CLUSTERING OF VARIABLES, APPLICATION IN CONSUMER AND SENSORY STUDIES

We consider two dissimilarity measures between variables that take acc ount of the variances of the variables as well as of their correlation s. When variables are standardised, we retrieve widely used dissimilar ity measures. The first dissimilarity measure is Euclidean distance an d is suitable in studies where negative correlation between variables implies disagreement. The second dissimilarity measure is a Procrustea n distance and is suitable in situations where both positive and negat ive correlations imply agreement. We also discuss aggregation strategi es in order to carry out hierarchical clustering and fund groups of va riables. Applications in consumer and sensory studies are outlined. (C ) 1997 Elsevier Science Ltd. All rights reserved.