The STATIS Method

STATIS is a generalization of principal component analysis (PCA) whose goal is to analyze several sets of variables collected on the same set of observations. It is attributed to Escouffier (1980) and L’Hermier des Plantes (1976, see also Lavit et al., 1994), a related approach is known as procrustes matching by congruence coefficients in the English speaking community (Korth & Tucker, 1976). The goal of STATIS is 1) to compare and analyze the relationship between the different data sets, 2) to combine them into a common structure called a compromisewhich is then analyzed via PCA to reveal the common structure between the observations, and finally 3) to project each of the original data sets onto the compromise to analyze communalities and discrepancies. STATIS is used in very different domains such as sensory evaluation (e.g., Qannari et al., 1995; Schlich, 1996; Chaya et al., 2003), molecular imaging (Coquet et al., 1996) brain imaging (e.g., Kherif et al., 2003), ecology (Thioulouse et al.,), and chemometrics (Stanimirova et al., 2004).