The internal consistency-reliability and factorial validity of the Substitutes for Leadership Questionnaire were studied in an educational setting, using data from 450 elementary school teachers at 47 schools in Oregon and Washington. Results support S. Kerr's (1977) formulation on leadership substitutes for 11 of the original 13 factors. (TJH)

Type I error rates and power were estimated for 10 tests of variance equality under various combinations of the following factors: similar and dissimilar distributional forms, equal and unequal means, and equal and unequal sample sizes. (TJH)

Configurational frequency analysis is suggested as a technique for longitudinal research in educational psychology. Testing for types of change of ratings (grades) and for ratings of change is illustrated by data from three courses in statistics from a cohort of 128 students at Marburg University in West Germany. (TJH)

For 271 middle-class tenth and eleventh graders, exploratory and confirmatory factor analyses were conducted on a correlation matrices of 90 items and 18 subtests, each containing five items. The Study Attitudes and Methods Survey was used. Via a multidimensional affective measure with homogeneous scales, both techniques yielded a high degree of…

Two studies assessed the kinesthetic aftereffect using a wide inducing block with the Petrie measurement procedure and a traditional procedure. The subjects included 76 male and 101 female undergraduates. Aftereffect scores were generally correlated as predicted. (TJH)

Using the Gini-Light-Margolin concept of "partioning" variance for qualitative data, correspondences are established between various kappa statistics and intraclass correlation coefficients under general conditions (multiple raters and polychotomous category systems). A measure of marginal symmetry for multiple ratings. (Author/TJH)

Analysis of the factor structure of rankings and ratings of three sets of values illustrates how counselors use them in working with adolescents. Data were analyzed from 600 interviews with eleventh graders. The analyses of gender-related differences give counselors perspectives from which to explore the values students consider important in…

This article examines the simple difference score (Y-X) using different correlational analyses. Three classes of correlational analyses considered involve the correlation of initial score (X) with change (Y-X); the correlation of another variable (A) with change (Y-X); and the correlation of one change score (B-A) with another (Y-X). (TJH)

The effects of statistical and cognitive difficulty ordering of test items, gender, and explicit labeling of item type on college students' test performance were assessed. A total of 137 male and 265 female undergraduates were administered two 40-item multiple choice tests. Results indicate significant effects for gender and use of labels, but…

One English and two Spanish 24-word lists were administered as vocabulary tests to 80 English-speaking and 80 Spanish-speaking (Mexican and Puerto Rican) eighth graders, respectively. Results provide insights into the frequency of use as a valid measure of word difficulty in bilingual vocabulary test construction and translation. (TJH)

The power to detect main and interaction effects in a factorial design was determined when the Bonferroni method was used to control the overall rate of Type I error. For sample sizes typical of educational research, the power of this procedure was considerably less than that of recommended standards. (TJH)

The Spearman-Brown (S-B) formula for correction of the split-half coefficient of reliability is discussed as a conceptual precursor of modern formulations of internal-consistency reliability. Derived from the principal components of the product moment coefficient, an alternative S-B formulation facilitates an understanding of internal…

A procedure proposed by H. F. Kaiser (1968) for averaging coefficients using the first eigenvalue of an intercorrelation matrix was studied via Monte Carlo methods. The study also assessed a modification of the Kaiser procedure and the use of Fisher's "z." Applications to sample size effects are discussed. (TJH)

LISREL program was used to examine measurement model assumptions and to assess reliability of Coopersmith Self-Esteem Inventory for Children, Form B. Data on 722 third-sixth graders from over 70 schools in large urban school district were used. LISREL program assessed (1) nature of basic measurement model for scale, (2) scale invariance across…

In the process of fitting a quantitative synthesis model, the assumption of homogeneous effect size variation is assessed via omnibus test statistics. Graphical representations of data on techniques for teaching composition skills are used to help determine the extent to which sample estimates deviate from modeled population estimates. (TJH)