Investigated Type I error rates of the likelihood-ratio test for the detection of differential item functioning (DIF) using Monte Carlo simulations under the graded-response model. Type I error rates were within theoretically expected values for all six combinations of sample sizes and ability-matching conditions at each of the nominal alpha…

Studied item exposure in a computerized adaptive test when the item selection algorithm presents examinees with questions they were asked in a previous test administration. Results with 178 repeat examinees on a medical technologists' test indicate that the combined use of an adaptive algorithm to select items and latent trait theory to estimate…

Whether a middle alternative in the response choices to a questionnaire influences the reliability and validity of survey responses was studied with 1,390 physicians, nurses, and midwives. Including a neutral option had little effect on overall reliability and validity, but allowed better coherence when items were considered globally. (SLD)

Describes three open-ended response types that could broaden the conception of mathematical problem solving used in computerized admissions tests: (1) mathematical expression (ME); (2) generating examples (GE); and (3) and graphical modeling (GM). Illustrates how combining ME, GE, and GM can form extended constructed response problems. (SLD)

Administered untimed Raven's Standard Progressive Matrices (SPM) to 173 African and 136 White college students in South Africa. In comparison with the 1993 U.S. normative sample, African students scored at the 14th percentile, and White students at the 61st percentile. Differences were greater on SPM items with the highest item total correlations,…

Statistical and theoretical issues that arise from assessing person-fit on measures of typical performance are discussed, including the frequent attenuation of detection of person-misfit, the need for methods of identifying sources of response aberrancy, and person-fit measures as moderators of trait-criterion relations. (SLD)

Investigates differential item functioning (DIF) across two different broad language groupings, Asian and European, in a speaking test in which the test takers' responses were rated polytomously. Data were collected from 1038 nonnative speakers of English from France, Hong Kong, Japan, Spain, Switzerland, and Thailand who took the SPEAK test in…

Between administrations of a test, 36 nursing students were given a practice test and answer key that provided feedback; 30 were not. Those who performed poorly on the test were more overconfident about answers to hard questions. This judgment bias can be reduced by providing feedback about their performance and confidence. (Contains 54…

Reports on the potential problems in scoring responses to sequencing tests, the development of a computer program to overcome these difficulties, and an exploration of the value of scoring procedures. (Author/VWL)

Discusses an approach to analyzing performance assessments that identifies potential reasons for misfitting items and uses this information to improve on items and rubrics for these assessments. Illustrates the approach through a 53-item mathematics performance assessment completed by approximately 500 middle school students. (SLD)

Compares Angoff and Nedelsky methods for setting passing scores on tests. Using one of the methods, 84 college students were taught to estimate their probable scores on a vocabulary test. Estimates were compared to their later actual scores. The Nedelsky method was considerably less accurate under certain conditions, and both methods…

Proposes an item-selection algorithm for neutralizing the differential effects of time limits on computerized adaptive test scores. Uses a statistical model for distributions of examinees' response times on items in a bank that is updated each time an item is administered. Demonstrates the method using an item bank from the Armed Services…

Investigated three models that permit restricted examinee control over revising previous answers in the context of adaptive testing, using simulation. Two models permitting item revisions worked well in preserving test fairness and accuracy, and one model may preserve some cognitive processing styles developed by examinees for a linear testing…

Examined whether patterns of gender differential item functioning (DIF) in parcels of items are influenced by changes in item position. Findings for more than 2,000 college freshmen taking a test of mathematics suggest that the amounts of gender DIF and DIF present in item parcels tend not to be influenced by changes in item position. (SLD)

A well-constructed test sheet not only helps the instructor evaluate the learning status of the students, but also facilitates the diagnosis of the problems embedded in the students' learning process. This paper addresses the problem of selecting proper test items to compose a test sheet that conforms to such assessment requirements as average…