The proposed method has the advantage of being a rational procedure which reduces the larger set of variables'' down to a desired subset of predictor variables. The selected subset, then, can be coded for a full regression run if it contains multiple level category variables among those selected. (Author)

Discusses the techniques used in one empirical study of the economies of scale in school districts, and demonstrates that empirical findings based on techniques of this type should not be considered to justify expenditure per student differentials or consolidations to reduce per pupil costs, based on economies of scale. (JF)

A printout of the program and sample output will be provided by the authors upon request. (Authors/CB)

Bounds for the multiple correlation of common factors with the items which comprise those factors are developed. It is then shown that under broad, but not completely general, conditions, the circumstances under which an infinite item domain does or does not perfectly determine selected subsets of its common factors. (Author/JKS)

Recent theoretical analyses of the concept of suppression are identified and discussed. A generalized definition of suppression is presented and the conditions for suppressor structures in the context of the General Linear Model are derived. (Author)

A method is presented for the construction of an artificial data set which will illustrate the behavior of the traditional, the negative, and the reciprocal suppressor variable in multiple regression analysis. It extends the method of Dayton (1972) and includes the previously reciprocal suppression defined by Conger (1974). (Author)

The perfunctory use of factor scores in conjunction with regression analysis is inappropriate for many purposes. It is suggested that factoring methods are most suitable for independent variable sets when some consideration has been given to the nature of the domain, which is implied by the predictors. (Author/BW)

For idealized item configurations, equal item weights are often virtually as good for a particular predictive purpose as the item weights that are theoretically optimal. What has not been clear, however, is what happens to the similarity when the item configuration's variance structure is complex. (Author/CTM)

The utility of least squares multiple regression in predicting new scores from previously established equations is considered. It is shown that in the absence of useful prior information, and when normality assumptions are not violated, least squares multiple regression weights are superior to alternatives recently presented in the literature.…

A new algorithm is used to test and describe the set of all possible solutions for any linear model of an empirical ordering derived from techniques such as additive conjoint measurement, unfolding theory, general Fechnerian scaling, and ordinal multiple regression. The algorithm is computationally faster and numerically superior to previous…

Using a degenerate multivariate normal model for the distribution of organismic variables, the form of least-squares regression analysis required to estimate a linear functional relationship between variables is derived. It is suggested that the two conventional regression lines may be considered to describe functional, not merely statistical,…

Problems in avoiding the singularity problem in analyzing matrices for optimal scaling are addressed. Conditions are given under which the stationary points and values of a ratio of quadratic forms in two singular matrices can be obtained by a series of simple matrix operations. (Author/JKS)

A convenient, two-stage general linear regression approach to analysis of variance is described for use in univariate or multivariate designs involving one repeated measurement factor and one or more independent classification factors. A brief illustrative example is provided. (Author)