An increasingly popular test format allows examinees to choose the items they will answer from among a larger set. When examinee choice is allowed fairness requires that the different test forms thus formed be equated for their possible differential difficulty. For this equating to be possible it is necessary to know how well examinees would have…

Applications of item response theory to practical testing problems including equating, differential item functioning, and computerized adaptive testing, require that item parameter estimates be placed onto a common metric. In this study, three methods for developing a common metric under item response theory are compared: (1) linking separate…

To generalize test results beyond the particular test administration, an examinee's ability estimate must be independent of the particular items attempted, and the item difficulty calibrations must be independent of the particular sample of people attempting the items. This stability is a key concept of the Rasch model, a latent trait model of…

This study investigated the extent to which log-linear smoothing could improve the accuracy of common-item equating by the chained equipercentile method in small samples of examinees. Examinee response data from a 100-item test (the Advanced Placement Examination in United States History) were used to create two overlapping forms of 58 items each,…

In this paper a quadratic curve equating method for different test forms under a random-group data-collection design is proposed. Procedures for implementing this method and related issues are described and discussed. The quadratic-curve method was evaluated with real test data (from two 30-item subtests for a professional licensure examination…

The Maryland Functional Testing Program (MFTP) uses the Rasch model as the statistical framework for the analysis of test items and scores. This paper is designed to assist the reader in developing an understanding of the fit statistics in the Rasch model. Background materials on application of the Rasch model in statistical analysis of the MFTP…

A procedure used to average several Mantel-Haenszel delta difference values for an item is described and evaluated. The differential item functioning (DIF) procedure used by the Educational Testing Service (ETS) is based on the Mantel-Haenszel statistical technique for studying matched groups. It is standard procedure at ETS to analyze test items…

The 1986 scores from the Statewide Student Assessment Test-II, a minimum-competency test required for high school graduation in Florida, were placed on the scale of the 1984 scores from that test using five different equating procedures: (1) linear method; (2) Rasch model; (3) three-parameter item response theory (IRT)--concurrent method; (4)…

This study examined how four commonly used test equating procedures (linear, equipercentile, Rasch Model, and three-parameter) would respond to situations in which the properties or the two tests being equated were different. Data for two tests plus an external anchor test were generated from a three parameter model in which mean test differences…

Comparisons were made of three Angoff Design V linear equating methods (two forms equated to a common test, two forms predicted by a common test, or two forms used to predict a common test) and Tucker's and R. Levine's linear methods, under common item linear equating with non-equivalent populations. Forms of a professional certification test…

New legislation in 1972 shifted the emphasis of the California Assessment Program (CAP) from traditional every pupil achievement testing to a more efficient multiple-matrix testing design, under which a broad spectrum of skills could be surveyed without undue expenditure of educational resources. Scale score reporting was introduced to the grade 6…

Three local norm methods for deriving Elementary Secondary Education Act Title I normal curve equivalent (NCE) gains are compared to each other and to the usual Model A1 which uses national norms. The 1977-78 Title I evaluation data for Chicago students ages 9-13 were used to estimate gains. Reading and total math scores from the 1971 Iowa Tests…

Data from the verbal portion of the College Entrance Examination Board Scholastic Aptitude Tests were used in an experimental test of the accuracy of equating for a variety of models in three categories: linear equating, equipercentile equating, and item characteristic curve equating. The models were tested for both mean squared error and bias.…

The three-, two- and one-parameter (Rasch) logistic item characteristic curve models are compared for use in a large multi-section college course. Only the three-parameter model produced clearly unacceptable parameter estimates for 100 item tests with examinee samples ranging from 594 to 1082. The Rasch and two-parameter models were compared for…

By means of computer simulation of test responses, the reliability of item analysis data and the accuracy of equating were examined for hypothetical samples of 250, 500, 1000, and 2000 subjects for two tests with 20 equating items plus 60 additional items on the same scale. Birnbaum's three-parameter logistic model was used for the simulation. The…