Consistent PLS vs Regular PLS

This forum is closed, and read-only.
Locked
sam.89
PLS Junior User
Posts: 2
Joined: Sat Jul 15, 2017 7:46 pm
Real name and title: Samaneh fadayi

Consistent PLS vs Regular PLS

Post by sam.89 »

Hello all,

I have a question about using PLS Algorithm and Consistent PLS Algorithm in SmartPLS 3 (or PLS Bootstrapping versus Consistent PLS Bootstrapping). I heard that when I have all first order constructs measured as reflective, it is better to use consistent analysis. I ran my model with both, consistent one gives me better results regarding r square and path significance. However, two path coefficients are more than 1 in running the consistent analysis. This is not the case with regular analysis. Can someone help on this?

Regards,
Samaneh
jmbecker
SmartPLS Developer
Posts: 1281
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Consistent PLS vs Regular PLS

Post by jmbecker »

Do you have a higher-order construct? Then, you should use the two-stage approach and not the repeated indicator approach, when using PLSc.
You may also rethink, whether all reflective constructs truly follow a common factor type model or if they are not better represented by a composite (specify as formative).
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
sam.89
PLS Junior User
Posts: 2
Joined: Sat Jul 15, 2017 7:46 pm
Real name and title: Samaneh fadayi

Re: Consistent PLS vs Regular PLS

Post by sam.89 »

Thank you very much Dr. Becker for your response. Actually, I have higher order formative construct, but that construct is not endogenous and it is predicting other factors. So I do not think that I need to use the two stage.
Thanks,
Samaneh
jmbecker
SmartPLS Developer
Posts: 1281
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: Consistent PLS vs Regular PLS

Post by jmbecker »

But the repeated indicator approach does not work well with PLSc. Then you should just use PLS.
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
Locked