In many practical settings, essentially the same differential item functioning (DIF) procedures have been in use since the late 1980s. Since then, examinee populations have become more heterogeneous, and tests have included more polytomously scored items. This paper summarizes and classifies new DIF methods and procedures that have appeared since…

The Longitudinal Surveys of Australian Youth (LSAY) is a research program that tracks young people as they move from school into further study, work and other destinations. It uses large, nationally representative samples of young people to collect information about education and training, work, and social development. It includes surveys…

Various methods of estimating main effects from ordinal data are presented and contrasted. Problems discussed include: (1) at what level to accumulate ordinal data into linear measures; (2) how to maintain scaling across analyses; and (3) the inevitable confounding of within cell variance with measurement error. An example shows three methods of…

Tukey's Honestly Significant Difference (HSD) procedure (J. Tukey, 1953) is probably the most recommended and used procedure for controlling Type I error rate when making multiple pairwise comparisons as follow-ups to a significant omnibus F test. This study compared observed Type I errors with nominal alphas of 0.01, 0.05, and 0.10 compared for…

This repeated measures factorial design study compared the results of two procedures for identifying multivariate outliers under varying conditions, the Mahalanobis distance and the Andrews-Pregibon statistic. Results were analyzed for the total number of outliers identified and number of false outliers identified. Simulated data were limited to…

This study examines how closely the kernel equating (KE) method (von Davier, Holland, & Thayer, 2004a) approximates the results of other observed-score equating methods--equipercentile and linear equatings. The study used pseudotests constructed of item responses from a real test to simulate three equating designs: an equivalent groups (EG)…

A brief, practical overview of "design effects" (DEFFs) is presented for users of the results of sample surveys. The overview is intended to help such users to determine how and when to use DEFFs and to compute them correctly. DEFFs are needed only for inferential statistics, not for descriptive statistics. When the selections for…

This study applies a procedure which yields estimates of true score change on the Scholastic Aptitude Test (SAT) adjusted for regression effects and student self-selection. It is shown that student self-selection in deciding to repeat an admissions test probably involves factors in addition to the measurement error attributable to variations in…

Formulas are derived for the bias in the maximum likelihood estimators (MLE) of the item parameters in the logistic item response model when examinee abilities are known. Numerical results are given for a typical verbal test for college admission. Most typically the bias of an MLE is about one-tenth of its standard error. It is very seldom more…

A possible method is developed for computing the asymptotic sampling variance-covariance matrix of joint maximum likelihood estimates in item response theory when both item parameters and abilities are unknown. For a set of artificial data, results are compared with empirical values and with the variance-covariance matrices found by the usual…

A procedure for estimating reliability in a factor analytic context, when reliability of the extracted factors is not an emphasis, is identified. The procedure is an extension of Dressel's work and might be applied in attitude measurement. It assesses how homogeneous the weighted original item responses are, when they are scored for pattern…

Investigated empirically through post mortem item-examinee sampling were the relative merits of two alternative procedures for allocating items to subtests in multiple matrix sampling and the feasibility of using the jackknife in approximating standard errors of estimate. The results indicate clearly that a partially balanced incomplete block…

Current usage and theory of standard error of measurement calls for one standard error of measurement figure to be used across all levels of scoring. The study revealed that scoring variance across scoring levels is not constant. As scoring ability increases scoring variance decreases. The assertion that low and high scoring subjects will…

The formulas which give the standard errors of factor loading estimates while available and computable are complicated, and our understanding of them is limited. A nontechnical description of their behavior under favorable and unfavorable conditions is given. Of particular interest is their behavior in the presence of singularities arising from…