About testing of Moderating Effect

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
thomasmakz@gmail.com
PLS Junior User
Posts: 4
Joined: Wed Dec 02, 2015 12:23 pm
Real name and title: Thomas Mak

About testing of Moderating Effect

Post by thomasmakz@gmail.com »

Dear, if there is a significant relationship between A and B (A-->B), and i would like to know what is the right way to test the moderating effect (for example: gender). What test should i use?
some people use (Gender * A --> B) to test moderating effect (SmartPLS 3) and some use MGA to run a t-test between A-->B (male) and A-->B (Female)?
Please help.
Thank you
jmbecker
SmartPLS Developer
Posts: 1282
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: About testing of Moderating Effect

Post by jmbecker »

Generally, both approaches should lead to more or less the same conclusion.
I would use the interaction approach if I have only one path that is affected by gender and the multi-group approach if I assume that several paths in my model are affected by gender.
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
smardiana
PLS Junior User
Posts: 1
Joined: Wed Oct 24, 2018 1:58 am
Real name and title: Siti Mardiana

Re: About testing of Moderating Effect

Post by smardiana »

Thank you, Dr. Becker.
That explanation is exactly what I need: when to use moderator vs. MGA.
Post Reply