Structural equation modeling (SEM) is used to test theories and concepts, and for exploratory research, by assessing latent variables at the observation level (outer or measurement model) and testing relationships between latent variables on the theoretical level (inner or structural model).

When applying SEM, researchers must consider two types of methods: covariance-based techniques (CB-SEM) and variance-based partial least squares (PLS-SEM).

Refer to:

• Hair et al., "An assessment of the use of partial least squares structural equation modeling in marketing research", 2012 -

  Article An Assessment of the Use of Partial Least Squares Structural...

• Sarstedt et al., "Partial Least Squares Structural Equation Modeling", 2021 -

  Chapter Partial Least Squares Structural Equation Modeling