A method is proposed that increases the accuracies of estimation of the operating characteristics of discrete item responses, especially when the true operating characteristic is represented by a steep curve, and also at the lower and upper ends of the ability distribution where the estimation tends to be inaccurate because of the smaller number…

Using simulated item response data, the performance of several "robust" and conventional schemes for ability estimation was evaluated in conjunction with logistic item response theory models (one, two, and three parameter models). The simulated item response data were generated using a model that is more complex than are the usual…

The symposium, "Taming the Rasch Tiger: Using Item Response Theory in Practical Educational Measurement," was organized to deemphasize the technical complexities of item response theory (IRT) and to show the audience how IRT can be used in practical educational measurement. Four papers from the symposium are summarized and comments are…

The design and architecture of two user-controlled, computer-based problem analysis environments in classical mechanics are discussed. In the expert-like environment, the user analyzes problems according to a hierarchical concept schema consistent with how experts analyze novel problems in physics. In the second environment, the user searches a…

Seventy-five subjects (Naval F-14 and E-2C crew members) were administered computer-based and paper-based tests of threat-parameter knowledge represented as a semantic network in order to determine the relative reliabilities and validities of these two assessment modes. Estimates of internal consistencies, equivalences, and discriminant validities…

Expert systems can be used to aid decision making. A computerized adaptive test (CAT) is one kind of expert system, although it is not commonly recognized as such. A new approach, termed EXSPRT, was devised that combines expert systems reasoning and sequential probability ratio test stopping rules. EXSPRT-R uses random selection of test items,…

Computer-assisted instruction has been integrated into an established library skills course at the State University of New York at Plattsburgh to supplement readings, classroom contact, and library assignments. Seven programs, one for each instructional unit of the course, were created in the form of self-tests that review course content, identify…

The Computerized Adaptive Screening Test (CAST) was developed to provide an estimate at recruiting stations of prospects' Armed Forces Qualification Test (AFQT) scores. The CAST was designed to replace the paper-and-pencil Enlistment Screening Test (EST). The initial validation study of CAST indicated that CAST predicts AFQT at least as accurately…

Conventional Armed Services Vocational Aptitude Battery-7 (ASVAB) Arithmetic Reasoning and Word Knowledge tests, were compared with computer-administered adaptive tests as predictors of performance in an Air Force Jet Engine Mechanic training course (n=495). Results supported earlier research in showing somewhat longer examinee response times for…

The plan described was developed to evaluate the training and cost-effectiveness of the Automated Instructional Management System (AIMS), a computer-based training and resource development system being developed by the Training and Doctrine Command (TRADOC) for possible installation in its schools and training centers. The Functional Description…

This discussion of an online, in-house computer system used in a group clinical psychology practice describes the development of a program designed to offer cost-effective testing services for patients of mental health professionals. The report provides detailed information on two psychological testing inventories rendered via computer. The first…

Criterion-referenced testing is an important area in the theory and practice of educational measurement. This study demonstrated that even these tests must be closely examined for construct validity. The dimensionality of a dataset will be affected by the examinee's cognitive processes as well as by the nature of the content domain. The methods of…

For performance tests to be truly standardized, they must be administered in a way that will minimize variation due to operator intervention and errors. Through such technological developments as low-cost digital computers and digital logic modules, automatic test administration without restriction of test content has become possible. A…

The effect of prior information in Bayesian estimation is considered, mainly from the standpoint of objective testing. In the estimation of a parameter belonging to an individual, the prior information is, in most cases, the density function of the population to which the individual belongs. Bayesian estimation was compared with maximum likelihood…

Two basic requirements for the successful initiation of a program for test assembly are the development of detailed item content classification systems and the delineation of the professional judgements made in building a test from a pool of items to detailed content, ability, and statistical specifications in terms precise enough to be translated…