Abstract: A method of forming a cohort for use in identification of an individual by comparing a model of characteristics of the individual, such as a model of utterances, with models of the cohort including a model for the client in respect of whom it is desired to test whether the individual is identifiable. Models related to the population excluding the client are tested to determine whether they meet an acceptance threshold test as to identify with a model for the client. Then, from each meeting the threshold test, it is determined whether those models are distributed so as to present at least a substantial probability that models for nonmembers of the population spaced from the client model in all directions will each be closer to a member of the cohort, excluding the client, than to the client. If that probability is less than a predetermined value, a selection is made from the population of another cohort member which will reduce that probability.