Accurate equating results are essential when comparing examinee scores across exam forms. Previous research indicates that equating results may not be accurate when group differences are large. This study compared the equating results of frequency estimation, chained equipercentile, item response theory (IRT) true-score, and IRT observed-score…

This article considers two new smoothing methods in equipercentile equating, the cubic B-spline presmoothing method and the direct presmoothing method. Using a simulation study, these two methods are compared with established methods, the beta-4 method, the polynomial loglinear method, and the cubic spline postsmoothing method, under three sample…

The concept of invariance in equating and linking is traced from the 1950s to the present. A number of research studies that examined population invariance are reviewed. Theory and research suggest that linkings other than equatings are population dependent. Theory also indicates that equatings are population dependent, although when test forms…

Reviews research literature on comparability issues in computerized adaptive testing (CAT) and synthesizes issues specific to comparability and test security. Develops a framework for evaluating comparability that contains three categories of criteria: (1) validity; (2) psychometric property/reliability; and (3) statistical assumption/test…

Describes procedures for calculating conditional standard error of measurement (CSEM) and reliability of scale scores and classification of consistency of performance levels. Applied these procedures to data from the American College Testing Program's Work Keys Writing Assessment with sample sizes of 7,097, 1,035, and 1,793. Results show that the…

Describes four procedures previously developed for estimating conditional standard errors of measurement for scale scores and compares them in a simulation study. All four procedures appear viable. Recommends that test users select a procedure based on various factors such as the type of scale score of concern, test characteristics, assumptions…

Presents an Item Response Theory (IRT) method for estimating standard errors of measurement of scale scores for the situation in which scale scores are nonlinear transformations of number-correct scores. Also describes procedures for estimating the average conditional standard error of measurement for scale scores and the reliability of scale…

Nine methods of smoothing double-entry expectancy tables (tables that relate two predictor variables to probability of attaining success on a criterion) were compared using data for entering students at 85 colleges and universities. The smoothed tables were more accurate than those based on observed relative frequencies. (Author/CTM)

Linear and nonlinear methods for incorporating score precision information when the score scale is established for educational tests are compared. Examples illustrate the methods, which discourage overinterpretation of small score differences and enhance score interpretability by equalizing error variance along the score scale. Measurement error…

Two traditional equating schemes and seven item response theory equating schemes were compared. Data used came from the 1978 equating project of the Iowa Tests of Educational Development. The study entailed both the equating of forms of similar difficulty and the equating of levels of differing difficulty. (Arthor/RL)

The adequacy of equipercentile, linear, one-parameter (Rasch), and three-parameter logistic item-response theory procedures for equating 12 forms of five tests of general educational development were compared. Results indicated the equating method adequacy depends on a variety of factors such as test characteristics, equating design, and sample…

Item-preequating and random groups designs were used to equate forms of the American College Testing Assessment Mathematics Test for over 36,000 students. Equipercentile and three-parameter logistic model item response theory (IRT) procedures were used for both designs. The pretest methods did not compare well with the random groups method. (SLD)

A procedure is described for estimating the reliability and conditional standard errors of measurement of scale scores incorporating the discrete transformation of raw scores to scale scores. The method is illustrated using a strong true score model, and practical applications are described. (SLD)

Estimation/smoothing methods that are flexible enough to fit a wide variety of test score distributions are reviewed: kernel method, strong true-score model-based method, and method that uses polynomial log-linear models. Applications of these methods include describing/comparing test score distributions, estimating norms, and estimating…