Given numbers (θ_1^*, θ_2^*, …, θ_γ^*, P^*), the smallest sample size is determined so that the probability of a correct selection and ranking is at least as large as P^* when the true (but unknown) ratio of the i-th to the (i+1)-th largest of cell probabilities is greater than or equal to θ_i^*(i=1,2,…, γ). The selection and ranking procedure is illustrated by an example in sensory evaluation.
