In recent years, educators, administrators, policymakers, and measurement experts have called for assessments that support educators in making better instructional decisions. One promising approach to measurement to support instructional decision-making is diagnostic classification models (DCMs). DCMs are flexible psychometric models that…

Categorical growth models describe examinee growth in terms of performance-level category transitions, which implies that some percentage of examinees will be misclassified. This paper introduces a new procedure for estimating the classification accuracy of categorical growth models, based on Rudner's classification accuracy index for item…

As the primary interface between test developers and multiple educational stakeholders, score reports are a critical component to the success (or failure) of any assessment program. The purpose of this review is to document recent research on individual-level score reporting to advance the research and practice of score reporting. We conducted a…

Drawing upon his experience, more than 60 years ago, as a psychometric support person to a very special teacher of brain damaged children, the author of this article reflects on the productive use of educational assessments and data from them to educate - assessment in the service of learning. Findings from the Gordon Commission on the Future of…

Student learning outcomes assessment has been increasingly used in U.S. higher education institutions over the last 10 years, partly fueled by the recommendation from the Spellings Commission that institutions need to demonstrate more direct evidence of student learning. To respond to the Commission's call, various accountability initiatives have…

The purpose of this ITEMS module is to provide an introduction to differential item functioning (DIF) analysis using mixture item response models. The mixture item response models for DIF analysis involve comparing item profiles across latent groups, instead of manifest groups. First, an overview of DIF analysis based on latent groups, called…

We examined summary indices of high school performance (coursework, grades, and test scores) based on the graded response model (GRM). The indices varied by inclusion of ACT test scores and whether high school courses were constrained to have the same difficulty and discrimination across groups of schools. The indices were examined with respect to…

Standard 3.9 of the Standards for Educational and Psychological Testing ([, 1999]) demands evidence of model fit when item response theory (IRT) models are employed to data from tests. Hambleton and Han ([Hambleton, R. K., 2005]) and Sinharay ([Sinharay, S., 2005]) recommended the assessment of practical significance of misfit of IRT models, but…

In recent years, many U.S. states have introduced growth models as part of their educational accountability systems. Although the validity of growth-based accountability models has been evaluated for the general population, the impact of those models for English language learner (ELL) students, a growing segment of the student population, has not…

This article describes an alignment study conducted to evaluate the alignment between Indiana's Kindergarten content standards and items on the Indiana Standards Tool for Alternate Reporting. Alignment is the extent to which standards and assessments are in agreement, working together to guide educators' efforts to support children's learning and…

The idea of test consistency is illustrated, with reference to two sets of test scores. A mathematical model is used to explain the relative consistency and relative inconsistency of measurements, and a means of indexing reliability is derived using the model. Practical aspects of estimating reliability are considered. (TJH)

Explores how a program of strong construct validation could be applied to the assessment of the construct of test anxiety, paying special attention to substantive, structural, and external aspects of construct validation. A framework is proposed to pull together various statistical methods used in construct validation research into an organized…

The need for an independent mechanism that regulates, or audits, the testing enterprise is discussed along with a critique of current mechanisms for challenging a high-stakes test or its use and the need for independent auditing of the commercial test industry. Models for an auditing mechanism are reviewed. (SLD)

In this paper I describe and illustrate the Roussos-Stout (1996) multidimensionality-based DIF analysis paradigm, with emphasis on its implication for the selection of a matching and studied subtest for DIF analyses. Standard DIF practice encourages an exploratory search for matching subtest items based on purely statistical criteria, such as a…

If curriculum is to be the basis for assessment reform, assessment specialists must model the process for producing valid assessment products. Validity criteria should guide any model for the assessment development process. However, curriculum-based assessment systems should not be confused with standards-driven assessment systems. (SLD)