The purpose of this paper is to examine the validity of regression estimates when skewed dichotomous scales are used as independent variables. When Pearson product-moment correlations are used to measure zero-order associations involving dichotomous variables, the resulting coefficients underestimate the true associations. As a result, using…

An example demonstrates a large number of important concepts in correlation and regression with numbers sufficiently small that the mathematics can be reasonably handled by students. (Author/KM)

This National Institute of Education report discusses problems of data aggregation and disaggregation which arise whenever the unit on which variables are measured is different from the unit of analytical, conceptual or policy-related interest. For example, researchers may want to know the effects of family background, of peer groups, or of school…

A brief introduction is presented on how multiple regression and linear model techniques can handle data analysis situations that most educators and psychologists think of as appropriate for analysis of variance. (Author/BJG)

The major portion of this article considered the multiple regression model, used for industrial prediction situations, and fourteen separate episodes the author discussed in trying to make that model work. (Author/RK)

The way newspaper quality related to newspaper circulation was examined by asking journalism professionals to list the four best and the four worst daily newspapers with under 200,000 circulation in their own states. Returns were counted in only those states where two or more judges returned ballots. A total of 79 newspapers was rated superior by…

The Automatic Interaction Detector (AID) is discussed as to its usefulness in multiple regression analysis. The algorithm of AID-4 is a reversal of the model building process; it starts with the ultimate restricted model, namely, the whole group as a unit. By a unique splitting process maximizing the between sum of squares for the categories of…

Aggregation, or grouping, is a statistical procedure through which all members of a study within a specified range of scores (usually observed scores) are assigned a common or "group" score (for example, the group mean). The various social science methodology literatures agree on the costs of grouping: not only does one always lose…

This short article presents some preliminary findings of a study which explores the effects on the statistical findings of using alternative forms for specifying Test of Understanding in College Economics (TUCE) scores as the dependent variable in the regression model. (Author/RM)

It is demonstrated here that standardized regression coefficients greater than one can legitimately occur. Furthermore, the relationship between the occurrence of such coefficients and the extent of multicollinearity present among the set of predictor variables in an equation is examined. Comments on the interpretation of these coefficients are…

Thirty-two personnel specialists evaluated written performance descriptions of four secretaries. The fourth secretary was a target, whose age and job experience were experimentally manipulated in a 2 X 2 factorial design. Participants above (below) the median age provided lower (higher) evaluations to the older target than to the younger.…

A simple roof is presented: that the squared multiple correlation of a variable with the remaining variables in the set of variables is a lower bound to the communality of that variable. (Author/JKS)

The use of interaction and non-linear terms in multiple regression poses problems for determining parsimonious models. Several computer programs for using these terms are discussed. (JKS)

Data analyses are presented investigating the relationship of high school grade point average and first year university grade point average. A variety of analyses are presented; the results imply that high school attended is a better predictor of university performance for poorer students than for better students. (Author/JKS)