Karen Draney

A Technique for Setting Standards and Maintaining Them over Time

This paper describes a new procedure for standard setting based on item response maps (“Wright maps”). Motivation for the technique is discussed, and variants of the item response formulation are shown. An example based on the Golden State Examinations is used as a context for the discussion, and for some results.

Application of the Saltus Model to Stagelike Data: Some Applications and Current Developments

The saltus model was developed in dichotomous form by Wilson (1989), and expanded to polytomous form by Draney (1996) as a method for detecting and analyzing discontinuities in performance that are hypothesized to occur as a result of rapidly occurring person growth (e.g.,Fischer, Pipp, & Bullock, 1984). Such discontinuities are often theorized to occur as the result of progression through developmental stages or levels. The most influential such theory was developed by Jean Piaget (e.g., Piaget, 1950; Inhelder & Piaget, 1958). Although Piagetian theory has been somewhat controversial of late (e.g., Lourenco & Machado, 1996), there is still a strong interest in stagelike development in a number of areas, including moral and ethical reasoning (e.g., Dawson, 2002; Kohlberg & Candee, 1984), evaluative reasoning (e.g., Dawson-Tunik, 2002; Armon, 1984), adult development (e.g., Commons et al., 1998; Fischer, Hand, & Russel, 1984), and cognitive development (e.g., Bond, 1995b,a; Bond & Bunting, 1995; Demetriou & Efklides, 1989, 1994; Hiele, 1986).

A Strategy for the Assessment of Competencies in Higher Education

The Berkeley Evaluation and Assessment Research (BEAR) Center has developed an assessment system called the BEAR Assessment System (BAS), which is based on four principles of sound assessment (Wilson, 2005). In turn, each principle is associated with a practical “building block” that embodies the way in which the principle is used in an assessment context, and the whole system is brought together by an integrative activity that can take on different aspects under different circumstances (e.g., assessment moderation, cut score setting, etc.).

A General Saltus LLTM-R for Cognitive Assessments

The purpose of this paper is to propose a general saltus LLTM-R for cognitive assessments. The proposed model is an extension of the Rasch model that combines a linear logistic latent trait with an error term (LLTM-R), a multidimensional Rasch model, and the saltus model, a parsimonious, structured mixture Rasch model. The general saltus LLTM-R can be used to (1) estimate parameters that describe test items by substantive theories, (2) evaluate the latent constructs that are associated with the knowledge structures of the test items, and (3) test hypotheses on qualitative differences between the sub-populations of subjects with different problem solving strategies, cognitive processes, or developmental stages. Bayesian estimation of the proposed model is described with an application to a test of deductive reasoning in children.