In the development of a psychometric scale, my original plan was EFA and then CFA. However, I've just realised that my theoretical model is one of a composite variable with causal indicators, rather than a latent variable with effect indicators.
As the indicators are likely to be causing the variable (rather than the other way around), I'm now unsure whether EFA is still the correct starting point. I'm also wondering whether Confirmatory Composite Analysis should be the second stage rather that CFA.
This is a relatively new area for me, so I would very much appreciate any advice please! Thank you!
I recommend that you take a look at the work of Jörg Henseler, Florian Schuberth, and colleagues on confirmatory composite analysis:
https://scholar.google.com/scholar?hl=de&as_sdt=0%2C49&q=henseler+composite+analysis&oq=henseler+composite+ana
- Badges
- Science topic
- Similar topics
- Social Science
- Media
- Journalism