To ensure the validity of the tests is to check that all items have similar results across different groups of individuals. However, differential item functioning (DIF) occurs when the results of individuals with equal ability levels from different groups differ from each other on the same test item. Based on Item Response Theory and Classic Test…

This article explores the amount of equating error at a passing score when equating scores from exams with small samples sizes. This article focuses on equating using classical test theory methods of Tucker linear, Levine linear, frequency estimation, and chained equipercentile equating. Both simulation and real data studies were used in the…

Purpose: Surveys that include skill measures may suffer from additional sources of error compared to those containing questionnaires alone. Examples are distractions such as noise or interruptions of testing sessions, as well as fatigue or lack of motivation to succeed. This paper aims to provide a review of statistical tools based on latent…

Methods for evaluating the consistency of responses to test items were compared. When a researcher is unwilling to make the assumptions of classical test theory, has only a small number of items, or is in a tailored testing context, Cliff's dominance indices may be useful. (Author/CTM)

Empirical Bayes point estimates of true score may be obtained if the distribution of observed score for a fixed examinee is approximated in one of several ways by a well-known compound binomial model. The Bayes estimates of true score may be expressed in terms of the observed score distribution and the distribution of a hypothetical binomial test.…

Several extended caution indices (ECIs) have been introduced earlier as a link between two distinctly different approaches: one based on standard statistics and the other, a model-based approach, utilizing item response theory (IRT). Expected values and variance of some ECIs are derived and their statistical properties are compared and discussed.…

Errors in self-reports of three academic performance measures are analyzed. Empirical errors are shown to depart radically from both no-error and random-error assumptions. Self-reports by females depart farther from the no-error and random-error models for all three performance measures. (Author/BW)

A content-oriented analysis of written solutions to test items in Israeli high school graduation examinations in mathematics yielded six error categories: misused data; misinterpreted language; logically invalid inference; distorted theorem or definition; unverified solution; and technical error. (Authors/MNS)

The progress of modern mental test theory depends very much on the techniques of maximum likelihood estimation, and many popular applications make use of likelihoods induced by logistic item response models. While, in reality, item responses are nonreplicate within a single examinee and the logistic models are only ideal, practitioners make…

A test score can be used for individual instructional diagnosis after determining whether: (1) difficulty of the test items was consistent with the complexity of the content measured; (2) items measuring the same underlying process were about equally difficult; and (3) partial credit scoring would increase the reliability of the diagnosis. (LMO)

This paper describes the development of a language arts test to assess the consistency of student response patterns and the feasibility of using the test to diagnose students' misconceptions. The studies were part of a project to develop computerized adaptive testing for the language arts with software to diagnose student errors. The…

A systematic and explicit approach to evaluation of pronunciation is proposed. Generalizability theory was applied in order to comprise all relevant factors in one psychomotor model. French and German pronunciation tests (in Appendix) were devised and evaluated. Common pronunciation problems for native Dutch speakers were incorporated. (Author/LMO)