Analysis of ranked preference data using latent class models

Consumer preference analysis using rating experiments can alternatively be performed by means of ranking experiments. Ranking procedures seem particul arly easy to perform by a consumer, as are paired comparisons experiments. Among a variety of probability models on rankings, the Bradley-Terry-Mallow s model is considered. Segmentation panel approach, as well as fitting proc edure in the presence of covariates, are presented. The extension of the us e of the BTM model in the case of partial rankings, obtained from a balance d incomplete block design, is also proposed. The preference rankings analys is including segmentation approach, covariates incorporation and/or incompl ete block design is illustrated in terms of an example involving the rankin g of seven extruded snacks by a panel of 56 consumers. (C) 1999 Elsevier Sc ience Ltd. All rights reserved.