PLS path modelling and multiple table analysis. Application to the cosmetic habits of women in Ile-de-France

Many statistical methods can be used to study data presented in the form of J blocks of variables observed on the same subjects. The most well-known m ethods are the following: Horst's generalised canonical correlation analysi s, Carroll's generalised canonical correlation analysis, Escofier and Pages ' multiple factor analysis and second order confirmatory factor analysis. T he aim of all these methods is to identify a common structure among the J d ata tables. The partial least squares (PLS) Path modelling approach of Herm an Wold can also be used on this type of data. Generalised canonical correl ation analyses of Horst and Carroll and multiple factor analysis are specia l cases of PLS Path modelling, but this approach also leads to new useful m ethods. In the first part of this paper, we briefly review PLS Path modelli ng, then we look in greater detail at the specific case of tables without s tructural relations, In the second part, we have applied PLS Path modelling to a study of the cosmetic habits of women in the Ile-de-France region. Lo hmoller's LVPLS software release 1.8 allowed us to carry out the applicatio n without too many difficulties. (C) 2001 Elsevier Science B.V. All rights reserved.