Describes the method of discriminant analysis, including the concept of discriminant function, discriminant score, group centroid, and discriminant weights and loadings. Discusses methods for testing the statistical significance of a function, methods of using the function in classification, and the concept of rotating functions. Illustrates the…

Provides an example to illustrate the clustering approach. Discusses the variety of approaches in clustering; choice of cluster analytic techniques; the steps in cluster analysis; the data features such as level, shape, and scatter, that affect cluster results; alternate clustering methods and their relative effectiveness; and applications of…

The study attempted to determine if there are differences in the perception of male and female managers toward communication barriers. Data were collected from 156 managers and analyzed using a multivariate analysis of variance (sex and salary level). Results showed significant differences in perceptions among male and female managers. (Author/CH)

Provided is a description of three methods for testing certain types of a priori hypotheses about differences among covariance matrices. Briefly outlined are procedures for using two computer programs, COFAMM and LISREL, for testing such hypotheses. Also provided are examples of application of the methods to a meaningful data set. (Author/BW)

Purpose: This study represents the first reporting of aggregate data of a longitudinal study designed to identify correlations between medical student personality traits and type of residency, later selected. It is a multisite project involving four US medical schools over a period of nearly ten years. The current study sought to test the…

This exploratory study examined the level of involvement of Temporary Assistance for Needy Families (TANF) applicants in Milwaukee County, Wisconsin with the child welfare system both before and after their application for TANF assistance and inclusion in the study. The study found a high level of involvement of TANF applicants with child…

The purpose of this study was to examine the effect of instrument completion instructions on univariate and multivariate distributional characteristics and relationships among variables. Instructions allowed free-choice allotment of ratings (unforced instructions) or requested the subject to assign a certain number of ratings to either the highest…

The longitudinal factor analysis" model, which uniquely resolves factors from two occasions of data representing the same persons measured on the same test battery, is shown to be derivable by application of canonical correlation procedures to factor scores. (Author)

Structural equation modeling is applied in conjunction with constrained monotone distance analysis. These alternative methods are used in an evaluation of a social-psychological model derived from Likert's theory of organizational behavior. (Author/JKS)

Interpretations regarding the effects of exogenous and endogenous variables on endogenous variables in linear structural equation systems depend upon the convergence of a matrix power series. The test for convergence developed by Joreskog and Sorbom is shown to be only sufficient, not necessary and sufficient. (Author/JKS)

Multivariate generalizability deals with the interpretation of a profile or composite of measurements. Using data from the Beginning Teacher Evaluation Study to illustrate the differing interpretations of viewing test data from universe and multivariate perspectives, this chapter concludes with computer programs that the reader can implement to…

Many models have been proposed for examining factors from several batteries of tests. A model for such an analysis is presented which allows for maintaining the distinction among batteries. A discussion of the computational procedures is given, and examples are provided. (Author/JKS)

In a secondary analysis of the Abrams and Siegel evaluation of the Transcendental Meditation program at Folsom prison, experimental groups fared better than control groups, although the treatment explains only a small proportion of the variance. (Author)

Examines the prevalence of inflated Type I error in counseling research and recommends wider use of multivariate statistics to correct the problem. Type I error becomes inflated beyond acceptable levels when researchers perform individual univariate statistics on each of several dependent variables within a single project. (Author)

Examines the recommendations of H. Keselman, K. Carriere, and L. Lix (1993) regarding choice of sample size for obtaining robust tests of the repeated measures main and interaction hypotheses in a one Between-Subjects by one Within- Subjects design with a Welch-James type multivariate test when covariance matrices are heterogeneous. (SLD)