Explores how a set of possible student misconceptions about solving a complex problem can be used in computer-based intelligent tutoring systems and in computer-based exercise and test generation. Topics discussed include expert systems, misconception covers, discrimination trees, methods of acquiring the set of misconceptions, and protocol…

A prototype expert system for the diagnosis of elementary students experiencing educational problems is described. After input of initial data, the system provides guidance on what further information might be sought and/or what remedial activities might be beneficial. The system includes databases of tests and remedial materials and strategies.…

A method is presented for incorporating a large number of constraints on adaptive item selection in the construction of computerized adaptive tests. The method, which emulates practices of expert test specialists, is illustrated for verbal and quantitative measures. Its foundation is application of a weighted deviations model and algorithm. (SLD)

Discusses the use of computerized adaptive testing (CAT) in the classroom. Highlights include item response theory; sequential probability ratio test (SPRT); combining SPRT with expert system reasoning, resulting in EXSPRT; and a study of college students that examined the efficiency and accuracy of the various CAT methods discussed. (Contains 16…

Four human judges agreed highly among themselves about the presence of errors committed by 60 adults solving algebra word problems, but were in less agreement about categorizing faults. An expert system agreed with judges about correctness of answers, but was in even less agreement about categorizing the faults. (SLD)

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,…

The article examines decision-making expert systems and discusses their implications for diagnosis and prescription of reading difficulties. A detailed description of how a reading diagnostic expert system might operate to aid classroom teachers is followed by a discussion of advantages and limitations of expert systems for educational use.…

The relationship of an expert-system-scored constrained free-response item type to multiple-choice and free-response items was studied using data for 614 students on the College Board's Advanced Placement Computer Science (APCS) Examination. Implications for testing and the APCS test are discussed. (SLD)

Discussion of expert systems and computerized adaptive tests describes two versions of EXSPRT, a new approach that combines uncertain inference in expert systems with sequential probability ratio test (SPRT) stopping rules. Results of two studies comparing EXSPRT to adaptive mastery testing based on item response theory and SPRT approaches are…

This paper reports the results of using a three-layer backpropagation artificial neural network to predict item difficulty in a reading comprehension test. Two network structures were developed, one with and one without a sigmoid function in the output processing unit. The data set, which consisted of a table of coded test items and corresponding…

Describes "Diagnosys," a knowledge-based computer diagnostic test of basic mathematical skills developed in the United Kingdom for university students. Highlights include the need for diagnostic testing; the advantages of a computer-based test; question design; and possible future developments. (Author/LRW)

The computer can be incorporated into educational assessment at two levels: clerical work such as scoring, converting scores, administering test items, and organizing data into manageable profiles; and expanding horizons and deepening the understanding of what is important to measure and how best to measure it through expert systems and new…

Expert systems can be used to aid decisionmaking. A computerized adaptive test is one kind of expert system, although not commonly recognized as such. A new approach, termed EXSPRT, was devised that combines expert systems reasoning and sequential probability ratio test stopping rules. Two versions of EXSPRT were developed, one with random…

This paper discusses systemic problems with testing and outlines two scenarios for reformulating testing based on intelligent tutoring systems. Five desiderata are provided to underpin the type of testing proposed: (1) tests should emphasize learning and thinking; (2) tests should require generation as well as selection; (3) tests should be…

Discusses the evolution of current decision support systems (DSS) computer software and their potential for use in assessing cognitive ability. Current applications of computer software for structured and unstructured problem solving are examined together with the feasibility of computerized adaptive testing. Characteristics of computer-based…