A Conjoint Approach to Model Product Preferences: The New England Market for Fresh and Frozen Salmon

This paper illustrates how conjoint analysis can be used to model preference for food products, and applies the technique to the study of fresh and frozen salmon preference among buyers from two intermediary wholesale levels in New England. The degree of preference for specific attributes and levels of the products is compared. The paper also evaluates the performance and predictive validity of a traditional additive conjoint model, a hybrid model estimated using both ordinary least squares, and a maximum likelihood hybrid two-limit Tobit model.