The important and sometimes difficult-to-grasp concept of regression suppressor variable effects is explored. An inquiry into the phenomenon of suppressor effects is accomplished via a synthesis of the existing literature and the use of a small heuristic data set to improve the accessibility of the concept. Implications for researchers are also…

Interpretation of emergent variables on the basis of structure coefficients (zero order correlations between original and emergent variables) is potentially very misleading and should be avoided in favor of interpretation on the basis of scoring coefficients. This is most apparent in multiple regression analysis and its special case, two-group…

The uses and restrictions of commonality analysis are described. Commonality analysis has been increasingly used as a method to examine the relative importance of independent variables, through the partitioning of variance among the variables of the regression equation into unique and common components. The effects of all other independent…

A review of cross-validation shrinkage formulas is presented which focuses on the theoretical and practical problems in the use of various formulas. Practical guidelines for use of both formulas and empirical cross-validation are provided. A comparison of results using these formulas in a range of situations is then presented. The result of these…

A Monte Carlo study was performed to test under what conditions and to what degree various alternatives would be superior to multiple linear regression (MLR). The criteria used was the mean squared error of prediction of individual scores and the mean squared error of estimation of the regression weights. Populations were simulated containing…

An empirical method called Predicted Error Sum of Squares (PRESS) is advanced and studied. This method is used to examine the cross-validated prediction accuracies of some popular algorithms for weighted predictor variables. The weighting methods that were considered were ordinary least squares, ridge regression, regression on principal…

Actual data sets were used to illustrate how substantially different conclusions and implications can be drawn from alternate multiple regressions predicting academic achievement from the same set of variables measuring student background. Variables assessing students' socioeconomic status and geographic mobility, used to predict reading and math…

Several advantages to the use of factor scores as independent variables in a multiple regression equation were found. To help select the most desirable type of factor score on which to calculate a regression equation, computer-based Monte Carlo methods were used to compare the predictive accuracy upon replication of regression of five…

If an effective school is defined as a school that causes student improvement on a number of important educational outcomes, the problem of identifying effective schools becomes one of establishing legitimate predictions of student performance and comparing those predictions to actual student or school outcomes. In attempting to identify effective…

The Tutorial Assistance Program (TAP) of the University of California (Irvine) is described and a new method of evaluation is illustrated through an analysis of the performance of students in six large introductory classes. This approach to evaluation starts with a multiple regression equation for predicting course grades of those not in tutoring…

The former HEW National Strategy for Youth Development Model was a community-based planning and procedural tool designed to enhance positive youth development and prevent delinquency through a process of youth needs assessment, development of targeted programs, and program impact evaluation. A series of 12 Impact Scales most directly reflect the…

A counseling program for senior medical school students is described. Each student who wishes to participate is provided with a prediction of his or her Federal Licensing Examination (FLEX) score, as well as the probability of passing the FLEX in Arkansas. Predictions were computed by performing regression analyses to obtain equations relating…

The accuracy and variability of 4 cross-validation procedures and 18 formulas were compared concerning their ability to estimate the population multiple correlation and the validity of the sample regression equation in the population. The investigation included two types of regression, multiple and stepwise; three sample sizes, N = 30, 60, 120;…

An investigation was undertaken of the intercorrelations among residuals obtained by applying regression techniques under two conditions: (1) mean sixth-grade Metropolitan Achievement Test reading scores predicted by mean second-grade Stanford Achievement Test reading scores, and (2) mean sixth-grade reading scores predicted by mean second-grade…

This paper examines the multivariate multiple regression model and explores its applicability to communication research. The first section discusses partitioning of a data matrix, as a heuristic device for distinguishing among alternative regression models. Section two examines various aspects of univariate multiple regression, including the form…