Discusses enrollment projection in terms of the general logic of statistical prediction. (Author)

A meta-analysis of outcomes from 32 studies investigating pretest effects was conducted. For all outcomes the average effect size was +.22, indicating an elevating effect of pretest on posttest. Duration of time between pre- and posttesting was also related to effect size. Researchers should continue to include pretest as a design variable.…

Depending on the nature of the predictor variable in the expectancy table, expectancy ranges may be computed by incorporating the standard error of estimate. The process of developing ranges is illustrated, and steps to be used in evaluating the quality and utility of expectancy data are outlined. (Author)

A critical reanalysis of Barrett, Caldwell, and Alexander's (1985) critique of dynamic criteria. Summarizes and questions Barrett, et al.'s three definitions of dynamic criteria and their conclusion that reported temporal changes in criteria could be explained by methodological artifacts. A greater focus on dynamic criteria as constructs is…

Responds to Austin, Humphreys, and Hulin's (1989) critique of Barrett, Caldwell, and Alexander, suggesting that the burden of proof still rests on the advocates of the concept of dynamic criteria, and that empirical support is lacking for the existence of dynamic criteria as a simplex. Contrary evidence from educational, organizations, and…

Seven methods for measuring and comparing value added in higher education are considered; six are index methods (all found unsatisfactory for lack of empirical support) and a seventh is proposed which calculates value added as the difference between the outcomes achieved and those predicted from national (United Kingdom) data. The advantages of a…

Examines difficulties with citation analysis as it is used to study citation frequency, usually for the evaluation of scientists, publications, or institutions. Topics addressed include selection of a control set of papers, comparisons of different types of papers (e.g., methodological or theoretical), effects of independent variables, and use of…

Nonlinear relationships and latent variable assumptions can lead to serious specification errors in structural models. A quadratic relationship, described by a linear structural model with a latent variable, is shown to have less predictive validity than a simple manifest variable regression model. Advocates the use of simpler preliminary…

Application of the statistical techniques of survival analysis and credit scoring to private education loans extended to law students found a pronounced seasoning effect for such loans and the robust predictive power of credit bureau scoring of borrowers. Other predictors of default included school-of-attendance, school's geographic location, and…

The aim of this work was to determine, in terms of Type I and Type II error rates, the risks of applying various statistical procedures for evaluating differential item functioning. To this end, the authors carried out a simulation study in which the Mantel-Haenszel and SIBTEST procedures were applied in conjunction. The variables manipulated were…

Objective: The purpose of this study was to (a) describe the timing of maltreatment recurrence and (b) measure associations between child demographics and characteristics of initial reports with recurrent maltreatment. Method: Using administrative data from the Florida Department of Children and Families, case histories of 189,375 children with an…

This study incorporated institutional characteristics (e.g., Carnegie type, selectivity) and resource allocations (e.g., instructional expenditures, student affairs expenditures) into a statistical model to predict undergraduate graduation rates. Instructional expenditures, library expenditures, and a number of institutional classification…

When a simple random sample of size n is employed to establish a classification rule for prediction of a polytomous variable by an independent variable, the best achievable rate of misclassification is higher than the corresponding best achievable rate if the conditional probability distribution is known for the predicted variable given the…

This book provides a clear introduction to widely used topics in bivariate and multivariate statistics, including multiple regression, discriminant analysis, MANOVA, factor analysis, and binary logistic regression. The approach is applied and does not require formal mathematics; equations are accompanied by verbal explanations. Students are asked…