This paper considers the model of school effectiveness (SE) currently dominant in research, policy and practice in England (although the concerns it raises are international). It shows, principally through consideration of initial and propagated error, that SE results cannot be relied upon. By considering the residual difference between the…

An index that reflects the accuracy of selection associated with a predictive validity of "r" is presented. Based on Sheppard's thoerem on median dichotomies, it is a measure of improvement over chance assignment to "accept" (or "reject"). Because the index is a measure of the accuracy of this assignment, rather than…

Empirical Bayes methods are shown to provide a practical alternative to standard least squares methods in fitting high dimensional models to sparse data. An example concerning prediction bias in educational testing is presented as an illustration. (Author)

Compared three statistical procedures to determine their ability to predict delinquents' return to juvenile prison after first release. Logit analysis, predictive attribute analysis, and a Burgess procedure were tested. No significant differences were found between statistical procedures in prediction. (Author/NB)

A new approach to partialling components is used. Like conventional partialling, this approach orthogonalizes variables by partitioning the scores or observations. Unlike conventional partialling, it yields a common component and two unique components. (Author/GDC)

New tests for comparing the strength of association between a variable and each of two potential predictor variables are proposed and compared to an existing test in a simulation study. Recommendations for use are made. (Author/JKS)

Three measures of person-fit (the extent to which an examinee's response pattern on a multiple-choice test is consistent with his ability as estimated by total score) were computed for students taking classroom tests under 12 different instructors at a comprehensive university. Supplementary questions on each test inquired concerning students'…

The study involved the use of a structured job analysis instrument called the Position Analysis Questionnaire (PAQ) as the direct basis for the establishment of the job component validity of aptitude tests (that is, a procedure for estimating the aptitude requirements for jobs strictly on the basis of job analysis data). The sample of jobs used…

An empirical method (PRESS) for examining and contrasting the cross-validated prediction accuracies of some popular algorithms for weighting predictor variables was advanced and examined. The sample specific PRESS method was suggested as most appropriate when selecting among several alternative weighting algorithms to achieve maximum…

Generally, this paper aims to: (1) provide clarification, quantification, and some mathematical analysis to the statistical problem of restricted range in a college admissions situation; and (2) discuss various questions related to the problem of selection strategies. (Author/PN)

An empirical study of statistical overkill investigated the generalizability of multiple regression equations as a function of the subject/variable ratio. Data from various-sized groups of rehabilitation clients were used to develop the equations. Findings showed that equations developed on samples with less than a 10 to 1 ratio failed to…

The purpose of this study was to generate descriptive statistical estimates regarding the expected proportion of occurrence of each of the PROANA 5 (Process Analysis) variables (line usage, clique group, detrimental clique group, leadership, and dominance) in small group communication. A second purpose was to determine the expected pattern of…

The Minnesota Child Development Inventory was used to obtain parent observations on 59 children before the start of the kindergarten year. Results indicated that the parent report on a number of variables from the MCDI correlated highly with postkindergarten success in reading. (Author)

Rules are given for estimating accuracy of predictions based on a multiple regression equation. Formulas for moments of distribution and other parameters are noted. The approximate inflation in mean absolute error due to estimating the regression coefficients is a function of the base sample size and number of predictors. (DWH)