After an extensive review of the available research on large-scale writing assessment, certain issues in writing assessment seem to be unresolved, and still other issues are not supported by adequate research. This paper reviews the basic issues in writing assessment, points out which topics are supported by strong research, and which topics are…

Much previously published material for estimating the reliability of classification has been based on the assumption that a test consists of a known number of equally weighted items. The test score is the number of those items answered correctly. These methods cannot be used with classifications based on weighted composite scores, especially if…

Arguments have recently been put forth that standard textbook procedures for determining the sample size necessary to achieve a certain level of power in a completely randomized design are incorrect when the dependent variable is fallible because they ignore measurement error. In fact, however, there are several correct procedures, one of which is…

The Bayesian approach to setting passing scores, as proposed by Swaminathan, Hambleton, and Algina, is compared with the empirical Bayes approach to the same problem that is derived from Huynh's decision-theoretic framework. Comparisons are based on simulated data which follow an approximate beta-binomial distribution and on real test results from…

Because latent trait models require that large numbers of items be calibrated or that testing of the same large group be repeated, item parameter estimates are often obtained by administering separate tests to different groups and "linking" the results to construct an adequate item pool. Four issues were studied, based upon the analysis…

The adequacy of a test developed for statewide assessment of basic mathematics skills was investigated. The test, comprised of multiple-choice items reflecting a series of behavioral objectives, was compared with a more extensive criterion measure generated from the same objectives by the application of a strict item sampling model. In many…

Vision assessments were provided to 297 preschoolers in nine Head Start programs in New York State. The protocol used provided a thorough evaluation and required only seven minutes per child. Sixty-three children (21.2%) were referred for further evaluation. Visual deficits detected included decreased acuity, strabismus, astigmatism, and…

This special issue covers recent technical developments in the field of criterion-referenced testing. An introduction, six papers, and two commentaries dealing with test development, test score uses, and evaluation of scores review relevant literature, offer new models and/or results, and suggest directions for additional research. (SLD)

The concurrent validity and reliability of Kaufman's short-form version of the McCarthy Scales of Children's Abilities were examined for a sample of 342 Mexican-American preschool and kindergarten age children. The results showed that generally the positive psychometric properties of the Kaufman short form were also noted for the children in this…

Error indices (bias, standard error of estimation, and root mean square error) obtained on different scales of measurement under different test termination rules in a computerized adaptive test (CAT) context were examined. Four ability estimation methods were studied: (1) maximum likelihood estimation (MLE); (2) weighted likelihood estimation…

This paper focuses on mixtures of two binomials with one known success parameter. It is shown how moment estimators can be obtained for the remaining unknown parameters of such mixtures, and results are presented from a Monte Carlo study carried out to explore the statistical properties of these estimators. (PN)

The number of rating items preferred by students on an instructional evaluation instrument was investigated. The median length preferred was 25 items. (Author/GK)

Compared area scores from short-form version of Stanford-Binet Intelligence Test (Fourth) with those from long form for 33 gifted children. Found three of five mean difference contrasts were significantly different and correlation coefficients between corresponding area scores and Test Composite were statistically significant. Suggests that…

The development of a short form of the Raven Advanced Progressive Matrices Test is reported. Results from 3 studies with 663 college students indicate that the short form demonstrates psychometric properties similar to the long form yet requires a substantially shorter administration time. (SLD)