A method for the construction of scales which combines the rational (or intuitive) approach with an empirical (item analysis) approach is presented. A step-by-step procedure is provided. (Author/JKS)

The interaction of subjects with test items is investigated. It is suggested that psychometricians rely too heavily on inferences about the nature of the interaction. An approach to data analysis is proposed which is more directly related to this interaction. (JKS)

Some preliminary data on Self-Esteem Questionnaire (SEQ), organized along Gough's conceptual model of primary, secondary, and tertiary evaluation, are presented. The SEQ appears to discriminate groups along a self-esteem continuum; fits in well with a variety of theoretical approaches; does not have loadings on sex, intelligence, or social status.…

The Family Health Scale is an instrument designed to quantify the quality of psychiatrically labeled or nonlabeled family functioning from the perspective of an external clinical observer. Clinical judgment is exercised in rating, based on information available and ideally from a valid standardized method of direct observation. Discusses…

Generalizability theory was used in this study of the Group Embedded Figures Test, which was administered to undergraduates in a mathematics course. Results indicated that the test has desirable psychometric characteristics, including test and item difficulty and item discrimination coefficients. (Author/GDC)

A role-playing measure of teenage girls' problem-solving skills--the Problem Inventory for Adolescent Girls (PIAG)--was administered to groups of Caucasian and Black female delinquents and nondelinquents. The PIAG significantly differentiated between adjudicated delinquents and nondelinquents and between subjects reporting high and low levels of…

When the parameters of item response data are estimated by a latent trait model, some variation will remain unaccounted. If baseline graphical configurations of the residual variation can be constructed, measurement irregularities may be exposed. An analytic strategy for the graphical representation and analysis of Rasch model residuals is…

The present study replicated an earlier investigation using the Pupil Control Ideology (PCI). The findings were congruent with earlier results. Consequently, it was recommended that the PCI should be refined and that the 10 item, unidimensional scale should be used in future investigations. (Author/LMO)

Despite much evidence that the Jenkins Activity Survey Type A (JAS Type A) scale is lacking in essential psychometric properties, it continues to be widely used for measuring coronary-prone behavior. Four psychometric properties of the scale were assessed. The scale failed to satisfy accepted reliability and validity criteria. (Author/JAZ)

Describes the development of a Values Conflict Resolution Assessment (VCRA) and reports on validation and reliability. Items were constructed from theoretical criteria in values clarification and decision making with "ethical-emotional" and "rational-behavioral" components. VCRA scores correlated negatively with…

In the present research, the psychometric models of Rasch and Guttman are used to illustrate contrasting yet complementary approaches to investigating reading skill hierarchies. The models share a general conclusion, but specific results from the Rasch model underscore its greater potential as a reading skills diagnostic technique. (Author/LMO)

Ruchalla, Schalt, and Vogel (1985) reported a negative correlation between the g-loadness of intelligence subtests and the extent to which the subtests correlated with reaction times. Possible methodological problems with Ruchalla et al. are described, and results of two other studies pertinent to the issue are discussed. (Author/LMO)

These analyses suggest that if a criterion-referenced test had a reliability (defined in terms of internal consistency) below 0.5, a simple a priori procedure would provide better estimates of students' universe scores than would individual observed scores. (Author/LMO)

The Rasch latent trait model was applied to investigate the relationship of performance on Raven items to expectations for individuals at different levels of the underlying scale. The use of Rasch model in instances of small samples and issues related to the interpretation of the model to Raven-type data are discussed. (DWH)

Compares concurrent validity of four sex-role instruments administered to a group of 281 urban university students. Reports that the instruments are sufficiently different in their measurement characteristics to warrant limiting generalizations about behavior based on these instruments to a particular instrument being used. (KH)