Since researchers acknowledged the several advantages of computerized adaptive testing (CAT) over traditional linear test administration, the issue of item exposure control has received increased attention. Due to CAT's underlying philosophy, particular items in the item pool may be presented too often and become overexposed, while other items are…

The standard error of the maximum likelihood ability estimator is commonly estimated by evaluating the test information function at an examinee's current maximum likelihood estimate (a point estimate) of ability. Because the test information function evaluated at the point estimate may differ from the test information function evaluated at an…

In this paper, we present two new methods for evaluating students' answerscripts based on the similarity measure between vague sets. The vague marks awarded to the answers in the students' answerscripts are represented by vague sets, where each element u[subscript i] in the universe of discourse U belonging to a vague set is represented by a…

Person-fit research in the context of paper-and-pencil tests is reviewed, and some specific problems regarding person fit in the context of computerized adaptive testing (CAT) are discussed. Some new methods are proposed to investigate person fit in a CAT environment. These statistics are based on Statistical Process Control (SPC) theory. A…

The Scan-Tron Forms Analysis Package (SFAP) is a collection of integrated programs that allow an IBM-PC (or compatible) to collect data from a Scan-Tron 1200 forms reader. In addition to the basic data acquisition capability, the SFAP has additional capabilities related to the viewing and formatting of incoming data. When used in combination with…

A computerized version of the Minnesota Multiphasic Personality Inventory was developed that incorporated both administration and scoring. This method was compared with the original manual form. The results indicated that the test-retest reliability was high regardless of the method of administration and that similar results were obtained on the…

Online assessment of any type is attractive to educators because it allows large amounts of student data to be gathered and accessed quickly. Indeed, online, summative assessments--generally end-of-course, state-level, and placement exams--are making the annual student testing ritual a meaningful audit instead of what some call an…

An a-stratified design (H. Chang and Z. Ying, 1997) is a new concept proposed to address the issues of item security and pool utilization in testing. It has been demonstrated to be effective in lowering the test overlap rate and improving the use of the entire pool when content constraints are not main concerns. However, it cannot really solve the…

Computerized testing has created new challenges for the production and administration of test forms. This paper describes a multi-stage, testlet-based framework for test design, assembly, and administration called computer-adaptive sequential testing (CAST). CAST is a structured testing approach that is amenable to both adaptive and mastery…

Developed a method based on 0-1 linear programming to stratify an item pool optimally for use in alpha-stratified adaptive testing. Applied the method to a previous item pool from the computerized adaptive test of the Graduate Record Examinations. Results show the new method performs well in practical situations. (SLD)

Concerns about Internet-based career assessments include the following: users' technical skill level, lack of screening, psychological factors, cultural bias, unprotected results, technical failures, lack of standardization, digital divide, interpretation problems, outdated tests, copyright violations, administrator qualifications, and hidden…

The use of computer-based test interpretation (CBTI) in career assessment raises numerous ethical and professional issues: How do current standards apply to Internet tests? What are appropriate and inappropriate uses of CBTI? How can it be used in career counseling? Who is qualified to use CBTI? and What are the potential benefits and problems?…

Several classical approaches and alternative approaches to item selection for computerized adaptive testing (CAT) are reviewed and compared. The study also describes procedures for constrained CAT that may be added to classical item selection approaches to allow them to be used for applied testing. (TJH)

Discusses computerized testing and certification and proposes three levels of certification testing, each one corresponding to a different notion of competent performance, from basic knowledge to expert performance. Declarative and procedural knowledge are defined; performance-based tests are discussed; and testing for problem-solving ability is…

Discusses problems of diagnosing and repairing infeasible linear-programming models in computerized test assembly. Demonstrates that it is possible to localize the causes of infeasibility, although this is not always easy. (SLD)