This guide is organized into five chapters; (1) an approach to testing--decisions made from test results, types of achievement tests, types and levels of objectives, and test validity, reliability, and practicality; (2) classroom test construction--planning, item banks, item writing, assembly, administration, and scoring; (3) test analysis-item…

This study examined the effect of two ways of question phrasing as related to three styles of expository writing on the test performance of elementary school children. Multiple-choice questions were developed for sets of passages which were written using three different syntactic structures; and which had different levels of difficulty. The…

CAFETERIA-type rating systems, modeled after the one developed at Purdue University, allow the instructors being evaluated to select those items which their students will use in evaluating the instructors. Such computer-assisted systems allow the instructor to tailor the evaluation to the particular instructional strategies used. This study…

This report examines how selection fairness is influenced by the characteristics of a selection instrument in terms of its distribution of item difficulties, level of item discrimination, degree of item bias, and testing strategy. Computer simulation was used in the administration of either a conventional or Bayesian adaptive ability test to a…

Some stochastic approximation procedures are considered in relation to the problem of choosing a sequence of test questions to accurately estimate a given examinee's standing on a psychological dimension. Illustrations are given evaluating certain procedures in a specific context. (Author/CK)

Two types of computer-administered unit quizzes in a systematic pathology course for second-year medical students were compared. Quizzes composed of questions selected on the basis of a student's ability had higher correlations with the final examination than did quizzes composed of questions randomly selected from topic areas. (Author/JAZ)

Describes a model for adapting the construction of teacher-made mathematics tests for mildly handicapped students including the educable mentally retarded, the emotionally handicapped, and the learning disabled, to the mainstreamed classroom. (PK)

The proportionality model assumes that total testing time is proportional to the number of test items and the number of options per multiple choice test item. This assumption was examined, using test items having from two to five options. The model was not supported. (Author/GDC)

The multifaceted structure of sentence-completion test items was analyzed to explain verbal comprehension. The three stimulus constituents were technical, logical-semantic, and associative-contextual. Guttman's facet and order theories and smallest space analysis were used. Results confirmed the multiple skills involved in solving these tasks.…

Universal design is an approach to educational assessment based on principles of accessibility for a wide variety of end users. Elements of universal design include inclusive test population; precisely defined constructs; accessible, non-biased items; tests that are amenable to accommodations; simple, clear and intuitive procedures; maximum…

Item parameter estimates vary for a variety of reasons, including estimation error, characteristics of the examinee samples, and context effects (e.g., item location effects, section location effects, etc.). Although we expect variation based on theory, there is reason to believe that observed variation in item parameter estimates exceeds what…

This study was designed to answer two key questions about the fixed portions of the fourth, eighth, and tenth grade spring 2003 Idaho Standards Achievement Tests (ISAT) in Reading, Language Usage and Mathematics: (1) To what extent do test items exhibit substantive differences in functioning across student groups formed based on ethnicity and…

The availability of item response times made possible by computerized testing represents an entirely new type of information about test items. This study explores the issue of how to represent response-time information in item banks. Empirical response-time distribution functions can be fit with statistical distribution functions with known…

Year-to-year rater variation may result in constructed response (CR) parameter changes, making CR items inappropriate to use in anchor sets for linking or equating. This study demonstrates how rater severity affected the writing and reading scores. Rater adjustments were made to statewide results using an item response theory (IRT) methodology…

As an integral part of the Schools and Staffing Survey (SASS) conducted by the National Center for Education Statistics (NCES) the School Administrator Questionnaire has been used to collect information from public and private school administrators regarding their demographic characteristics, academic background, professional training, and…