This paper presents a multistage adaptive testing test development paradigm that promises to handle content balancing and other test development needs, psychometric reliability concerns, and item exposure. The bundled multistage adaptive testing (BMAT) framework is a modification of the computer-adaptive sequential testing framework introduced by…

The purpose of this project was to develop valid evaluation procedures for the selection of Container Equipment Operators (CEOs) in the shipping industry. A job analysis was conducted to identify the essential tasks of the CEO job. Site visits, a task inventory, and the determination of essential tasks were used in the job analysis. The skills and…

One challenge associated with computerized adaptive testing (CAT) is the maintenance of test and item security while allowing for daily testing. An alternative to continually creating new pools containing an independent set of items would be to consider each CAT pool as a sample of items from a larger collection (referred to as a VAT) rather than…

This paper shows how JavaScript can be used within HTML pages to add interactive review sessions and quizzes incorporating graphics and sound files. JavaScript has the advantage of providing basic interactive functions without the use of separate software applications and players. Because it can be part of a standard HTML page, it is…

To assess the feasibility of computer-assisted Federal Aviation Administration certification examinations, a system for administering the Private Pilot Certification Examination was implemented using PLATO. Characteristics, reactions, and guidelines for use of the test are included. (Author/JJD)

Compares two methods for computer generation of tests: question retrieval and question generation. Both techniques are described with specific applications for university teaching. Also evaluates the effects of these methods on student performance. Future developments of computer assisted test construction are also discussed. (CS)

Some perceived difficulties with conventional multiple choice tests are mentioned, and a modified form of examination is proposed. It uses a computer program to award partial marks for partially correct answers, full marks for correct answers, and check for widespread misunderstanding of an item or subject. (MSE)

Tailored testing by Cliff's method of implied orders was simulated through the use of responses gathered during conventional administration of the Stanford-Binet Intelligence Scale. Tailoring eliminated approximately half the responses with only modest decreases in score reliability. (Author/BW)

The effectiveness of various tailored testing strategies for use in objective based instructional programs was investigated. The three factors of a tailored testing strategy under study with various hypothetical distributions of abilities across two learning hierarchies were test length, mastery cutting score, and starting point. (Author/JKS)

When the network-flow algorithm (NFA) and the average growth approximation algorithm (AGAA) were used for automated test assembly with American College Test and Armed Services Vocational Aptitude Battery item banks, results indicate that reasonable error in item parameters is not harmful for test assembly using NFA or AGAA. (SLD)

The authors of the "Guidelines," a task force of eight, intend to present an organized list of features to be considered in reporting or evaluating computerized-adaptive assessments. Apart from a few weaknesses, the book is a useful and complete document that will be very helpful to test developers. (SLD)

Potential benefits of using item response theory in test construction are evaluated using the experience and evidence accumulated during nine years of using a three-parameter model in the development of major achievement batteries. Topics addressed include error of measurement, test equating, item bias, and item difficulty. (TJH)

TESTAT is a supplementary module for the popular SYSTAT statistical package for the personal computer. The program performs test analyses based on classical test theory and item response theory. Limitations and advantages are discussed. (SLD)

A method is presented and illustrated for simultaneously generating multiple tests with similar characteristics from the item bank by using binary programing techniques. The parallel tests are created to match an existing seed test item for item and to match user-supplied taxonomic specifications. (SLD)

Describes the design and implementation of a computer-based listening test--the "Text dictation." The article first discusses the importance of listening centering on a coherent text, rather than short listening fragments, and discusses drawbacks of listening programs wherein the required responses consist of noninteractive test types, such as…