Typeness of personality profiles: a continuous person‐centred approach to personality data
I propose a new method of analysing personality profiles based on multiple traits. Personality profiles are regressed within individuals on prototypic profiles for personality types. To increase reliability, empirical Bayes estimates as obtained from hierarchical linear modelling (HLM) are used. The regression coefficients are interpreted as typeness, the extent to which the individual personality profile deviates from the mean profile in the sample consistent with the deviations of the personality types. These continuous parameters of typeness are subsequently used in between‐person analyses. This method was applied to two studies of Big Five profiles that were related to prototypic profiles for overcontrollers and undercontrollers. The typeness parameters, if reliable, showed a longitudinal stability and an external validity similar to the Big Five scales. The merits and limits of the proposed approach for the description of, and prediction from, personality are discussed. Copyright © 2006 John Wiley & Sons, Ltd.