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)

Current scoring procedures depend on unrealistic assumptions about subjects' performance on the rod-and-frame test. A procedure is presented which corrects for constant error, is sensitive to response strategy and consistency, and examines qualitative and quantitative aspects of performance and individual differences in laterality bias as defined…

Discusses four ubiquitous major sources of measurement error for individual intelligence scales. Argues that where these sources cannot be directly investigated, they should be estimated rather than ignored. Estimated the typical magnitude of error arising from each of content sampling, time sampling, scoring, and administration. (Author)

Findings for couples (N=119) show wife's work, money, and spare time low between-spouse correlations are due in part to random measurement error. Suggests that increasing reliability of measures by creating multi-item indices can also increase correlations. Car purchase, vacation, and child discipline were not accounted for by random measurement…

Assesses the reliability and stability of television exposure, and the relationship of various demographic variables to this hypothetical construct, when measurement error is removed. Analyzes data collected from Black adults. Concludes that more attention should be given to theoretically defining media exposure and to taking into account…

The accuracy of statistics based on performance assessments that represent percentages of students reaching standards is explored using data from a large-scale performance assessment, the Maryland School Performance Assessment Program. Results with students in grades 3, 5, and 8 support the accuracy of pooling results to produce the statistics.…

Goodness of fit indexes developed by R. P. McDonald (1989) and Satorra-Bentler scale correction methods (A. Satorra and P. M. Bentler, 1988) were studied. The Satorra-Bentler index is shown to have the least error under each distributional misspecification level when the model has correct structural specification. (SLD)

Through the standard error, rather than a reliability coefficient, generalizability theory provides an indicator of the uncertainty attached to school and individual scores on performance assessments. Recommendations are made to apply generalizability theory to current performance assessments, emphasizing practices that differ from usual…

LISREL 8 invokes a ridge option when maximum likelihood or generalized least squares are used to estimate a structural equation model with a nonpositive definite covariance or correlation matrix. Implications of the ridge option for model fit, parameter estimates, and standard errors are explored through two examples. (SLD)

Variability of aided sound field thresholds (ASFTs) was examined in 30 hearing-impaired children comprising 2 age groups (5-9 and 10-14 years). Findings showed that 2 ASFTs would have to differ by more than 10 decibels across signal test frequencies to attain statistical significance. (Author/DB)

A Monte Carlo simulation was used to examine pay-performance relationships. Conventional merit systems achieved a better link between pay and performance than bonus systems, because merit systems benefit from consistency of performance over time. Even very substantial errors in measurement of performance have only a modest effect on…

Describes a study used to determine differences in exam reliability, difficulty, and student evaluations. Indicates that when a fourth option was added to the three-option items, the exams became more difficult. Includes methods, results discussion, and tables on student characteristics, whole test analyses, and selected items. (RT)

Simulated data were used to investigate the performance of modified versions of the Mantel-Haenszel method of differential item functioning (DIF) analysis in computerized adaptive tests (CAT). Results indicate that CAT-based DIF procedures perform well and support the use of item response theory-based matching variables in DIF analysis. (SLD)

Regression to the mean (RTM) is often misunderstood. It is demonstrated that artifactual RTM depends fundamentally on the magnitude of measurement error at pretest. Adjustment usually involves estimating the measurement error and determining consequences, but even without adjustment, effects of RTM can be ameliorated. (SLD)

A generalized variance criterion is proposed to measure efficiency in item-response-theory (IRT) models. Heuristic arguments are given to formulate the efficiency of a design in terms of an asymptotic generalized variance criterion. Efficiencies of designs for one-, two-, and three-parameter models are compared. (SLD)