Using item response theory to investigate differential item functioning (DIF), students' expected course grades were examined and found to function similarly across sex and race. These grades were incorporated into the matching criterion, enhancing the validity of subgroup comparisons for the third-grade mathematics test taken by 1,050 students.…

The agreement of diagnostic classifications from two parallel subtests assessing a mathematics skill with three levels of scoring was studied with 431 Arab Israeli 10th graders. Results indicate that, even when parallel form reliability is high, less agreement is apparent when performance is evaluated at the micro level. (SLD)

Different methodologies for linking tests across languages are reviewed and evaluated, focusing on monolingual item response theory, bilingual group designs, and matched monolingual group designs. These methods, although not without weaknesses, are superior for promoting score comparability than methods that rely on translation or expert judgment…

Examined the longitudinal invariance of method effects associated with negatively worded items on a self-report measure of global self-esteem. Data from the National Educational Longitudinal Study for 3,950 junior high school and high school students show that the method effects associated with negatively worded items exhibit invariance across…

Assumptions of a servocontrol model of test item feedback were tested in a study of 94 junior and senior high school students receiving feedback or no feedback with 2 retention intervals. Results support the assumption that response certitude is related to the learner's ability to comprehend a given item. (SLD)

Examines the ways in which computers can assist teachers in developing good tests. Describes the program TESTWORKS in detail and provides charts comparing this program with 11 others in the areas of price, type of questions generated, computer functions, and the usefulness of each. Discusses the use of word processors and databases. (KO)

How computers are used to analyze item data is reviewed, and the information that existing item-analysis programs provide is described. Summaries of studies comparing the performance of some of these packages reveal some of their current limitations. Emphasis is on the usefulness to educational practice of these packages. (SLD)

A study of gender bias in the Dental Admission Test's mathematics test and its validity in predicting dental school success found no significant difference between male and female performance and no significant difference in the predictive validity of items favoring males or females. (Author/MSE)

Compares the effect of content ordering and scrambled ordering on examinations in courses, such as economics, that require quantitative skills. Empirical results suggest that students do no better if they are given a content-ordered rather than a scrambled examination as student performance is not adversely affected by scrambled ordered…

The effects of using item response theory (IRT) ability estimates based on customized tests formed by selecting areas from a nationally standardized achievement test were examined. For some populations, in some conditions, IRT ability estimates can be equivalent to scores based on full-length tests. (SLD)

Six procedures for combining sets of item response theory (IRT) item parameter estimates from different samples were evaluated using real and simulated response data. Results support use of covariance matrix-weighted averaging and a procedure using sample-size-weighted averaging of estimated item characteristic curves at the center of the ability…

Presents a study conducted to provide a comparative analysis of five item analysis indices using both IRT and non-IRT indices to describe the characteristics of flagged items and to investigate the appropriateness of logistic regression as an item analysis technique for further studies. The performance of five item analysis indices was examined.…

Three related Canadian studies assessed the content validity of 59 clinical problems designed as part of a test of medical decision-making skills. Focus was on the key features, i.e., the critical or essential steps in identification and management of the clinical problem. Results support content validity of the key features. (MSE)

The Rasch model was applied to selection of items for an Arabic version of the Otis-Lennon Mental Ability Test using a sample of 599 male and female Kuwaiti secondary school and university students. Results indicated that the test is suitable for the range of ability intended to be measured. (SLD)

The role of assessment in science education is explored, focusing on summative assessment in British public certificate examinations. Examples of test items are presented to illustrate difficulties in making valid and reliable assessments, and issues with implications for formative assessment are discussed. (SLD)