Abstract
In order to categorize (classify) craniofacial forms, varying linear dimensional arrays from a series of pretreatment cephalographs (‘A’ records) were subjected to cluster analysis. The derived subgroups (clusters) not only showed inconsistencies in their component patients, but also their ‘nearest neighbors’, i.e. cases identified as being most similar to one another. This study, therefore, emphasized the need to devise more appropriate cephalometric appraisal techniques for patient categorization (diagnosis).