Two longitudinal studies involving 29 raters concerning the construct validity, temporal stability, and interrater reliability of the latent common factors underlying subjective assessments by human raters of personality traits in the stumptail macaque and the zebra finch illustrate the use of generalizability analysis to test prespecified…

This article reviews the history of divergent thinking tests and provides a projection of current research suggesting a bright outlook for creativity tests. A model relating problem finding and problem solving is described, as are approaches to increasing test reliability. (DB)

Elaborates on and responds to challenges of direct writing assessment. Speculates on future directions in writing assessment. Suggests that, if writing instructors accept that writing is a multidimensional, situational construct that fluctuates across a wide variety of contexts, then they must also respect the complexity of teaching and testing…

Concerns about norm-referenced achievement tests involve (1) the purposes of the tests (comparability of results); (2) the content of the tests; (3) psychometric screening of test items; (4) the form of tests items; (5) the interpretation of summary scores; and (6) the construct validity of the tests. Offers guidelines for use of norm-referenced…

An equation derived by W. A. Nicewander and J. M. Price relating statistical power to reliability of dependent variable measures when true score regression is homogeneous across treatment conditions is enhanced through overcoming the problem of directly estimating the squared linear correlation between true scores for X and Y. (SLD)

Reports development of a battery of scales measuring four dimensions of adolescent leisure experience: boredom, awareness, anxiety, and challenge. Analysis confirmed the internal consistency reliability of a shortened version. Test-retest reliability was established over 12 months. Correlations with theoretically related measures suggested initial…

A technique is presented to transform incomplete categorical data into complete data by imputing appropriate scores into missing cells. A solution of the optimization problem is suggested, and relevant psychometric theory is discussed. The average correlation should be at least 0.50 before the method becomes practical. (SLD)

Discusses the development of the Family Assessment Form for use in in-home family support services at the Children's Bureau of Los Angeles, California. Focuses on details of the form, its reliability and validity, and refinements in its use. (BB)

The degree of agreement between two raters rating several objects for a single characteristic can be expressed through an association coefficient, such as the Pearson product-moment correlation. How to select an appropriate association coefficient, and the desirable properties and uses of a class of such coefficients--the Euclidean…

The discrete mathematics topics of trees and computational complexity are implemented in a simple reliability program which illustrates the process advantages of the PASCAL programing language. The discussion focuses on the impact that reliability research can provide in assessment of the risks found in complex technological ventures. (Author/JJK)

National Assessment of Educational Progress writing sample essays from 1988 and 1990 (495 and 599 essays) were subjected to computerized grading and human ratings. Cross-validation suggests that computer scoring is superior to a two-judge panel, a finding encouraging for large programs of essay evaluation. (SLD)

Scores from 324 Louisiana schools on the Louisiana Graduation Exit Examination and a within-school split sample of 255 schools indicate that a single subject or grade provides a less consistent and more narrow perspective on school effectiveness than a subcomposite made up of 2 subject areas. (SLD)

Investigated correlations between two intelligence measures for exceptional children. Corrected correlations between the tests indicated differences with correlations reported in one manual. Relationships were generally higher than those reported elsewhere. Implications are discussed, especially those involving the use of correlations between…

Nine comprehensive observations were conducted of 24 preschoolers (8 with disabilities) in free play settings, with social behavior categories based on the work of Strain. Comparison of partial and complete observational records demonstrated that at least five observations were required to represent the children's social behavior adequately.…

It is proposed that proportional reduction in loss (PRL) be used as a theoretical basis to derive, justify, and interpret reliability measures to gauge reliability on a zero-to-one scale. This PRL approach simplifies the interpretation of existing measures (e.g., generalizability-theory measures). (SLD)