The optimum weighting of variables to predict a dependent-criterion variable is an important problem in nearly all of the social and natural sciences. Although the predominant method, multiple regression analysis (MR), yields optimum weights for the sample at hand, these weights are not generally optimum in the population from which the sample was…

The contributions of several core variables to the white suicide rates in 24 Florida counties were examined. A prediction equation including age, crime rate, insanity, and alcoholism was found that accounted for 79 percent of the variation in the suicide rates across counties. (Author)

A study examined whether information about student approaches to making their course choices could have been used to identify those who subsequently changed or withdrew from their courses. Multivariate analysis indicated that combinations of the information could discriminate between students who persisted and those who withdrew. (Author/MLW)

Analyzes the impact of expenditures per year of schooling on earnings, based on data from a longitudinal study of 1,633 male American World War II veterans. (Available from North-Holland Publishing Company, P.O. Box 211, Amsterdam, the Netherlands; $13.50 annually, plus $4.00 postage and handling) (JG)

(See also TM 501 087, TM 501 089 and TM 501 090.)

Realizing the need to select success crtieria for use in a longitudinal vocational development study, the authors developed a model which depicted the relationships between several available success criteria. Hopefully, these hypothetical relationships would act as a framework for further research. (DS)

Johnson-Neyman, Potthoff, and Erlander and Gustavsson techniques for obtaining confidence regions for the difference between regression surfaces are compared. (DG)

Explores problems involved in the quantitative verification of independent variables in investigations of the effects on student outcomes of planned variations in instructional behavior. Specifically addresses (1) gathering of data through direct systematic observation, and (2) analysis of those data through the use of inferential statistics. (GC)

Describes a study conducted to determine the accuracy of the Cohort-Survival Method of Enrollment Forecasting, based on enrollment data collected over a ten-year period from a random sample of 42 Missouri school districts. Compares forecast accuracy with the enrollment stability and location of each of the districts. (JP)

Presents a method to improve client classification. Reviews clinical prediction models and statistical prediction issues. In classifying clients for remedial services, utility of the prediction scheme depends on gains accrued by its use over program base rates and relative cost. This assumes that differential treatments parallel diagnostic…

Multiple regression is used to discover interconnections between IQ and vocabulary test scores as one variable, and socioeconomic factors as the other. Results show total variance as explained by predictors is never more than eight per cent, indicating differences in IQ scores are not attributable to environmental factors. (RW)

This study with 45 institutionalized individuals with mental retardation and self injurious behavior (SIB) calculated conditional probability using sequential analysis techniques. It found that successive episodes of self-injury were sequentially dependent and this association was not related to frequency or rate of occurrence. The best predictor…

Describes how the State University of New York, using large databases and regression techniques, has developed several coordinated, comprehensive efforts to evaluate and project current and future enrollments. One requires decomposition of the student population into mutually exclusive subgroups. The other, superior, approach uses logistic…

This study investigated the effect of Systematic Desensitisation (SD) therapy on the reduction of test anxiety on some identified test anxious students. In addition, three secondary independent variables were studied along. These were entry test anxiety level, sex, and locus of control. A 2 x 2 x 2 way factorial design was employed. SD was found…