In studying college effects, an input-output model is commonly used in which student input is controlled by using regression analysis to compute an "expected" output. The part correlation of the college environment variable and the output with input variance removed only from the output is interpreted as a measure of the college effect. However,…

A method for measuring status inconsistency that permits a comprehensive test of inconsistency theory without the complicated statistical problems that have plagued previous researchers is presented. (Author/AM)

Comments on the uses of statistical analysis in social sciences within the context of Freedman's "As Other's See Us: A Case Study in Path Analysis." Points out that there is an unacknowledged gap between statistical principles and the data analysis that social scientists use. (RB)

Examines D. A. Freedman's criticism of path analysis, agreeing with Freedman's criticism of its application to nonexperimental data in the social sciences. Argues that Freedman's overall conclusions, however, are too pessimistic. (RB)

The development of a nonparametric K-sample test for equality of slopes using Puri's generalized L statistic is presented. The test is recommended when the assumptions underlying the parametric model are violated. This procedure replaces original data with either ranks (for data with heavy tails) or normal scores (for data with light tails).…

Considers the impact of empirical social science methodology and data analysis techniques on the process of historical analysis and its product, generalizations about the past. Uses political preference and voting information as a vehicle to illustrate the differences in historical conclusions reached by Lee Benson and J. Morgan Kousser. (JDH)

An analytic procedure is presented for testing the homogeneity of unstandardized regression weight vectors when the vectors are correlated. The basic design involves repeated measurements on a dependent variable and a set of independent variables. The method is illustrated with a study of perceived leader behavior. (Author/BW)

The paper examines three models still considered useful in identifying achievement-aptitude discrepancies: the prediction model, true score regression model, and prescore partialling model. Data are cited to provide support for the regression model as the simplest to use and most efficient statistically. (Author/CL)

This report is meant to help juvenile courts develop practical risk-screening instruments. Courts increasingly are using some method of risk classification to assist in assignment of youth to differential service/supervision programs. A comparison of commonly used or advocated risk classification methods may provide courts with guidance in…

This paper presents teaching strategies and examples developed for a two-semester sequence in quantitative problem solving, specifically outlining a non-calculus derivation of linear regression formulas supported by the graphical display of the TI-83 calculator to visualize the minimization of the sum-squared vertical distances. The paper…

Two prominent themes often emerge from evaluations of education and social program evaluations: (1) the interventions being studied serve diverse populations, even if they are intended to target groups with particular characteristics; and (2) the interventions' impacts vary across groups within the population being served. Thus, most evaluations…

Maximum likelihood and least-squares estimates of parameters from the logistic regression model are derived from an iteratively reweighted linear regression algorithm. Empirical Bayes estimates are derived using an m-group regression model to regress the within-group estimates toward common values. The m-group regression model assumes that the…

When multiple regression is used to develop a prediction model, sample size must be large enough to ensure stable coefficients. If sample size is inadequate, the model may not predict well in future samples. Unfortunately, there are problems and contradictions among the various sample size methods in regression. For example, how does one reconcile…

The analysis of interaction effects in multiple regression has received considerable attention in recent years, but problems with the valid identification of moderating variables have been noted by researchers. G. McClelland and C. Judd (1993), in their discussion of the statistical difficulties of detecting interactions and moderating effects,…

This paper presents results from a comparison of the multiple regression (MR) approach to examining faculty salary equity (with clusters for the various disciplines) and hierarchical linear modeling (HLM) for the same problem. The comparison was done in two steps. First, a practical example of applying both techniques, using empirical data, is…