The main reasons to include higher order model t is to reduce the number of relationships in the structural model, making the PLS path model more parsimonious and easier to grasp (Hair et al., 2014).
The PLS path modeling algorithm requires that every latent variable has at least one manifest indicator. Phantom variables are not possible.
Solution: Repeated-indicator approach (Wold, 1982; Lohmoller, 1989).
Exercise 1: Download data set here, draw the model below and analyze.
Exercise 2: Download the dataset here, and draw the model below.
Exercise 3: Download a project here.