An equating design in which two groups of examinees from slightly different populations are administered a different test form with a subset of common items is widely used. This paper presents standard errors and a simulation that verifies the equation for large samples for an equipercentile equating procedure for this design. (Author/BS)

This paper develops and illustrates a latent trait approach to constructing an item bank when responses are scored in several ordered categories. This approach is an extension of the methodology developed by Choppin, Wright and Stone, and Wright and Bell for the construction and maintenance of banks of dichotomously scored items. (Author/PN)

This study investigated the effect on student scores of using anchor sets that differed in dimensionality in item response theory (IRT) scaled tests. Real data from a mathematics achievement test that had been documented to have dimensions aligned with item format were used. Item responses were available from a representative sample of…

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…

This study compared the performance of the LOGIST and BILOG computer programs on item response theory (IRT) based scaling and equating for the Test of English as a Foreign Language (TOEFL) using real and simulated data and two calibration structures. Applications of IRT for the TOEFL program are based on the three-parameter logistic (3PL) model.…

An instructional module is presented to promote a conceptual understanding of test form equating using traditional methods. Equating is distinguished from scaling. The equating methods described are: (1) mean; (2) linear; and (3) equipercentile. The module includes a self-test. (SLD)

Whether anchor item sets varying in difficulty and discrimination affect precision of cutting score equivalents generated through judge rescaling as much as equivalents from score equating was studied with 4 groups of experts and 250 and 1,000 examinees. Results indicate the robustness of judge rescaling and its superiority over equating. (SLD)

Scores from four samples each of 250 and 1,000 physicians demonstrated that a linear procedure for equating scores and rescaling judges' standards for a certification test could be applied to individual item data gathered through the Angoff standard-setting method. Equated and rescaled values were close to those actually assigned. (SLD)

Performance of a common set of test items on an examination in which the order of options for one test form was experimentally manipulated. Results for 759 medical specialty board examinees find that reordering item options results in significant but unpredictable effects on item difficulty. (SLD)

The following ways of linking results from distinct assessments to use them for multiple purposes are reviewed: (1) equating; (2) calibration; (3) statistical moderation; (4) prediction; and (5) social moderation. The characteristics of these methods, their requirements, and the comparative inferences they support are described. (SLD)

This paper describes the basic concepts of linking educational assessments. Although it discusses statistical machinery for interpreting evidence about students' achievements, this paper's principal message is that linking tests is not just a technical problem. Technical questions can not be asked or answered until questions about the nature of…

This study compared the lower asymptotes estimated by the maximum likelihood procedures of the LOGIST computer program with those obtained via application of the Norton methodology. The study also compared the equating results from the three-parameter logistic model with those obtained from the equipercentile, Rasch, and conditional…

Reviews the Anchor Test Study which had two major objectives: to provide a method for translating a child's score on any one of eight widely used standardized reading tests into a score on any of the other tests and to provide new nationally representative norms for each of these eight tests. (Author/BJG)

This paper provides empirical data on two approaches to statistically equate scores derived from the direct assessment of writing. These methods are linear equating and equating based on the general polychotomous form of the Rasch model. Data from the Maryland Functional Writing Test are used to equate scores obtained from two prompts given in…

An investigation is described of the ORT ONLY MODEL, which is one of four models being used to obtain national norm-referenced and local criterion- or objective-referenced information from a single assessment instrument. Raw scores on a norm-referenced test (NRT) were equated to raw scores on an objective-referenced test (ORT). Resultant equating…