Interaction effects using PLS

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
Choukri
PLS Expert User
Posts: 114
Joined: Thu Apr 16, 2015 2:11 pm
Real name and title: Choukri MENIDJEL

Interaction effects using PLS

Post by Choukri »

Hi everyone,

Please I need your help, I got confused after I red that Baron and Kenny (1986) method has been abondoned, now I am looking for an alternative method that I can follow to test moderating effects using smartpls 3. Then I found something intersting: Chiu et al. (2012, p. 840) reported in there study that "In formulating and testing for interaction effects using PLS, we need to follow a hierarchical process that is similar to that used in multiple regression, in which we compare the results of two models (i.e., one with and one without the interaction construct) (Chin et al., 2003)".

I understand this process quite well (Hierarchical Process), but I am not sure if it is as the same as Baron and Kenny (1986) process or not?

My question:Is this process (Hierarchical Process) safe in terms of publication?

I am looking forward to your reply

Thank you again
jmbecker
SmartPLS Developer
Posts: 1282
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Interaction effects using PLS

Post by jmbecker »

Are you testing a mediation or a moderation (interaction)?

The mediation approach by Baron and Kenny has been critized. Instead one should follow an assessment of the indirect effects using bootstrapping (Preacher and Hayes, etc.).

The moderating approach has always been the same: the most important part is the assessment of the siginicance of the interaction effect. In addition, you can also try to assess the increase in variance explained (R²) in the dependent variable.
So far the best resource for moderation in PLS is Chin and Henseler (2010).

Henseler, J., and Chin, W. W. 2010. A Comparison of Approaches for the Analysis of Interaction Effects Between Latent Variables Using Partial Least Squares Path Modeling. Structural Equation Modeling: A Multidisciplinary Journal, 17(1): 82-109.
Dr. Jan-Michael Becker, BI Norwegian Business School, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
Choukri
PLS Expert User
Posts: 114
Joined: Thu Apr 16, 2015 2:11 pm
Real name and title: Choukri MENIDJEL

Re: Interaction effects using PLS

Post by Choukri »

Thank you Dr. Jan-Michael Becker for the clarification

That's exactly what I need to understand.

I am testing both a mediation and a moderation. Now it is clear for the moderation.

You said Jan-Michael Becker that "Instead one should follow an assessment of the indirect effects using bootstrapping (Preacher and Hayes, etc.)."

Do you mean by (Preacher and Hayes,): "Preacher and Hayes (2008), "Asymptotic and resampling strategies for assessing and comparing indirect effects in multiple mediator models, Behavior Research Methods 2008, 40 (3), 879-891". or an other paper

Thank you again Jan-Michael Becker
jmbecker
SmartPLS Developer
Posts: 1282
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Interaction effects using PLS

Post by jmbecker »

Yes, this is probably one of the more important papers, but there are several more papers by Preacher and or Hayes.
Another important paper that you may read is Zhao, X., Lynch, J. G., & Chen, Q. (2010). Reconsidering Baron and Kenny: Myths and truths about mediation analysis. Journal of Consumer Research, 37, 197–206.
Dr. Jan-Michael Becker, BI Norwegian Business School, SmartPLS Developer
Researchgate: https://www.researchgate.net/profile/Jan_Michael_Becker
GoogleScholar: http://scholar.google.de/citations?user ... AAAJ&hl=de
Choukri
PLS Expert User
Posts: 114
Joined: Thu Apr 16, 2015 2:11 pm
Real name and title: Choukri MENIDJEL

Re: Interaction effects using PLS

Post by Choukri »

Exactly,

I took a look on this paper, it is really important, and it'll help a lot in my report. Thank you Jan-Michael Becker,

Untill now I have got three important papers:

Preacher, Kristopher J. and Andrew F. Hayes (2004), “SPSS and SAS Procedures for Estimating Indirect Effects in Simple Mediation Models,” Behavior Research Methods, Instruments, and Computers, 36 (4), 717–31.

Preacher, Kristopher J. and Andrew F. Hayes (2008), “Asymptotic and Resampling Strategies for Assessing and Comparing Indirect Effects in Multiple Mediator Models,” Behavior Research Methods, 40 (3), 879–91.

Zhao, X., Lynch, J. G., & Chen, Q. (2010). Reconsidering Baron and Kenny: Myths and truths about mediation analysis. Journal of Consumer Research, 37, 197–206.

Kind regards
User avatar
Hengkov
PLS Super-Expert
Posts: 1599
Joined: Sun Apr 24, 2011 10:13 am
Real name and title: Hengky Latan
Location: AMQ, Indonesia
Contact:

Re: Interaction effects using PLS

Post by Hengkov »

Hi,

Please refer to the book of Hayes or Jose on PLS Literature.

Best regards,
Choukri
PLS Expert User
Posts: 114
Joined: Thu Apr 16, 2015 2:11 pm
Real name and title: Choukri MENIDJEL

Re: Interaction effects using PLS

Post by Choukri »

Hi,
Thank you for your response

I see that Hayes used in his book SPSS software to measure mediating and moderation effects, Does his process work with SmartPLS too?

What is special in Hayes' book to make it better than the above papers.

Greetings
js459
PLS Junior User
Posts: 5
Joined: Thu Jan 03, 2013 12:01 am
Real name and title:

Re: Interaction effects using PLS

Post by js459 »

I'm confused how to report results using both SmartPLS and Preacher and Hayes' "Indirect".

I analyzed my data for the measurement model using SmartPLS which provided me with reliability, validity, and R squared values. I also ran a bootstrap to get significance results. To test for mediation I used Indirect.

Now, I get t-values and p-values for the dependent and independent paths in SmartPLS and I get dependent, independent, and mediated t-values and p-values in Indirect. Which results do I report? Do I report the dependent and independent paths in SmartPLS and the total and indirect paths in Indirect or do I report the results for all of the paths from Indirect?

If anyone can help me it would be greatly appreciated. Also, if anyone knows of a study that uses both SmartPLS and Indirect to report results that would be of considerable help. Thank you!
User avatar
cringle
SmartPLS Developer
Posts: 818
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Re: Interaction effects using PLS

Post by cringle »

Avoid the circle path and/or use the latent variables scores from a model without a circular relationship and estimate the structural model with the circular path by using 2SLS (e.g. in the R program).
nayam
PLS Junior User
Posts: 1
Joined: Wed Sep 11, 2019 9:14 am
Real name and title: Nayan More
Contact:

Re: Interaction effects using PLS

Post by nayam »

It is helpful information. Thanks for sharing.
Post Reply