A Paradigm for testing concept attainment, comprised of twelve tasks, was formulated. These tasks were hypothesized to form a cumulative hierarchy. Tests were constructed in mathematics and social studies using the paradigm. Data for these tests was analyzed by Kaiser's method for fitting a perfect simplex and Schonemann's method for fitting a…

A summary is provided of the rationale for questioning the applicability of classical reliability measures to criterion referenced tests; an extension of the classical theory of true and error scores to incorporate a theory of dichotomous decisions; a presentation of the mean split-half coefficient of agreement, a single-administration test index…

A cubic spline method for smoothing equipercentile equating relationships under the common item nonequivalent populations design is described. Statistical techniques based on bootstrap estimation are presented for choosing an equating method/degree of smoothing. Smoothing decreases the estimate of random error but results in an increase in…

Argues that rank order correlations may not be ubiquitously suitable for assessing the relations between children's behavior or characteristics at one age or in one situation, and those shown later or in another context. (HOD)

Classifies errors as either systematic or blunder and uncertainties as either systematic or random. Discusses use of error/uncertainty analysis in direct/indirect measurement, describing the process of planning experiments to ensure lowest possible uncertainty. Also considers appropriate level of error analysis for high school physics students'…

The Bookmark Standard Setting Procedure (Lewis, Mitzel, and Green, 1996) is an item-response-theory-based standard setting method that has been widely implemented by state testing programs. The primary purposes of this study were to: (1) estimate standard errors for cutscores that result from Bookmark standard settings under a generalizability…

This study explored possible configurations of the new SAT® critical reading section without analogy items. The item pool contained items from SAT verbal (SAT-V) sections of 14 previously administered SAT tests, calibrated using the three-parameter logistic IRT model. Multiple versions of several prototypes that do not contain analogy items were…

Two sources of inconsistency were separated by reanalyzing data from a major study on short-term consistency. Little evidence was found for generalizability or behavioral predictability. Results supported the assumption that measurement error from short-term fluctuations is not due to systematic individual differences in response consistency.…

Mail questionnaire items that are susceptible to order effects were examined using data from 168 questionnaires in a Florida Cooperative Extension Service evaluation. Order effects were found for multiple-response and attributive questions but not for single-response items. Order also interacted with question complexity, social desirability, and…

Potential methods are explored for removing or otherwise controlling random measurement error, assessment artifacts, irrelevant variation in outcome measures, and confounding sources of covariation in a structural equations model. Using examples with measures of quality of life and functioning, the authors consider these methods for field…

This study provides empirical evidence about the sampling variability and generalizability (reliability) of a statewide performance assessment for grade six. Results for 600 students at individual and school levels indicate that task-sampling variability was the major source of measurement error. Rater-sampling variability was negligible. (SLD)

Methods for setting cutoff scores based on criterion performance, normative comparison, and absolute judgment were compared for scores on a multiple-choice psychology examination for 121 undergraduates and 251 undergraduates as a comparison group. All methods fell within the standard error of measurement. Implications of differences for decision…

Analysis of data on freshman-to-senior developmental gains in 722 University of Tennessee-Knoxville students provides evidence of the advantages of structural equation modeling with latent variables and suggests that the group differences identified by traditional analysis of variance and covariance techniques may be an artifact of measurement…

Bias, standard error, and reliability of five ability estimators were evaluated using Monte Carlo estimates of the unknown conditional means and variances of the estimators. Results indicate that estimates based on Bayesian modal, expected a posteriori, and weighted likelihood estimators were reasonably unbiased with relatively small standard…

Our purpose in this report is to evaluate scientifically that body of literature relating the effects of prenatal and postnatal exposure to polychlorinated biphenyls (PCBs) upon neurobehavioral, health-related, and cognitive deficits in neonates, developing infants, children, and adults. The data derive from seven cohorts: six cohorts of mothers…