Collection and analysis of perceived product inter-distances using multiple factor analysis: Application to the study of 10 white wines from the Loire Valley

Abstract

The concept of sensory distance between products is familiar. It is used mainly in graphical displays, for example provided by principal components analysis carried out from conventional profiles. In such a methodology, the importance (or weight) granted to the descriptors by the subjects is not taken into account in the averaging process. To take into account these weights, two practices can classically be used: similarity scaling and multidimensional sorting. Here a third way is proposed: the direct collection of perceived inter-products distance by each subject. In this method, each subject is asked to position the products onto a large sheet of paper according to the sensory distances he perceives between the products. Thus, for each subject, the data consist in a bi-dimensional configuration of the products. These configurations can be analysed by multiple factor analysis. This procedure is described here and applied to 10 white wines from the Loire Valley; the results are interpreted with the help of a classical descriptive sensory analysis.