A brief historical background of discriminant analysis is given, with a description of the variety of roles that discriminant analysis can perform. Focus is on the classification role of discriminant analysis and how it can be performed by using Fisher's classification functions or the canonical discriminant functions. A small hypothetical data…

Conventional canonical methods distinguish between the two variable sets being analyzed, but the methods do not attempt to optimize the variance from a given variable set that will be contained in the final solution. In this respect canonical methods are said the be "symmetric." This paper proposes two non-symmetric, canonical-like…

A particular strategy for investigating effects resulting from a multivariate analysis of variance (MANOVA) is proposed. The strategy involves multiple two-group multivariate analyses. The two groups result from considering multivariate pairwise group contrasts or multivariate complex group contrasts. Assuming a given two-group analysis yields…

The purposes of this study are: (1) to demonstrate the superiority of simple ridge regression over ordinary least squares regression through theoretical argument and empirical example; (2) to modify ridge regression through use of the variance normalization criterion; and (3) to demonstrate the superiority of simple ridge regression based on the…

Multivariate analysis techniques employ various methods of optimally weighting variables to form composites. The interpretation of these composites in subsequent analyses is rarely straightforward, fraught with difficulties based upon the statistical properites of the estimated weights. This paper synthesizes interpretive guidelines for four…

In their Monte Carlo study of canonical analysis, Barcikowski and Stevens evaluated the relative stability of canonical weights and loadings. This paper identifies some weaknesses in their study, suggests directions for future research in this area, and discusses interpretation of canonical analysis both in development and in cross-validation. For…

This article is a rejoinder to TM 502 249. Each of Thorndike's comments are examined. A possible solution to the large number of subjects necessary for stable weights and variate-variable correlations using ridge regression procedures is suggested. (RC)

Presents and illustrates structural equation modeling (multivariate analysis with latent variables, also called causal modeling or covariance structure analysis), discussing issues and problems related to the use of this methodology, possible applications of structural equation modeling to counseling psychology research, and resources for further…

A new approach to partialling components is used. Like conventional partialling, this approach orthogonalizes variables by partitioning the scores or observations. Unlike conventional partialling, it yields a common component and two unique components. (Author/GDC)

Employs latent partition analysis (a multivariate technique) to reveal pre/postcognitive structure of freshman engineering students (N=70) taking general chemistry. Similarities and dissimilarities among high and low scorers are discussed. Arguments for use of this statistical techniques are presented. (DH)

Examined data from a questionnaire concerning people with chronic health, emotional, mental, physical, and sensory impairments, and four respondent demographic and experiential characteristics to determine if 150 human service providers endorsed the premise that components of society disable people who are impaired. Results confirmed that…

This paper presents a discussion of various statistical concepts and techniques in light of two propositions. The first is that researchers need to select analytical techniques that prevent them from committing Type VI errors, which are inconsistencies between the research question and the statistical analysis. The second is that many statistical…

Methods for comparing the suitability of alternative models for covariance matrices are examined. A cross-validation procedure is suggested and its properties examined. A series of examples using longitudinal data are examined. (Author/JKS)

Theta is a statistic which measures the degree to which a designated pattern successfully partitions a matrix of pre- and post-treatment ratings into regions typical of each of two treatments. In this paper, theta is extended to multivariate and multigroup cases. (Author/BW)

The available methods for analyzing and interpreting data with multivariate analysis of variance are reviewed, and guidelines for their use are presented. Causal models that underlie the various methods are presented to facilitate the use and understanding of the methods. (Author/PN)