Control variables lead to decreased AVE

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
Twanneman
PLS Junior User
Posts: 1
Joined: Thu Jun 15, 2017 8:20 pm
Real name and title: Twan Akkers

Control variables lead to decreased AVE

Post by Twanneman »

Hello all,

I'm having troubles with implementing my control variables at my DV. My DV scores good on AVE (above .5) but when I add the control variables to my DV, AVE for the DV drops below .5. Normally I would say leave the control variables out, but they significantly correlate with my DV and therefore I suppose I have to keep them in my final model....
I really don't know how to fix this....

Thanks in advance and kind regards,

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

Re: Control variables lead to decreased AVE

Post by jmbecker »

The PLS algorithm estimates the model parameters context dependent. Thus, adding another variable slightly changes the results also for other model parts.
Usually the change is very minor (i.e., slightly changes the results...). Only if the measurement in the some parts of the model is very unstable/unreliable (e.g., relatively low loadings or weights) than a change in the model (e.g., adding another variable) can have a larger effect on the model parameters.
I would also suspect that the AVE before adding the control variable was only slightly above 0.5, right?
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