forum.smartpls.com

Hi all

I have a model like the one in the attached file.

The construct IT is a reflective-formative model - it has its own factors but at the same time it is a factor to another variable.

1. Should I use PLS or consistent PLS in this case?
2. Do I need to treat it as a higher order construct (repeated indicators / two-step approach)?

I have read lots of forum discussions, videos, articles but sorry - I am still very confused! Much appreciate your help to strike me with clarity.

Hi all,

I have the same questions with Rebecca.I also collected data for the "second-order construct" (with its own indicators - x1, x2 and x3) and there are three "first-order constructs" (with their own indicators) affect it, but do I need treat it as the second-order construct and conduct HOC analysis?

Really appreciated for your help.

If the construct has its own indicators, it is not a higher-order construct. A higher-order construct is generally describes as a construct where not some direct observed indicators are available for measurement, but some other latent variables are the actual measures (the lower-order constructs). Then there are different strategies (repeated indicators, two-stage, etc.) to identify the higher-order construct.
If you have direct measures, it is just a different constructs, maybe at a different level of abstraction, but still a normal latent construct.

Whether to use PLS or PLSc is a question of whether you want to estimate a composite or common factor model for your reflective constructs. You may read the recent literature on these topics to familiarize yourself with the questions. Our Smartpls website provides some helpful suggestion for literature in this regard: e.g., https://www.smartpls.com/documentation/ ... d-when-not

Thank you very much Dr. Becker for the clear and helpful answer.