A method for medical screening is adapted to differential item functioning (DIF). Its essential elements are explicit declarations of the level of DIF that is acceptable and of the loss function that quantifies the consequences of the two kinds of inappropriate classification of an item. Instead of a single level and a single function, sets of…

Most experts in the testing community have presumed that the $350 million promised by the U.S. Department of Education to support common assessments would promote those that made greater use of open-ended items capable of measuring higher-order critical-thinking skills. But as measurement experts consider the multitude of possibilities for an…

While measurement precision is relatively easy to establish for single tests and assessments, it is much more difficult to determine for decision making with multiple tests on different subjects. This latter is the situation in the system of final examinations for secondary education in the Netherlands and is used as an example in this paper. This…

Item-discrimination indices are numbers calculated from test data that are used in assessing the effectiveness of individual test questions. This article asserts that the indices are so unreliable as to suggest that countless good questions may have been discarded over the years. It considers how the indices, and hence overall test reliability,…

The wording and structure of questionnaire items can interact with specified sample categories based on evaluation goals and respondent characteristics. The effects of the interactions can restructure samples and introduce bias into the data analysis. These effects, and suggestions for avoiding them, are demonstrated for five types of…

Multiple choice tests are widely viewed as the most effective and objective means of assessment. Item development is the central component of creating an effective test, but test developers often do not have the background in item development. This document describes recall, application, and analysis, the three cognitive levels of test items. It…

Describes Florida's efforts at instituting statewide item banking and testing program in vocational education. Discusses rationale for statewide testing program and item banking procedure as well as development and coding of items, dissemination of item bank to school districts, and development of statewide test. Outlines problems encountered,…

Describes measurement problems associated with computer based testing (CBT) programs when they are part of a computer assisted instruction curriculum. Topics discussed include CBT standards; selection of item types; the contamination of items that arise from test design strategies; and the non-equivalence of comparison groups in item analyses. (8…

A norm-referenced achievement test, in combination with supplementary items, can be used to produce norm-referenced data as well as objective-referenced data. The experiences of the Palm Beach County (Florida) school district in developing and using such a test are described. (EGS)

A one-parameter latent trait model was the basis of the test development procedures in the Basic Skills Assessment Program (BSAP) of the Department of Defense Dependents Schools (DoDDS). Several issues are involved in applying the Rasch model to an assessment program in a large school district. Separate sets of skills continua are arranged by…

Four problems faced by the staff of the California Assessment Program (CAP) were solved by applying Rasch scaling techniques: (1) item cultural bias in the Entry Level Test (ELT) given to all first grade pupils; (2) nonlinear regression analysis of the third grade Reading Test scores; (3) comparison of school growth from grades two to three, using…