PLS-MGA: Grouping variable equals IV

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
Victoria01
PLS Junior User
Posts: 6
Joined: Wed Dec 20, 2017 11:33 am
Real name and title: Victoria Oers

PLS-MGA: Grouping variable equals IV

Post by Victoria01 »

Dear all,

I have a special issue concerning the application of MGA:

In my model, the independent variable is a categorical variable with three values that I included as two dummy variables. These variables lead via mediating effects to various DVs.
Now, I want to conduct an MGA to understand whether two categories of the categorical IV differ significantly from one another. Since I have mediating effects in my model, I need to keep the IV in my model while running the MGA with the IV as a grouping variable. However, in SmartPLS3 this is not possible.

Can you please tell me if there is a way to create this MGA with the IVs simultaneously as grouping variables? And if so, any advice on helpful literature is appreciated.

Thanks a lot in advance,
Victoria
jmbecker
SmartPLS Developer
Posts: 1282
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: PLS-MGA: Grouping variable equals IV

Post by jmbecker »

It is just not possible to run a MGA with the grouping variable in your model. Not in PLS and also not in other methods.

But you probably also don't need a MGA.
Your grouping dummies already gives you the possibilities to analyze your questions.
The effect of the dummies on your DVs indicate the mean change in the DV due to a change in the group. If you include interaction effects with other variables, you also can assess the change in path strength due to a change in treatment groups.
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
Post Reply