The 32-item Attitudes about Romance and Mate Selection Scale (ARMSS) was developed to measure constraining beliefs about mate selection. Results of factor analysis showed few gender differences in the degree to which constraining beliefs about mate selection are held by single young adults. However, significant differences were found when age,…

Examines the construct validity of a scale for 7-year-old children and analyzes the degree of factorial similarity between this analysis and another study performed on 4-year-old children. Results indicate that the cognitive abilities measured by the scale become more general with age and the level of schooling. (RJM)

Three different applications of the testlet concept are presented, and the psychometric models most suitable for each application are described. Difficulties that testlets can help overcome include (1) context effects; (2) item ordering; and (3) content balancing. Implications for test construction are discussed. (SLD)

Issues in measuring language proficiency of monolingual and bilingual persons are discussed. Psychometric procedures in developing both English- and Spanish-language proficiency instruments are illustrated through development of the New York City Language Assessment Battery, an assessment of proficiency in both languages used to screen eligibility…

Reports on two studies designed to develop and evaluate the Automatic Thoughts Questionnaire-Positive (ATQ-P), a measure of positive automatic thinking that is complementary to the ATQ, a measure of negative thinking in psychopathology. Describes results suggesting that ATQ-P is reliable and valid measure of positive thinking. (Author/NB)

A probabilistic item response theory (IRT) model is developed for pair-comparison design in which the unfolding principle governing the choice process uses a discriminant process analogous to Thurstone's Law of Comparative Judgment. A simulation study demonstrates the feasibility of estimation, and two examples illustrate the implications for…

A procedure--based on item response theory--for testing the hypothesis of unidimensionality of the latent space is proposed. Use of the procedure is supported by an asymptotic theory and a Monte Carlo simulation study. The procedure tests for unidimensionality in test construction and/or compares two tests. (SLD)

Seventh-grade science students (n=22) wrote prompted essays, compare-contrast essays, and traditional end-of-chapter criterion-referenced tests. Results indicated that essay tests may be highly sensitive to instructional content and prompt design, and the validity of essays as measures of content learning relates more to goals of instruction than…

Administration of the Willoughby Personality Schedule-R to 27 adult male Yugoslav stutterers revealed internal consistency of the assessment. Factor analysis revealed three separate dimensions: social isolation, social confidence, and social sensitivity. Results are consistent with the contention that hypersensitivity to interpersonal stress is…

Investigated the adequacy of the Gesell School Readiness Screening Test (GSRST) to gauge 46 kindergartners' readiness. Found agreement between GSRST and teacher assessments of student readiness. Test-retest and interrater reliability were below acceptable levels, and lower than figures yielded by a quantitative scoring method. Concluded that GSRST…

The effects of controlling for individual differences in simple reaction time (RT) on the correlations of choice RT and discrimination RT with intelligence quotient were studied for 213 male college students. Simple RT was controlled by subtraction, partial correlation, and multiple correlation. (SLD)

Examined convergent and discriminant validity of eight widely used preschooler, toddler, and infant temperament questionnaires. There was surprisingly strong evidence for convergence among scales intended to measure similar concepts, with most convergent validity coefficients falling in the .50s, .60s, and .70s. (SH)

The monograph by D. Rogosa and G. Ghandour represents a body of cohesive and comprehensive research that can be the basis of a new measurement theory combining features of generalizability theory and strong true-score theory. Principles, approaches, arguments, and conclusions are reviewed; and critical comments are offered. (SLD)

Issues raised with the statistical models developed are discussed point by point, restating the emphasis on finite observation time, and reiterating the criticism of traditional psychometric methods. It is noted that the language and technical formulation of psychometrics can be extremely awkward in dealing with biased estimates. (SLD)

The Children's Sex Role Inventory was tested on third, fourth, sixth, and seventh graders. Reliability was established through internal consistency of femininity and masculinity scales and stable test-retest reliabilities. Validity of the scales was evident in gender differences on both scales. (BC)