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 study examined population invariance of equating functions over subgroups defined by ethnicity on a teacher certification test. Investigating subgroup equating invariance was important because the total group who took this test consists of two subgroups (i.e., Hispanic and non-Hispanic) and the Hispanic group is a distinctively more able…

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…

A method for equating test scores between two standardized achievement testing programs was developed. The first test was the Survey of Basic Skills (SBS) published by Science Research Associates. The second was the Tests of Individual Performance (TIP) of the Portland Public Schools in Oregon. Scores reported in Rasch units (RIT) from the TIP…

A formal analysis is presented of the effects of item deletion on equating/scaling functions and reported score distributions. The phrase "item deletion" refers to the process of changing the original key of a flawed item to either all options correct, including omits, or to no options correct, i.e., not scoring the flawed item. There…

The question of whether weighting (rank-ordering) of student teacher evaluation criteria, as determined by student and supervising teachers, university supervisors, and employing officials, results in better differentiation between and among student teachers is explored in this paper. Participants in the study were asked to rank order 15…

A common problem arises in scale transformation when independent estimates of item parameters from two separate data sets must be expressed in the same metric. These item parameter estimates will be different because the metric or scale defined by each independent calibration of the items is different. The problem is frequently confronted in…