Systematic procedures are outlined for testing the assumption made on the dependent variables in a variety of statistical techniques. Specifically, procedures are outlined for testing the assumption that the dependent variables are measuring the same constructs in the same metrics with equivalent reliabilities across all subgroups. (Author/JKS)

A series of multiple regression analyses was used to investigate a salary equity policy in a statewide system of institutions of higher education. Faculty rank, number of publications, and teaching effectiveness were among the variables examined. (JKS)

Discusses a path analysis of the attitudes of 800 black male and female Americans in Baton Rouge, Louisiana. Their attitude toward their skin color is analyzed as a function of their personal orientation toward political and social separation, whereas both their ratings and their orientation are analyzed as a function of their education, age and…

Evaluation Research Society members (n=160) assessed the attributes of research that produce credibility. The study focused on the acceptability of no-difference findings. Randomization, statistical power, number of measures reported, and equivalent groups were tested to determine their influence on acceptability of both no-difference and…

A 1984 survey of dental schools was compared with a 1979 survey showing an increase in the teaching of geriatric dentistry. Factors associated with the establishment of a course were that the school was located in a state with a large geriatric population and financial assistance for patients was available. (Author/MLW)

The development, reliability, and validity of a practical examination to evaluate student attainment of course objectives in an externship program are described. Examination content was determined by surveying preceptors and suggestions from practicing pharmacists; the reliability was assessed by interrater agreement and internal consistency…

This study used multiple regression analysis to relate computer user satisfaction to communication monitor (CM) variables. Results indicate the variables of user expectations, manufacturers, and vendors are most significant in affecting overall satisfaction, whereas number of systems represented and not using communication monitors have least…

Multiple linear regression is a versatile model for encompassing analysis of variance, analysis of covariance, and aptitude-by-treatment interaction designs. The questions of how to teach the coding of levels of a qualitative variable is addressed in this paper. (Author/LMO)

This study was undertaken to determine if adolescent social disaffection with school and family not only would be a significant predictor of cigarette use but also would explain a significant amount of the association with friends who smoke. Results are presented. (Author/MT)

The author examined the prevalence of multiple operational definitions of outcome constructs and an estimate of the incidence of Type I error rates when univariate procedures were applied to multiple variables in educational psychology. Multiple operational definitions of constructs were advocated and wider use of multivariate analysis was…

A multiple regression approach was applied to data to measure the following by geographic municipality: the ratio of high school graduates enrolled in a given institution to that institution's entering freshman enrollment, eligible population, academic ability, educational attainment, income level, wage rate, unemployment rate, cost of attendance,…

The statistical and institutional influences on the prediction of first-year college grades were examined using data from College Board validity studies and the College Handbook. The criterion was the size of the multiple correlation between academic predictors and first-year college grades. (Author/MLW)

Uses multiple regression analysis to demonstrate that the earnings of illegal aliens rise with schooling and labor market experience, but experience in the U.S. is more important than in the country of origin. Shows that Mexican illegal aliens earn about 30 percent less than Canadian/European illegal aliens. (Author/RDN)

Proposes a quadratic programming, least squares solution to Carroll's weighted unfolding model with nonnegativity constraints imposed on weights. It can be used to test various hypotheses about the weighted unfolding model with or without constraints. (RC)

An attempt was made to identify student characteristics which might lead to greater achievement for an individualized treatment. (Editor)