In 1994 the State Collaborative on Assessment and Student Standards of the Council of Chief State School Officers began a study to examine the generalizability of performance-based assessments (PBAs) for state-mandated assessment programs. The intent was to examine the major sources of error associated with PBAs and the generalizability and…

Several recent studies have investigated the application of statistical inference procedures to the analysis of differential item functioning (DIF) in test items that are scored on an ordinal scale. Mantel's extension of the Mantel-Haenszel test is a possible hypothesis-testing method for this purpose. The development of descriptive statistics for…

When students are nested within course sections, the assumption of independence of residuals is unlikely to be met, unless the course section is explicitly included in the model. Hierarchical linear modeling (HLM) allows for modeling the course section as a random effect, leading to more accurate standard errors. In this study, students chose one…

This paper examines some characteristics of the statistics associated with the sampling distribution of the proficiency level estimate when the Rasch model is used. These characteristics allow the judgment of the meaning to be given to the proficiency level estimate obtained in adaptive testing, and as a consequence, they can illustrate the…

A brief note presenting algebraically equivalent formulas for the variances of three error types. (Author)

Paper is concerned with the hypothesis that two variables have a perfect disattenuated correlation, hence measure the same trait except for errors of measurement. (Author/RK)

The general problem of using group status to estimate true scores given multiple measures is considered in this paper. (Authors)

An alternative biweight estimator based on Tukey's is examined in which (1) test disturbances are not assumed to be the same for all subjects, (2) each response is utilized proportional to its value, and (3) the biweight and maximum likelihood estimate agree when no disturbances are present. Smaller mean-squared errors are shown. (Author/CM)

Two psychological experiments--Anderson and Shanteau (1970), Berkowitz and LePage (1967)--are reanalyzed to present the problem of the relative importance of low Type 1 error probability and high power when answering a research question by testing several statistical hypotheses. (Author/PN)

This review of issues about correcting for attenuation concludes that the basic difficulty lies in being able to identify and equate sources of variance in estimates of validity and reliability. Recommendations are proposed for cautious use of correction for attenuation. (Author/CM)

In a Monte Carlo simulation, a methodology was developed to investigate the existence of radex properties among objective test items. In an experiment with items covering four categories of Bloom's cognitive domain taxonomy, the items did not have the factorial properties of a radex with four levels of complexity. (Author/BW)

No WISC-R IQ scale is immune to serious scoring errors. Inspection of the standard deviations reveals that the score an examinee receives for a given performance on WISC-R content can easily vary by six to eight IQ points. (Author)

Discusses the problems associated with teaching uncertainties in measurements and significant figures. Appendices present an experiment on measurement that introduces uncertainty in measurement, and an exercise in significant figures. (CS)

There are difficulties in expressing effect sizes on a common metric when some studies use transformed scales to express group differences, or use factorial designs or covariance adjustments to obtain a reduced error term. A common metric on which effect sizes may be standardized is described. (Author/RL)

Supposing different values of the standard measurement error, the relation of scale coarseness to the total amount of error is studied on the basis of probability distribution of error. The analyses are performed within two models of error and with two criteria of amount of error. (Editor/SJL)