To determine if Rasch Model procedures have any utility for equating pre-existing tests, data from the equating phase of the Anchor Test Study (ATS) were reanalyzed. This management report summarizes the work completed in the project, describes the differences in this project and that of the ATS, and presents recommendations and conclusions to the…

The purpose of this investigation was to establish the effects of repeaters on test equating. Since consideration was not given to repeaters in test equating, such as in the derivation of equations by Angoff (1971), the hypothetical effect needed to be established. A case study was examined which showed results on a test as expected; overall mean…

Prior use of the equipercentile method of test equating was based on a graphic procedure which is tedious, subject to smoothing errors, and non-analytical. Recognition of the equipercentile method as a curve-fitting procedure for two cumulative percentage distributions leads to a proposed analytical solution to the problem through use of linear…

The Anchor Test Study provides a method for translating a pupil's score on any one of eight widely used standardized reading tests for Grades 4, 5, and 6 to a corresponding score on any of the other seven tests, as well as furnishing new nationally representative norms for each of the eight tests. In addition, the Study presents new estimates of…

This study examines a common set of equating items for their appropriateness to both American and Canadian populations and, to determine the equations for converting scores from the verbal and mathematical scales of the 1971 form of the Canadian Scholastic Aptitude Test (the future standard continuing scales of the CSAT) to the corresponding…

Rasch model equatings of multilevel achievement test data before and after the deletion of misfitting persons were compared. Rasch equatings were also compared with an equating obtained using the equipercentile method. No basis could be found in the results for choosing between the two Rasch equatings. (Author/LMO)

Three professional associations, the American Educational Research Association, the American Psychological Association, and the National Council on Measurement in Education, jointly adopted the new "Standards for Educational and Psychological Testing" in 1985. The relationship of these to earlier standards is reviewed, and implications…

A procedure is proposed for determining whether correlations obtained between two measures justify the assumption that the measures are identical. It is intended especially for small samples. In the example, the performance scales of two intelligence tests were administered to 32 deaf adolescents. (GDC)

One of the most challenging issues a state must resolve in designing a statewide standards and college readiness assessment is that of how student scores should be reported. The ACT is an effective and reliable measure of student readiness for college and work, but in some cases states may wish to augment the ACT with tests of their own design. In…

This study explores the relative merits of a potentially useful item response theory (IRT) linking design: using a single set of anchor items with fixed common item parameters (FCIP) during the calibration process. An empirical study was conducted to investigate the appropriateness of this linking design using 6 groups of students taking 6 forms…

Application of the Rasch model to data from 267 naval personnel taking a multiple-choice test subject to guessing indicates that goodness of fit is a problem small enough to ignore, but that modification to account for guessing may be necessary for accurate equating. (SLD)

The properties of Tucker's congruence coefficient--an index used to help determine the equality of latent structures for different subgroups on a common set of test items--are explored. An example using data from 1,370 subjects in the National Assessment of Educational Progress 1976 mathematics assessment illustrates the index's use. (SLD)

For anchor test equating, 3 linear observed score methods are derived for populations differing in ability. Each version requires that the correlations of the tests with the selection variable be known. Five sets of assumptions are made for each model--yielding 15 methods--which are then related to existing methods. (SLD)

Combinations of five methods of equating test scores and two methods of selecting samples of students for equating were compared for accuracy, using data from the administration of the Scholastic Aptitude Test to more than 115,000 students. Implications for research and practice are discussed. (SLD)

Data from the California Learning Assessment System mathematics assessment were used to examine issues that arise when scores from different assessment modes are combined. Multiple-choice, open-ended, and investigation items were combined in a test across three test forms. Results illustrate the difficulties faced in evaluating combined…