Item response theory (IRT) methods are generally used to create score scales for large-scale tests. Research has shown that IRT scales are stable across groups and over time. Most studies have focused on items that are dichotomously scored. Now Rasch and other IRT models are used to create scales for tests that include polytomously scored items.…

Although testing accommodations are commonly provided to students with disabilities within large-scale testing programs, research findings on how well accommodations allow for comparable measurement of student knowledge and skill remain inconclusive. The purpose of this study was to examine the extent to which 1 commonly held belief about testing…

Item Response Theory and Mantel-Haenszel approaches for investigating differential item performance were compared to assess the level of agreement of the approaches in identifying potentially biased items. Subjects were 2,000 White and 2,000 Native American high school students. The Mantel-Haenszel method provides an acceptable approximation of…

Studied methods for structuring a performance domain for a certification test in emergency nursing based on task frequency ratings from 659 emergency nurses or task similarity ratings from 21 experts. A 125-job analysis survey was used. Similarity judgment results are more easily interpreted and adequately modeled by multivariate analysis. (SLD)

The use of the "none-of-the-above" option (NOTA) in 20 college-level multiple-choice tests was evaluated for classes with 100 or more students. Eight academic disciplines were represented, and 295 NOTA and 724 regular test items were used. It appears that the NOTA can be compatible with good classroom measurement. (TJH)

A model-testing approach for evaluating the stability of item response theory item parameter estimates (IPEs) in a pretest-posttest design is illustrated. Nineteen items from the Head Start Measures Battery were used. A moderately high degree of stability in the IPEs for 5,510 children assessed on 2 occasions was found. (TJH)

Several multiple-choice item formats are examined in the current climate of test reform. The reform movement is discussed as it affects use of the following formats: (1) complex multiple-choice; (2) alternate choice; (3) true-false; (4) multiple true-false; and (5) the context dependent item set. (SLD)

Measures of linguistic competence for limited-English-proficient students are discussed. The results for 134 students in grades 3 through 6 from a study of the reliability and validity of the Sentence Verification Technique tests as measures of listening and reading comprehension performance in native languages and English are reported. (TJH)

The influence of test wiseness on the performance of 736 high school seniors in British Columbia on provincial school leaving examinations in English, algebra, geography, history, biology, and chemistry was studied. The performance of many students on the multiple-choice sections was spuriously enhanced by test wiseness. (TJH)

Eighth grade teachers in three local school districts helped customize two standardized norm-referenced tests for ninth graders to investigate effects of deleting some items and adding locally constructed items. Results indicate that percentile ranks for the customized tests could be very different from those for the complete test. (SLD)

The usefulness of latent class modeling in addressing several measurement issues is demonstrated via a study of 74 good and 74 poor readers in grades 5 and 6. Procedures were particularly useful for assessing the hierarchical relation among skills and for exploring issues related to item domains. (SLD)