A common belief is that the Bookmark method is a cognitively simpler standard-setting method than the modified Angoff method. However, a limited amount of research has investigated panelist's ability to perform well the Bookmark method, and whether some of the challenges panelists face with the Angoff method may also be present in the Bookmark…

Various subscore estimation methods that use auxiliary information to improve subscore accuracy and stability have been developed. This report provides a review of various subscore estimation methods described in the literature. The methodology of each method is described, then research studies on these subscore estimation methods are summarized.…

Developing and writing assessment items that measure teachers' knowledge is an intricate and complex undertaking. In this paper, we begin with an overview of what is known about measuring teacher knowledge. We then highlight the challenges inherent in creating assessment items that focus specifically on measuring teachers' specialised knowledge…

To some extent, good testing procedure, like good language use, can be achieved through avoidance of errors. Almost any language-instruction program requires the preparation and administration of tests, and it is only to the extent that certain common testing mistakes have been avoided that such tests can be said to be worthwhile selection,…

Most implementations of the Mantel-Haenszel differential item functioning procedure delete records with missing responses or replace missing responses with scores of 0. These treatments of missing data make strong assumptions about the causes of the missing data. Such assumptions may be particularly problematic when groups differ in their patterns…

Traditional methods for examining differential item functioning (DIF) in polytomously scored test items yield a single item-level index of DIF and thus provide no information concerning which score levels are implicated in the DIF effect. To address this limitation of DIF methodology, the framework of differential step functioning (DSF) has…

In the attempt to identify or prevent unfair tests, both quantitative analyses and logical evaluation are often used. For the most part, fairness evaluation is a pragmatic attempt at determining whether procedural or substantive due process has been accorded to either a group of test takers or an individual. In both the individual and comparative…

This article describes the results of a simulation study to investigate the impact of missing data on the detection of differential item functioning (DIF). Specifically, it investigates how four methods for dealing with missing data (listwise deletion, zero imputation, two-way imputation, response function imputation) interact with two methods of…

In this article, we introduce a person-fit statistic called the hierarchy consistency index (HCI) to help detect misfitting item response vectors for tests developed and analyzed based on a cognitive model. The HCI ranges from -1.0 to 1.0, with values close to -1.0 indicating that students respond unexpectedly or differently from the responses…

A potential undesirable effect of multistage testing is differential speededness, which happens if some of the test takers run out of time because they receive subtests with items that are more time intensive than others. This article shows how a probabilistic response-time model can be used for estimating differences in time intensities and speed…

The literature on item bias, i.e., the question of whether some items in tests favor one cultural group over another cultural group due to irrelevant factors, is reviewed and evaluated. All known references through 1981 are described including a large number of unpublished reports. Each method is described and the criticisms that have appeared in…

The tendency of some respondents to omit items more often when they feel they have a less positive evaluation to make and less frequently when the evaluation is more positive is discussed. Five examples illustrate this form of nonresponse bias. Recommendations to overcome nonresponse bias are offered. (SLD)

Computer-based assessments are becoming more commonplace, perhaps as a necessity for faculty to cope with large class sizes. These tests often occur in large computer testing venues in which test security may be compromised. In an attempt to limit the likelihood of cheating in such venues, randomised presentation of items is automatically…

Multiple matrix sampling of items and examinees was applied to an 18-item rank order instrument administered to a randomly assigned group and compared to the ordering and ranking of all items by control subjects. High correlations between ranks suggest the methodology may viably reduce respondent effort on long rank ordering tasks. (Author/CM)

Several methods of assessing test item bias are described, and the concept of fair use of tests is examined. A test item is biased if individuals of equal ability have different probabilities of attaining the item correct. The following seven general procedures used to examine test items for bias are summarized and discussed: (1) analysis of…