Full Measurement Invariance and then?

Small talk on SmartPLS that does not correspond to the other forums!
Post Reply
yang
PLS Junior User
Posts: 3
Joined: Mon Jun 25, 2018 1:38 pm
Real name and title: Xi Yang

Full Measurement Invariance and then?

Post by yang » Mon Jun 25, 2018 2:07 pm

Dear All,

I ran the MICOM for MGA and fortunately, I got the result as full measurement invariance. It means that the different groups can be pooled and moderator analyses are permitted. Here is the question... Does the result mean that I can potentially choose two different ways for the further analyses 1) compare path coefficients across groups or 2) merge the data and set a dummy variable as the moderator in the model? Or the second option (merge the data) has to be chosen due to full measurement invariance. By given the research design as an experimental setting (no treatment vs. treatment), I tend to choose path coefficients comparison.

A second opinion is really appreciated. Thank you!

jmbecker
SmartPLS Developer
Posts: 888
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Full Measurement Invariance and then?

Post by jmbecker » Mon Jun 25, 2018 7:03 pm

You can choose.
However, I would think about the objective of your experimental design. With an MGA you can only see if your path coefficients change due to the treatment (i.e., you can only assess the interaction of treatment will all predictors). When you use dummies you can also test if the treatment has an effect itself (i.e., a level difference in the focal constructs).
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

yang
PLS Junior User
Posts: 3
Joined: Mon Jun 25, 2018 1:38 pm
Real name and title: Xi Yang

Re: Full Measurement Invariance and then?

Post by yang » Tue Jul 03, 2018 9:40 am

Great Thanks!

Post Reply