A model is proposed to represent individual differences in situation-behavior profiles. The model consists of 3 components: (a) q'ypologies of person, situation, and behavior classes; (b) hierarchical relations between the classes of each typology; and (c) a characterization of the person types in terms of different sets of if (situation class) then (behavior class) rules by which the 3 typologies are linked to one another. A data analysis technique (INDCLAS) is available to induce a triple typology model from empirical data. To reveal the psychological mechanisms behind such a model, the classes of the model can be related to situation, behavior, and person features. As a result, person types can be interpreted in terms of systems of cognitive-affective variables that mediate between active situation features and behavioral manifestations. This is illustrated with a study on selfreported hostile behavior in frustrating situations.According to Bem( 1983 ), the fundamental scientific task for personality research is to convert observations of particular persons behaving in particular ways in particular situations into assertions that certain kinds of persons will behave in certain kinds of ways in certain kinds of situations, that is, to construct triple typologies or equivalence classes--of persons, of behaviors, and of situations--and to fashion theories of personality that relate these equivalence classes to one another. (p. 566) Several authors other than Bern have underscored the importance of studying personality in terms of meaningful patterns of stability and change in well-defined groups of behaviors in relation to well-defined groups of situations (Allport, 1937;Claeys, Timmers, & Phalet, 1993;Golding, 1975;Mischel & Shoda, 1995;Olweus, 1976;Pervin, 1976;Shoda, Mischel, & Wright, 1993Wright & Mischel, 1987). In particular, Wright and Mischel, building on earlier work of Alston (1975), proposed a conditional approach to the study of personality, in which the fundamental unit of observation is not the unconditional probability of behavior but rather the conditional probability of a certain type of behavior given types of situations or psychological conditions. Within this context, differences between (classes of) persons may be conceived as differences in if (situation class) then (behavior class) rules. Wright and Mischel further assumed that the situation category as well as the behavior Kristof Vansteelandt and Iven Van Mechelen, Department of Psychology, Katholieke Universiteit Leuven, Leuven, Belgium.The research reported in this article was supported by North Atlantic Treaty Organization Grant CRG921321. We thank Seymour Rosenberg for his helpful comments on an earlier version of this article.Correspondence concerning this article should be addressed to Kristof Vansteelandt, Department of Psychology, Katholieke Universiteit Leuven, Tiensestraat 102, B-3000 Leuven, Belgium. Electronic mail may be sent to kristof.vansteelandt @psy.kuleuven.ac.be. category are prototype-based categories with vague boun...