Describes an integrated approach to test development and administration called computer-adaptive sequential testing (CAST). CAST incorporates adaptive testing methods with automated test assembly. Describes the CAST framework and demonstrates several applications using a medical-licensure example. (SLD)

Proposes two new methods for item-exposure control, the Progressive method and the Restricted Maximum Information method. Compares both methods with six other item-selection methods. Discusses advantages of the two new methods and the usefulness of combining them. (SLD)

Summarizes the benefits of computerized assessment and provides a review of some practical issues concerning measurement, item and examinee characteristics, hardware, and software. Adequate measures of reliability and validity have been established for many computer-based tests, and the benefits of computer testing have been realized in applied…

Compared five item selection rules with respect to the efficiency and precision of trait (theta) estimation at the early stages of computerized adaptive testing (CAT). The Fisher interval information, Fisher information with a posterior distribution, Kullback-Leibler information, and Kullback-Leibler information with a posterior distribution…

Used Monte Carlo simulation to compare the relative measurement efficiency of polytomous modeling and dichotomous modeling under different scoring schemes and termination criteria. Results suggest that polytomous computerized adaptive testing (CAT) yields marginal gains over dichotomous CAT when termination criteria are more stringent. Discusses…

Evaluated procedures applying person-fit indices to identify individuals who had previously memorized test items in computerized adaptive-testing situations. All of the indices studied showed little power to detect the use of memorization. Discusses possibilities for altering a test when the model becomes inappropriate for an examinee. (SLD)

Provides an overview of computerized adaptive testing (CAT) and introduces contributions to this special issue. CAT elements discussed include item selection, estimation of the latent trait, item exposure, measurement precision, and item-bank development. (SLD)

The second edition of "Computerized Adaptive Testing" contains new materials related to: (1) chapter 2, system design; (2) chapter 4, item response theory, item calibration, and proficiency estimation; and (3) chapter 10, caveats, pitfalls, and unexpected consequences. The book raises critical computerized adaptive testing research and application…

Computer-based testing by credentialing agencies has become common; however, selecting a test design is difficult because several good ones are available - parallel forms, computer adaptive (CAT), and multistage (MST). In this study, three computer-based test designs under some common examination conditions were investigated. Item bank size and…

Item-exposure control in computerized adaptive testing is implemented by imposing item-ineligibility constraints on the assembly process of the shadow tests. The method resembles Sympson and Hetter's (1985) method of item-exposure control in that the decisions to impose the constraints are probabilistic. The method does not, however, require…

It is unrealistic to suppose that standard item response theory (IRT) models will be appropriate for all the new and currently considered computer-based tests. In addition to developing new models, we also need to give attention to the possibility of constructing and analyzing new tests without the aid of strong models. Computerized adaptive…

This work presents innovative cybernetics (feedback) techniques based on Bayesian statistics for drawing questions from an Item Bank towards personalized multi-student improvement. A novel software tool, namely "Module for Adaptive Assessment of Students" (or, "MAAS" for short), implements the proposed (feedback) techniques. In conclusion, a pilot…

The authors reported findings from 3 studies examining the efficacy of Five Standards pedagogy in raising student achievement. Studies 1 and 2 were randomized designs; Study 3 was a quasi-experimental design. Samples included 53 teachers and 622 predominantly low-income Latino students in Grades 1-4. Studies assessed model fidelity with the…

In the process of item calibration for a computerized adaptive test (CAT), many well-established calibrating packages show weakness in the estimation of item parameters. This paper introduces an on-line calibration algorithm based on the convexity of likelihood functions. This package consists of: (1) an algorithm that estimates examinee ability…

Measures of consistency and completeness of order relationships derived from test data such as Guttman scales are proposed. The measures are generalized to apply to incomplete data such as data from tailored testing. (Author/JKS)