When not to use PLSc?

[MLindsay]

Hi,

I am working on a study with a very simple model with one exogenous and one endogenous construct. The exogenous construct has 8 reflective indicators and the endogenous construct has 5 reflective indicators. The sample size is 214 at this time. Is PLSc warranted in this case, or is basic PLS okay to use? The loadings are very nice in basic PLS, but some drop below acceptable levels using PLSc.

Please advise.

Thank you for any assistance you can offer.

Mark

[cringle]

If you like to mimic common factor models (and CB-SEM), PLSc and fit measures may be useful:
https://www.smartpls.com/documentation/ ... ith-cb-sem

If you use composite models, you may just want to use PLS; also PLSc can be used to estmate a model that uses both common factor models and composite models. For the decision, which proxy you would use for a latent variable (composite or common factor), you may find this article useful:
http://www.sciencedirect.com/science/ar ... 6316304404

Best
Christian