A collinearity based hierarchical method to identify clusters of variables

The most frequently used hierarchical methods for clustering of quantitative variables are based on bivariate or multivariate correlation measures. These solutions can be unsuitable in presence of uncorrelated but collinear variables. We propose a new measure of collinearity between groups of variables that can be used for their hierarchical clustering. Its main theoretical features are described and its performance is evaluated both on simulated and real data sets.