Dear all,
I have modelled an exogenous construct as a second-order construct with five latent variables.Since the number of indicators for each latent variable varies (between 3 and 8 indicators), the two-stage approach should be applied, otherwise the relationships between the first-order constructs and the second-order construct will be distorted, right?
Now to the actual question: For my second-order construct, I have additionally measured a manifest indicator. Can I somehow integrate this indicator into the analysis? Or can second-order constructs only be modelled as latent variables without manifest indicators?
Best
Rob