Conjoint Use of Variables Clustering and PLS Structural Equations Modeling

Valentina Stan (1) , Gilbert Saporta (2)

1 ESSCA - Ecole Supérieure des Sciences Commerciales d'Angers
2 CEDRIC - MSDMA - CEDRIC. Méthodes statistiques de data-mining et apprentissage

In PLS approach, it is frequently assumed that the blocks of variables satisfy the assumption of unidimensionality. In order to fulfill at best this hypothesis,we use clustering methods of variables. We illustrate the conjoint use of variables clustering and PLS structural equations modeling on data provided by PSA Company (Peugeot Citroën) on customers? satisfaction. The data are satisfaction scores on 32 manifest variables given by 2,922 customers.

Mots clés: PLS; Structural equations; Cluster analysis

Mots clés: Analyse typologique; Équations structurelles

Domaines: Statistiques [math.ST]

Valentina Stan, Gilbert Saporta. Conjoint Use of Variables Clustering and PLS Structural Equations Modeling. Springer. Handbook of Partial Least Squares,, Springer Berlin Heidelberg, pp.235-246, 2010, 978-3-540-32825-4. ⟨10.1007/978-3-540-32827-8_11⟩. ⟨hal-01125749⟩