Electronic Journal of Applied Statistical Analysis EJASA (2011), Electron. J. App. Stat. Anal., Vol. 4, Issue 2, 265 – 276 e-ISSN 2070-5948, DOI 10.1285/i20705948v4n2p265 © 2011 Università del Salento – http://siba-ese.unile.it/index.php/ejasa/index 265 THE IMPACT OF CHEMICAL AND SENSORY CHARACTERISTICS ON THE MARKET PRICE OF ITALIAN RED WINES Eugenio Brentari, Paola Zuccolotto * Department of Quantitative Methods, University of Brescia, Italy Received 03 October 2010; Accepted 27 June 2011 Available online 14 October 2011 Abstract: The hedonic price analysis presented in this paper is carried out on a dataset containing observable, sensory and chemical characteristics of a sample of Italian red wines. The study starts from the commonly observed evidence that in general the market price can be explained by the objective characteristics appearing on the label of the bottle and not by the wine’s quality. The aim of the analysis is to discover how quality matters. This objective is pursued by means of the construction of latent sensory and chemical factors, whose implicit value, quantified using Random Forest variable importance measures, turns out to be appreciably high. Keywords: Hedonic price of wine, canonical correlation, Random Forest. 1. Introduction The hedonic price method aims at analyzing the relationship between a product ’s price and its quality. In general, the method consists in a (possibly nonlinear) regression analysis of the price on the characteristics of the product. The implicit value of a characteristic is then given by the importance of the product attribute in the prediction of price, according to the above regression model. The implicit value of a given feature can be different from what we mean to be its role in the quality of the product, as the former is influenced by market mechanisms, while the latter is concerned with the domain of intrinsic quality. The analysis of hedonic price is able to highlight these differences, thus assessing the market effect on the definition of price. For a long time the * Corresponding author. E-mail: zuk@eco.unibs.it