This paper discusses the principles underlying discriminant analysis and constructs a simulated data set to illustrate its methods. Discriminant analysis is a multivariate technique for identifying the best combination of variables to maximally discriminate between groups. Discriminant functions are established on existing groups and used to…

A dichotomous dependent variable is used to determine a combination of variables that will predict group membership. Dichotomous variables are frequently encountered in multiple regression analysis. However, several textbooks question the appropriateness of using multiple regression analysis when analyzing dichotomous dependent variables. The…

A four-variable equation to predict administrative effectiveness of academic deans was derived from 17 variables by discriminant analysis. The study objective was to validate four indicators of administrator effectiveness. If the four variables were found to discriminate between effective and ineffective deans, search-screening committees could…

The objective of this study was to identify those cognitive characteristics that best differentiate the Navy's Basic Electricity and Electronics (BE/E) Preparatory School graduates and failures. Subjects included 207 BE/E students--172 graduates and 35 failures. Before these trainees had commenced BE/E School, they were administered six tests of…

Used discriminant analysis in an attempt to differentiate nonviolent and violent families as a function of variables said to be significant predictors of family violence in a decade review by Gelles. Results indicate that the predictor variables fail to account consistently for differences among the groups. (Author)

The recent development of strong statistical techniques has made accurate predictions of recidivism possible. To investigate the utility of discriminant analysis methodology in making predictions of recidivism in juvenile offenders, the court records of 271 male and female juvenile offenders, aged 12-16, were reviewed. A cross validation group…

The logit methodology provides a unique way of examining input-output relationships for social systems where the principal output of the analysis is a probability of some action or state. (Author)

In the 1988-89 school year, the Austin (Texas) Independent School District's Office of Research and Evaluation undertook a new dropout research project. Part of this initiative, termed Project GRAD, attempted to develop a statistical equation by which one could predict which students were likely to drop out. If reliable predictive information…

A linear classification rule (used with equal covariance matrices) was contrasted with a quadratic rule (used with unequal covariance matrices) for accuracy of internal and external classification. The comparisons were made for seven situations which resulted from combining three data conditions (equal and unequal covariance matrices, minimal and…

An alternative approach for program evaluation of small, specialized programs when comparison groups are not available is described. This application is illustrated by presenting the results of an analysis of data from Project Talent, a national manpower study, and discussing its application to the evaluation of a medical training program.…

This study examined career teachers' allocation of extra work time within a conceptual framework influencing time use. Distinct groups prefering instructional tasks; student, or parent, counseling; or committee activities were identifiable in a prediction model. Teachers selected professional time uses congruent with their perceived skills and…

Vocational identity is an important construct for physician career development. Physician vocational development has been grouped into three tasks (crystallization, specification, and implementation) pertaining to career choice and specialty choice (1) In defining the construct of vocational identity, it has been suggested that the relation…

Specific aim of the study was to determine the predictive accuracy of selected observations obtained during developmental periods on later developmental outcome. (Authors)

The extent to which successful completion of the Master of Business Administration (MBA) degree could be predicted from readily available admissions data was examined. Results of the discriminant analysis showed that the two criterion groups (graduates and nongraduates) could be differentiated. (Author/GK)

Describes a study that examined quantifiable characteristics of library schools to construct a model that predicts a judgment of perceived quality of library schools. Two perception studies conducted by Herbert White are discussed, statistical methods used are explained, and recommendations for further research are given. (34 references) (LRW)