Rater-mediated assessments require the evaluation of the accuracy and consistency of the inferences made by the raters to ensure the validity of score interpretations and uses. Modeling rater response processes allows for a better understanding of how raters map their representations of the examinee performance to their representation of the…

Test assembly is the process of selecting items from an item pool to form one or more new test forms. Often new test forms are constructed to be parallel with an existing (or an ideal) test. Within the context of item response theory, the test information function (TIF) or the test characteristic curve (TCC) are commonly used as statistical…

Cross-level invariance in a multilevel item response model can be investigated by testing whether the within-level item discriminations are equal to the between-level item discriminations. Testing the cross-level invariance assumption is important to understand constructs in multilevel data. However, in most multilevel item response model…

Although the Angoff procedure is among the most widely used standard setting procedures for tests comprising multiple-choice items, research has shown that subject matter experts have considerable difficulty accurately making the required judgments in the absence of examinee performance data. Some authors have viewed the need to provide…

Data from the Center for the Study of Evaluation's Secondary School Test Evaluations were analyzed to explore the present adequacy and propose a future direction of formal procedures for evaluating standardized tests. (Author/RC)

This article examines some of the values that might be considered in a selection situation within the context of a decision theoretic model also described here. Several alternate expressions of fair selection are suggested in the form of utility statements in which these values can be understood and compared. (Author/DEP)

The profiles of seven major publishers of elementary-level tests were prepared from systematic ratings of the qualities of their tests. Meaningful rating differences among the publishers' priorities were found and three types of publishers could be identified and described. (Authors)

Compares and evaluates models for bias in selection. Strategies are compared and evaluated as to their advantages and disadvantages in the areas of business and education. Some suggested formats for establishing culture fair selection are felt, by the authors, to be inadequate for their task and require a more complex analysis. (Author/DEP)

Discusses some models, including the Petersen Novick Model (TM 502 259) regarding fair selection procedures. (DEP)

A defense of the use of standards with criterion-referenced testing is made in response to Glass's article (TM 504 031). (JKS)

The rationale for use of instructional sensitivity in the empirical review of test items is examined, and the results of a study that distinguishes instructional sensitivity from other item concepts are presented. Research is reviewed which indicates the existence of instructional sensitivity as a unique criterion-referenced test item concept. (RL)

The use of setting standards for criterion-referenced tests is defended in a response to two papers by Gene Glass and Nancy Burton. (JKS)

An historical and philosophical perspective on the setting of standards for criterion-referenced testing is presented. The author suggests that performance standards are more symbolic than substantive. (JKS)

Criteria were developed to assess sexual and racial item content bias for every item from six IQ tests. Each reference was judged as either stereotyped or not sterotyped. This analysis pointed out an overwhelming sexual and racial imbalance in item content. (Author/RL)

The use of cut-off scores with criterion referenced tests is defended in this response to two papers by Gene Glass and Nancy Burton. Suggestions for setting cut-off scores are made. (JKS)