forum.smartpls.com

Usually, researchers treat those 7-point Likert scales as quasi-metric and thus continuous. That would suggest using an interaction effect approach. In contrast, dichotomization using high and low values, for example, using a median split might lose information and is generally seen less favorably. ...

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). T...

Given the statistics, discriminant validity at least may be a problem. You need to deal with that. Either by arguing why you think that the constructs are conceptually different despite the opposite finding from the statistics (and why the discriminant validity may not be a problem in your model), o...

If theory does not allow to tell you which type of construct you have (formative or reflective), what type of constructs are that? Are you inventing these constructs? Still you need to think about whether the indicators (first-order constructs) are causing or being caused by the constructs (formativ...

The next version 3.2.9, which we are just about to finish and which should be published this year will include PLS-MGA and Permuation also for PLSc.

Shmueli, G., Sarstedt, M., Hair, J.F., Cheah, J.-H., Ting, H., Vaithilingam, S., & Ringle, C.M. (2019). Predictive model assessment in PLS-SEM: Guidelines of using PLSpredict, European Journal of Marketing, 53(11), 2322-2347.

Actually, you should better use the unstandardized latent variables scores from the IPMA as indicators on the second stage to conduct the CTA. Usually, it does not make much of a difference, whether you use unstandardized or standardized latent variable scores as indicators, but the CTA works on cov...

The relative impact may be large, but if you omit the construct other construct will take its role and explain the same variance in the dependent construct. This is likely due to some (high) collinearity between the variables.

If an interaction term (e.g., A·C) is in the model, it is indispensable to always include all simple effects (A->B and C->B) in the model. Excluding simple effects will bias all other estimates in an interaction model. This is a general requirement of moderating models. Thus, SmartPLS does not allow...

Yes.

You will get this from the PLS output > Latent Variables > Latent Variable Correlation

Our FAQ provide the solution: https://www.smartpls.com/faq/problems/heap-space

Thank you for your suggestion. We will try to implement such a feature in future releases.

SmartPLS 3 should be able to do all the calculations as well. As far as I remember the paper, it also involves some hand calculations outside of Adanco. That would also be necessary in SmartPLS, but generally SmartPLS has the same and even more capabilities than Adanco.

1) Yes. The bootstrapping procedure standardizes each sample and not the original data that it samples from. In this sense we are following Hayes recommendation, although this has been the standard practice in PLS much longer than Hayes Macros exist. Because it is something not only important for th...