NUMERICAL TAXONOMY AND THE PRINCIPLE OF MAXIMUM-ENTROPY

The standard procedure in numerical classification and identification of micro-organisms bared on binary features is given a justification b ased on the principle of maximum entropy. This principle also strongly supports the assumption that all characteristics upon which the class ification is based are equally important and the use of polythetic tax a. The relevance of the principle of maximum entropy in connection wit h taxonomic structures based on clustering and maximal predictivity is discussed. A result on asymptotic separateness of maximum entropy dis tributions has implications for minimizing identification errors.