We present a new approach to estimating outer weights in PLS Path Modeling that is fully based on the PLS principle. Two new modes are presented for estimating the measurement model: PLScore Mode with standardized scores and oriented to maximizing correlations between
latent variables (LVs); PLScow Mode with constrained weights and oriented to maximizing covariances between LVs. Both modes involve integrating a PLS Regression as an estimation technique within the outer estimation phase of PLS-PM. However, in PLScore Mode a PLS Regression is run under the classical PLS-PM constraints of unitary variance for the LV scores, while in PLScow Mode the outer weights are constrained to have a unitary norm thus importing the classical normalization constraints of PLS Regression.
TRINCHERA, L., RUSSOLILLO, G. et ESPOSITO VINZI, V. (2011). Multi-component Estimation of PLS Predictive Path Modeling. Dans: 58th World Statistics Congress of the International Statistical Institute (ISI 2011).