Outlines a method for constructing minimum competency tests that are legitimate, answerable, and useful. At the heart of such tests is an item bank that is open to all to view. (Author/IRT)

Logical estimates of item difficulty made by judges were compared to empirical estimates derived from a test administration. Results indicated substantial correspondence between logical and empirical estimates, and substantial variation among judges. Further, the more elaborate the system used by judges to make estimates, the more accurate the…

Item level differences between a type of constructed response item (figural response) and comparable multiple choice items in the domain of architecture were studied. Data from 120 architects and architecture students show that item level differences in difficulty correspond to differences in cognitive processing requirements and that relations…

Four issues associated with calculator-available assessments are discussed: (1) benefits and problems of calculator use; (2) components of various types of calculator-available assessments; (3) construction of calculator-available assessments; and (4) the need for additional examination of items included on calculator-available assessments. (SLD)

One-parameter (1PPC) and two-parameter partial credit (2PPC) models were compared using real and simulated data with constructed response items present. Results suggest that the more flexible three-parameter logistic-2PPC model combination produces better model fit than the combination of the one-parameter logistic and the 1PPC models. (SLD)

In a theory/lecture course with limited use of case method, it is possible to get students to choose case study questions on examinations if topics are interesting, attention directing, and well understood. Case study test questions give students opportunities for critical analysis and self-expression. (SK)

Examined the analysis and interpretation of wording effects associated with positively and negatively worded survey items using data from a national sample of secondary school students (National Education Longitudinal Study 1988-1994). Results for 14,374 students support the interpretation of wording effects in terms of personality traits with…

Used empirical data from a certification test to study methods from statistical process control that have been proposed to classify an item score pattern as fitting or misfitting the underlying item response theory model in computerized adaptive testing. Results for 1,392 examinees show that different types of misfit can be distinguished. (SLD)

Validated a taxonomy of 31 multiple-choice item-writing guidelines through a logical process that included reviewing 27 textbooks on educational testing and the results of 27 studies and reviews published since 1990. Presents the taxonomy, which is intended for classroom assessment. (SLD)

The impact of varying levels of item omissions on Minnesota Multiphasic Personality Inventory-2 (MMPI-2) two-point code types was studied with MMPI-2 results from 100 psychological outpatients. Results suggest that defined code types are relatively robust for up to 30 omitted items. (SLD)

Comparison of two indices of answer copying, one using only wrong responses and the other using right and wrong responses for six tests taken by from 910 to 1,154 college students suggests that indices of copying may perform differentially well according to the size of scores of examinee pairs evaluated. (SLD)

A multidimensionality-based differential item functioning (DIF) analysis paradigm is presented that unifies substantive and statistical DIF analysis approaches by linking both to a theoretically sound and mathematically rigorous multidimensional DIF conceptualization. This approach results in the potential for DIF analysis more closely integrated…

Common strategies for dealing with flawed items in conventional testing, grounded in principles of fairness to examinees, are re-examined in the context of adaptive testing. The additional strategy of retesting from a pool cleansed of flawed items is found, through a Monte Carlo study, to bring about no practical improvement. (SLD)

Examined the influence of deviant scale items on item parameter estimates of focal scale items and person parameter estimates through a comparison of item response theory (IRT) and classical test theory (CTT) models. Used Monte Carlo methods to explore results from a pilot investigation of job attitude data. Discusses implications for researchers…

Studied the match between the Ontario (Canada) eighth grade curriculum for 1997 and the item pool of the Third International Mathematics and Science Study (TIMSS) and analyzed the matching process itself. Findings show that the 1997 curriculum is a better match to the TIMSS item pool, achieving the better match by enlarging the curriculum and…