MODELING MEAL ACCEPTABILITY IN A FREE-CHOICE ENVIRONMENT

The difficulties of predicting overall meal acceptability when subject s have complete freedom to select from a wide range of possible foods are discussed, and some solutions offered in the context of a study co nducted in a student cafeteria. We identified several subgroups in the data corresponding to different types of meals and modelled these sep arately. Tree diagrams were found to be a useful aid to identifying su bgroups and provided a quick summary of the numbers of subjects select ing specific meal combinations. Some of the problems of using multiple linear regression to model overall acceptability are discussed, parti cularly the related problems of varied meal sizes and missing values i nherent in a free selection environment.