A0772
Title: A non-iterative algorithm for structural equations modeling
Authors: Arthur Tenenhaus - Laboratoire Signaux et Systemes (France) [presenting]
Michel Tenenhaus - HEC School of Management (France)
Abstract: Structural equation modeling is presented with factors and composites in the framework of the basic design. Two estimation methods are discussed. The first one is a new non-iterative method based on singular value decomposition calculations (SVD-SEM). This new approach produces consistent and asymptotically normal estimators of the parameters. Then, the restricted maximum-likelihood approach (ML-SEM) is described. SVD-SEM and ML-SEM are compared in a Monte Carlo simulation on a nonrecursive model with factors and composites and in a case study on a model with factors.
