This study evaluates various scoring methods including number-correct scoring, IRT theta scoring, and hybrid scoring in terms of scale-score stability over time. A simulation study was conducted to examine the relative performance of five scoring methods in terms of preserving the first two moments of scale scores for a population in a chain of…

One of the primary goals of international large-scale assessments in education is the comparison of country means in student achievement. This article introduces a framework for discussing differential item functioning (DIF) for such mean comparisons. We compare three different linking methods: concurrent scaling based on full invariance,…

Increasing use of item pools in large-scale educational assessments calls for an appropriate scaling procedure to achieve a common metric among field-tested items. The present study examines scaling procedures for developing a new item pool under a spiraled block linking design. The three scaling procedures are considered: (a) concurrent…

Previous investigations of the ability of content experts and test developers to estimate item difficulty have, for themost part, produced disappointing results. These investigations were based on a noncomparative method of independently rating the difficulty of items. In this article, we argue that, by eliciting comparative judgments of…

Common test items play an important role in equating alternate test forms under the common item nonequivalent groups design. When the item response theory (IRT) method is applied in equating, inconsistent item parameter estimates among common items can lead to large bias in equated scores. It is prudent to evaluate inconsistency in parameter…

The article compares three different methods to estimate effects of task characteristics and to use these estimates for model-based proficiency scaling: prediction of item difficulties from the Rasch model, the linear logistic test model (LLTM), and an LLTM including random item effects (LLTM+e). The methods are applied to empirical data from a…

The majority of large-scale assessments develop various score scales that are either linear or nonlinear transformations of raw scores for better interpretations and uses of assessment results. The current formula for coefficient alpha (a; the commonly used reliability coefficient) only provides internal consistency reliability estimates of raw…

This paper uses an approximate average percent-correct methodology to compare the ranks that would be obtained for PISA 2006 countries if the rankings had been derived from items judged by each country to be of highest priority for inclusion. The results reported show a remarkable consistency in the country rank orderings across different sets of…

The population sensitivity of vertical scaling results was evaluated for a state reading assessment spanning grades 3-10 and a state mathematics test spanning grades 3-8. Subpopulations considered included males and females. The 3-parameter logistic model was used to calibrate math and reading items and a common item design was used to construct…

This paper makes an in-depth comparison of the PISA (OECD) and TIMSS (IEA) mathematics assessments conducted in 2003. First, a comparison of survey methodologies is presented, followed by an examination of the mathematics frameworks in the two studies. The methodologies and the frameworks in the two studies form the basis for providing…

This study evaluated the impact of unequal reliability on test equating methods in the nonequivalent groups with anchor test (NEAT) design. Classical true score-based models were compared in terms of their assumptions about how reliability impacts test scores. These models were related to treatment of population ability differences by different…

Coefficient "H" is used as an index of scalability in nonparametric item response theory (NIRT). It indicates the degree to which a set of items rank orders examinees. Theoretical sampling distributions, however, have only been derived asymptotically and only under restrictive conditions. Bootstrap methods offer an alternative possibility to…

One-parameter (1PPC) and two-parameter partial credit (2PPC) models were compared using real and simulated data with constructed response items present. Results suggest that the more flexible three-parameter logistic-2PPC model combination produces better model fit than the combination of the one-parameter logistic and the 1PPC models. (SLD)

Procedures used to establish the comparability of scores derived from the College Board Admissions Testing Program (ATP) computer adaptive Scholastic Aptitude Test (SAT) prototype and the paper-and-pencil SAT are described in this report. Both the prototype, which is made up of Verbal and Mathematics computer adaptive tests (CATs), and a form of…

The purpose of this study was to compare and evaluate five online pretest item calibration/scaling methods in computerized adaptive testing (CAT): (1) the marginal maximum likelihood estimate with one-EM cycle (OEM); (2) the marginal maximum likelihood estimate with multiple EM cycles (MEM); (3) Stocking's Method A (M. Stocking, 1988); (4)…