Several Moderating Effects (SmartPLS3)

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
plueschke
PLS Junior User
Posts: 3
Joined: Fri Nov 14, 2014 11:01 am
Real name and title: Boris Plüschke

Several Moderating Effects (SmartPLS3)

Post by plueschke »

Dear all,

why is it impossible to reuse the same variables for computing a moderating effect for different endogenous constructs?

Within my model, I have one independent variable then three mediating ones and then three dependent variables. Furthermore each mediating variable is connected with each dependent variable. When trying to use a further variable for moderating effects on all relations between the mediating variables and the dependent variables, SmartPLS 3 is giving an error massage which states that my latent variables have to be unique.

Why? Am I misapplying SmartPLS 3 or is there a new restriction?

Best & Thanks
jmbecker
SmartPLS Developer
Posts: 1284
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Several Moderating Effects (SmartPLS3)

Post by jmbecker »

First, you need to have at least two variables predicting your dependent variable to include an interaction term. The interaction term is, like in regression, based on a product term (with different approaches to generate the product term: Two Stage, Product Indicators, Othrogonalizing). If you only have one antecedent it is neither possible nor meaningful to create an interaction term.

Second, as we have to include the product term in the inner model regressions, the interaction term must be unique to one dependent variable. However, you can include the same interaction several times for all your dependent variables or multiple different interaction terms, if you like. It is just not possible to have one for all.
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
plueschke
PLS Junior User
Posts: 3
Joined: Fri Nov 14, 2014 11:01 am
Real name and title: Boris Plüschke

Re: Several Moderating Effects (SmartPLS3)

Post by plueschke »

The first aspect is no problem as I have several latent variables pointing at one endogenous construct.
However, the second seems to be the problem as I am trying to include the same interaction several times for all my dependent variables (not for the same one). However, then I am receiving the error massage, as you can see at the picture.
Attachments
Problem.jpg
Problem.jpg (204.86 KiB) Viewed 5848 times
plueschke
PLS Junior User
Posts: 3
Joined: Fri Nov 14, 2014 11:01 am
Real name and title: Boris Plüschke

Re: Several Moderating Effects (SmartPLS3)

Post by plueschke »

Oh. The ability to read is sometimes very helpful and renaming the moderating effects is the road to success.

Nevertheless in SmartPLS 2 this (maybe useful) restriction was not implemented and I have discovered a new feature.
bradley7680
PLS Expert User
Posts: 51
Joined: Tue Nov 04, 2014 5:27 am
Real name and title: Dr. Bradley Wilson. Senior Lecturer in Advertising. School of Media and Communication. RMIT University.

Re: Several Moderating Effects (SmartPLS3)

Post by bradley7680 »

see my thesis and sage PLS handbook contribution here

See my contribution in PLS handbook. SAGE

or get it off my Researchgate.

Bradley Wilson.
https://www.researchgate.net/profile/Bradley_Wilson2
Bradley Wilson. Ph.D. Senior Lecturer in Advertising. School of Media and Communication. RMIT University. Melbourne, Australia.
SEE: http://www.researchgate.net/profile/Bradley_Wilson2 http://scholar.google.com.au/citations? ... AAAJ&hl=en
Post Reply