Procedure to analyse possible "Confounding variable" and spurious effects in SMARTPLS

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
Alexg
PLS User
Posts: 12
Joined: Fri May 18, 2018 11:34 am
Real name and title: Mr. Alessandro Grillo

Procedure to analyse possible "Confounding variable" and spurious effects in SMARTPLS

Post by Alexg »

Dear smartpls users,

I am trying to analyse the relationship between two latent variables A--->B.

However, in doing so, I am also trying to control for a possible confounding variable "C" and check for any spurious effects. In plain words I would like to strengthen the hypothesis of causal relationship between variables A and B and make sure that their positive relationship would be there regardless any effect of "C" on both of them.

My question is:
What procedure is best to use in this kind of situation?

Should I compare two different models? The first one with A--->B and the second one introducing the supposed "Confounding" variable "C" pointing at both variables (C--->A, C--->B and A--->B) and then check what happens to the path coefficients A--->B when "C" is controlled for?

Also, C is a single item continuous variable!

Thank you in advance for reading this!
Alex
jmbecker
SmartPLS Developer
Posts: 1281
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Procedure to analyse possible "Confounding variable" and spurious effects in SMARTPLS

Post by jmbecker »

If you want to show that there is an effect of A on B controlling for C then you should estimate that model including C.
If you want to show that controlling for C does not change the effect of A on B then you need to estimate both models.
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