I would like to model Knowledge as a formative composite measure using PLS. I understand that formative measures alone are unidentifiable and unfortunately, I don't have any outcome variables to include in the model. I'm wondering if I could use the repeated indicator approach to model only the measurement of a construct by turning indicators into single-item first-order constructs and the composite a second order construct?
Also, I'm wondering if anyone is familiar with Adanco? Adanco is able to estimate item loadings of a composite construct, although the weights are all equal when using Mode B. Would modeling the variable this way be any more useful than simply calculating item-total correlations?
It is mandatory to have factors along with latent constructs in PLS or AMOS
I order to test if the formative indicators result in substantially high R-Squared (also known as redundancy analysis), you can define one single indicator of the tentative outcome of all the formative indicators. If you are taking the composite of the multiple dimensions, you must understand that the dimensions should have substantial correlation amongst them, and secondly, the development of a composite should justify theoretically.
- Badges
- Science topic
- Similar topics
- Psychometrics
- Measurement