forum.smartpls.com

I have a model in which a construct is measured using the two-step approach where the L.V scores obtained in the first step are used to run the entire model. I am consulting the steps for IMPA as recommended by Ringle and Sarstedt, 2016. The minimum requirement states that the latent variable scores should be such that they can be re-scaled from 0 to 100.
As my model includes a second-order construct which is also connected to other constructs in the full model. How can I run IMPA for the complete model as the min and max for the construct measured using a two-step approach are -3.371 to 2.137 rescaling this construct's values will not fall in the 0 to 100 range which is one of the essential requirements to run the analysis.

Please Help.

You need to run the IPMA also for the first-stage model and then take the unstandardized latent variables scores as indicators into the next stage. This is something that I would generally recommend, as you will get the same standardized results, but have some additional flexibility. For example, it is also necessary if you want to use PLSPredict or something else that operates on unstandardized data.

Thanks, Dr. Becker. Can you suggest any related literature if possible?

There is no literature on this yet.