The interrelationships among halo and leniency rating errors were examined using simulated rating data. As leniency increased, halo decreased when measured by dimension intercorrelations but increased when measured by standard deviations across dimensions. Implications of these results for the use of the various measures are discussed. (SLD)

In conjunction with testing mandates, some states have developed new measures intended to reflect changes in thinking about reading. Discusses, in dialogue form, whether these new measures support educational improvement or limit them. (BJV)

A taxonomy of 43 rules for writing multiple-choice test items is presented, based on a consensus of 46 textbooks. These guidelines are presented as complete and authoritative, with solid consensus apparent for 33 of the rules. Four rules lack consensus, and 5 rules were cited fewer than 10 times. (SLD)

An asymptotic expression for the reliability of a linearly equated test is developed using normal theory. Reliability is expressed as the product of test reliability before equating and an adjustment term that is a function of the sample sizes used to estimate the linear equating transformation. The approach is illustrated. (SLD)

Relationships between Bayesian ability estimates and the parameters of a normal population distribution are derived in the context of classical test theory. Formulas are presented for practical work with Bayesian ability estimates, and a numerical illustration is provided. (SLD)

Reviews recent trends in performance testing, focusing on different definitions of performance testing; the extent to which performance tests have drawn upon the theoretical discussions of competence and performance; research on performance tests; and future developmental and research questions. (66 references) (MDM)

TESTAT is a supplementary module for the popular SYSTAT statistical package for the personal computer. The program performs test analyses based on classical test theory and item response theory. Limitations and advantages are discussed. (SLD)

Polynomial algorithms are presented that are used to solve selected problems in test theory, and computational results from sample problems with several hundred decision variables are provided that demonstrate the benefits of these algorithms. The algorithms are based on optimization theory in networks (graphs). (SLD)

Statistical analysis tools in language testing are described, chiefly classical test theory and item response theory. Computer software for statistical analysis is briefly reviewed and divided into three tiers: commonly available; statistical packages; and specialty software. (Author/VWL)

Reviews what is happening in examination systems that have begun to allow the use of Computer Algebra Systems (CAS) in externally set 'high stakes' assessment regimes. Discusses possible options for the future with the intention of developing a dialogue on how assessment with a CAS can help develop the mathematical literacy of students. (Author/MM)

The purpose of this study was to document the instrument development of maze measures for grades 3-8. Each maze passage contained twelve omitted words that students filled in by choosing the best-fit word from among the provided options. In this technical report, we describe the process of creating, reviewing, and pilot testing the maze measures.…

The purpose of this paper is to clarify the seemingly discrepant views of test theorists and test developers about terminology related to the evaluation of test content. The origin and evolution of the concept of content validity are traced, and the concept is reformulated in a way that emphasizes the notion that content domain definition,…

An effective test and measurement course in psychology should expose students to a variety of available psychological tests, as well as to the mechanics of test construction and evaluation. In a test and measurement course at the State University of New York's College at Cortland, the course is divided into two components with an overlaying group…

The Mantel-Haenszel (MH) procedure attempts to identify and quantify differential item performance (item bias). This paper summarizes the MH statistics, and identifies the parameters they estimate. An equivalent procedure based on the Rasch model is described. The theoretical properties of the two approaches are compared and shown to require the…

This report describes a methodology for using verbal reports of thinking to develop and validate multiple-choice tests of critical thinking. These verbal reports of individuals' thinking on draft items of multiple-choice critical thinking tests can be used systematically to provide evidence of the thinking processes elicited by such tests, and in…