Three tables are provided to aid in the clinical interpretation of factor scores for the Wechsler Adult Intelligence Scale-Revised (WAIS-R; 1981). The factor structure of the WAIS-R has proven to be robust across samples, tests, time, statistical analyses, measurement scales, and distortions of the distribution. Information necessary to make…

A practical application of generalizability theory, demonstrating how the variance components contribute to understanding and interpreting the data collected to evaluate a program, is described. The evaluation concerned 120 learning modules developed for the Dental Auxiliary Education Project. The goals of the project were to design, implement,…

Measurement disturbances, such as guessing, startup, and plodding, often result in an examinee's ability being either over- or under-estimated by the maximum likelihood estimation employed in latent trait psychometric models. Several authors have suggested methods to lessen the impact of unexpected responses on the ability estimation process. This…

Heckman's correction for regression in selected samples for predictive validity studies was applied to a large data file on 7,984 law school applicants. Data included ethnic group, sex, socioeconomic status, undergraduate degree, school, scores on the Law School Admission Test (LSAT), writing ability, undergraduate grade point average, and age.…

The reliability of criterion referenced tests, which are often used to evaluate health education programs, may be conceptualized in different ways. Classical conceptualizations of test reliability have limited usefulness when applied to health-related criterion referenced tests. When a cutting score is set, test reliability can be represented as…

This paper brings to first fruition an analytic schema based on four elements which involve a conception of skills independent or particular testing devices: (1) the development and application of a class of statistical models incorporating qualitative definitions of skill, distorted in item response by errors conceived as misclassifications; (2)…

The presence of artifactual bias in analysis of covariance (ANCOVA) and in matching nonequivalent control group (NECG) designs was empirically investigated. The data set was obtained from a study of the effects of a television program on children from three day care centers in Mexico in which the subjects had been randomly selected within centers.…

Failure to consider errors of measurement when using partial correlation or analysis of covariance techniques can result in erroneous conclusions. Certain aspects of this problem are discussed and particular attention is given to issues raised in a recent article by Brewar, Campbell, and Crano. (Author)

Item parameter estimates vary for a variety of reasons, including estimation error, characteristics of the examinee samples, and context effects (e.g., item location effects, section location effects, etc.). Although we expect variation based on theory, there is reason to believe that observed variation in item parameter estimates exceeds what…

The paper initially describes the sources of uncertainty in National Assessment of Educational Progress (NAEP) data and standard errors. As NAEP sample sizes have increased, greater precision has been attained by the program. For this reason, exclusion effects are increasingly important. Two scenarios of revised NAEP results are presented (for New…

School test performance is commonly summarized in terms of the percentage of students at or above a cut score (PAAC) that has been set on a test. Two approaches to estimating the standard errors for school PAACs were examined in this study: conditional standard errors and overall standard errors. The tests used were English language arts and…

Generalizability theory is used to examine the psychometric characteristics of the Listening and Writing Tests developed by American College Testing for its Work Keys program. Results with samples of 50 suggest the desirability of a minimum number of the tests' tape-recorded messages and the use of at least 2 raters. (SLD)

In studies of relatives, conventional multiple regression may not be appropriate because observations are not independent. Obtaining estimates of regression coefficients and correct standard errors from these populations through a structural equation modeling framework is discussed and illustrated with data from twins. (SLD)

A conceptual approach and a set of computer simulations are presented to demonstrate that random measurement error in the pretest does not bias the estimate of the treatment effect in the regression-discontinuity design. Focus is on the case of no interaction between pretest and treatment on posttest. (SLD)

The aim of the review of D.V. Cicchetti, A.S. Kaufman, and S.S. Sparrow (funded by the General Electric Company; this issue) is to "evaluate [the] literature relating the effects of prenatal and postnatal exposure to polychlorinated biphenyls (PCBs) upon neurobehavioral, health-related, and cognitive deficits in neonates, developing infants,…