Comparing alternative methods for conjoint analysis: A case of tomatoes in the German market

Conjoint analysis is a multi-attribute, decompositional and analytical method for estimating the consumer’s preference structure from a global evaluation of a set of alternatives on the basis of a series of different attributes and their possible combinations. Conjoint analysis is mature and widely used in the study of consumer goods, recently, this analytical technique is been used in the study of food, and to date, few studies have used the technique in the study of fruits and vegetables. In this paper, the authors used three alternative methods (ordinary least squares, ordered Logit, and doublycensored Tobit) for estimating preference through conjoint analysis with respect to one of the most highly consumed vegetables in the world: Tomatoes. In particular, the authors studied the tomato market in Germany. They consider four particularly important attributes in vegetable purchase behaviour among German consumers: Level of freshness, country of origin, price, and production method. The results obtained using these three estimation methods provide significant coefficients in all cases, although significant differences do exist in the importance of the different attributes in function of the estimation methods used. Nevertheless, two of the three methods coincide in pointing to the level of freshness as the most important attribute of tomatoes for German consumers.