In the answer-until-correct mode of multiple-choice testing, respondents are directed to continue choosing among the alternatives to each item until they find the correct response. There is no consensus as to how to convert the resulting pattern of responses into a measure because of two conflicting models of item response behavior. The first…

The computer can assist test construction in the following four ways: (1) storage or banking of test items; (2) banking of item attributes; (3) test construction; and (4) test printing. Automated Item Banking (AIB) is a computerized item storage and test construction system which illustrates these capabilities. It was developed, implemented, and…

By means of computer simulation of test responses, the reliability of item analysis data and the accuracy of equating were examined for hypothetical samples of 250, 500, 1000, and 2000 subjects for two tests with 20 equating items plus 60 additional items on the same scale. Birnbaum's three-parameter logistic model was used for the simulation. The…

Discusses features of a microcomputer program, SCOREIT, used at New Orleans' Loyola University and several high schools to score and analyze test results. Benefits and dimensions of the program's automated test and item analysis are outlined, and several examples illustrating test and item analyses by SCOREIT are presented. (MBR)

A small-scale study was conducted to compare test-taking strategies, problem-solving strategies, and general impressions about the test across computer and paper-and-pencil administration modes. Thirty-six examinees (high school students) participated in the study. Each examinee took a test in one of the content areas of English, Mathematics,…

Three different applications of the testlet concept are presented, and the psychometric models most suitable for each application are described. Difficulties that testlets can help overcome include (1) context effects; (2) item ordering; and (3) content balancing. Implications for test construction are discussed. (SLD)

Discussion of the use of human markers to mark responses on write-in questions focuses on a study that determined the feasibility of using a computer program to mark write-in responses for the Medical Council of Canada Qualifying Examination. The computer performance was compared with that of physician markers. (seven references) (LRW)

A computerized adaptive test (CAT) based on the nominal response model (NR CAT) was implemented, and the performance of the NR CAT and a CAT based on the three-parameter logistic model was compared. The NR CAT produced trait estimates comparable to those of the three-parameter test. (SLD)

Replenishing item pools for on-line ability testing requires innovative and efficient data collection. A method is proposed to collect test item calibration data in an on-line testing environment sequentially using locally D-optimum designs, thereby achieving high Fisher information for the item parameters. (SLD)

This paper describes the use of the Rasch model to help implement computerized administration of the standard and advanced forms of Raven's Progressive Matrices (RPM), to compare relative item difficulties, and to convert scores between the standard and advanced forms. The sample consisted of 95 girls and 95 boys in Australia. (SLD)

Examines the strategies used in answering a computerized multiple-choice test where all questions on a semantic topic were grouped together or randomly distributed. Findings indicate that students grouped by performance on the test used different strategies in completing the test due to distinct cognitive processes between the groups. (AEF)

The IRT (Item Response Theory) has been studied and applied in computer-based test for decades. However, almost of all these existing studies evaluated focus merely on test questions with text-based (or static text/graphic) type of presentation form illustrated exclusively. In this paper, we present our study on test questions using both…

The purpose of the study was to determine comparability of an online version to the original paper-pencil version of Defining Issues Test 2 (DIT2). This study employed methods from both Classical Test Theory (CTT) and Item Response Theory (IRT). Findings from CTT analyses supported the reliability and discriminant validity of both versions.…

Test-item writing efforts typically results in item pools with an undesirable correlational structure between the content attributes of the items and their statistical information. If such pools are used in computerized adaptive testing (CAT), the algorithm may be forced to select items with less than optimal information, that violate the content…

This study investigated factors related to score differences on computerized and paper-and-pencil versions of a series of primary K-3 reading tests. Factors studied included item and student characteristics. The results suggest that the score differences were more related to student than item characteristics. These student characteristics include…