joined: Sat Nov 25, 2017 2:29 pm
Real name and title: Ms. Shasheela Devi

Need Help on Mediator Effect

Post by shash » Sun Nov 26, 2017 2:54 pm

Hi,

I have done bootstrapping on my research model. I have 3 independent variables, 2 mediators, 2nd order construct DV measured by 6 formative 1st order. The others are reflective. All the paths showing t-value, except for the path from both mediators to my 2nd order DV is showing 0.0000. What does this mean? is it normal to get value like this? In the path coefficient table, both mediators rows are totally empty. Or am I supposed to test the mediators separately?
please advise. I am lost. tq.

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

Re: Need Help on Mediator Effect

Post by jmbecker » Sun Nov 26, 2017 3:01 pm

This is not surprising if you use the repeated indicator approach for your formative higher-order construct.
You either need to also specify indirect effect via the lower-order components and then assess the total effect on the higher-order construct or use the two-stage approach.

See, for example,
Becker, J.-M., Klein, K., and Wetzels, M. 2012. Hierarchical Latent Variable Models in PLS-SEM: Guidelines for Using Reflective-Formative Type Models. Long Range Planning 45 (5–6): 359–394.
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

shash
PLS Junior User
Posts: 5
Joined: Sat Nov 25, 2017 2:29 pm
Real name and title: Ms. Shasheela Devi

Re: Need Help on Mediator Effect

Post by shash » Sun Nov 26, 2017 4:01 pm

Hi,

Great. My model works now. Just to double confirm, the reliability and validity test should be done before designing the 2-stage approach to test path coefficient right?

Thank you.

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

Re: Need Help on Mediator Effect

Post by jmbecker » Mon Nov 27, 2017 9:32 am

I would evaluate both first and second stage model. Both are contributing to the final result and should therefore fulfill the minimum requirements.
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