The method of unweighted means in the multivariate analysis of variance with unequal sample sizes was investigated. By approximating the distribution of the hypothesis sums-of-squares-and-cross-products with a Wishart distribution, multivariate test statistics were derived. Monte Carlo methods and a numerical example illustrate the technique.…

Comments on Kerwin et al.'s article on Covariance Structure analysis (LISREL). Concerns include assumptions about requirements for causal inferences, psychometric properties of measurement scales, validity of the indicators of each latent variable, completeness of the structural model, linearity of the latent variables, and the joint distribution…

Variance stabilizing transformations yield statistics whose standard errors are only influenced by the number of observations on which they are based. A solution that can be extended to inference on all of these parameters is presented and illustrated via three examples. (TJH)

A review of model-selection criteria is presented, suggesting their similarities. Some problems treated by hypothesis tests may be more expeditiously treated by the application of model-selection criteria. Multivariate analysis, cluster analysis, and factor analysis are considered. (Author/GDC)

A multivariate model is proposed for assessing a severe discrepancy between intellectual ability and actual achievement in learning disabled (LD) children. Formulas for computing universe difference score variance, the standard error of the difference score, and its generalizability coefficient are given. (Author)

The basic notion of variability is generalized from a univariate context to a multivariate context using two matrix functions, a determinant, and a trace, yielding a number of alternative multivariate indices of shared variation. Some problems in the interpretation of tests of multivariate hypotheses are reviewed. (Author/BW)

Because ignoring the missing data in an evaluation may lead to results that are questionable, this study investigated the effects of use of four missing data handling techniques on a survey instrument. A questionnaire containing 35 5-point Likert-style questions was completed by 384 respondents. Of these, 166 (43%) questionnaires contained 1 or…

The AIDS epidemic is making orphans out of many African children and threatens to reverse hard-won gains in raising school enrollments. The average gross primary enrollment ration (GPER) the number of children enrolled as a percent of the total number of children of school age was only 77% for Sub-Saharan Africa in 1996. The countries are hard-hit…

This study investigated the attitudes toward statistics of graduate students who studied advanced statistics in a course in which the focus of instruction was the use of a computer program in class. The use of the program made it possible to provide an individualized, self-paced, student-centered, and activity-based course. The three sections…

When measuring the same variables on different occasions, two procedures for canonical analysis with stationary compositing weights are developed. Both methods are extended to allow for cohort sequential designs and a numerical illustration is presented. (Author/JKS)

Calls attention to limitations and dangers in routine application of multivariate analysis of variance (MANOVA), describes some alternative procedures, and laments the necessarily pervasive character of the statistical problem. (Author)

A diagram is used to aid discussion of how several of the frequently used multivariate statistical techniques are interrelated. All of those discussed can be regarded as special cases of canonical correlation. (Author)

Two studies involving a total of 837 intermediate-grade students found that multivariate analyses of self-concept inventories reveal dimensions uncovered by univariate methods. (NRB)

A multivariate post hoc procedure (the Roy-Bose procedure) which allows for the construction of an infinite number of confidence intervals or probability statements concerning the p variables, all of which hold at a 100(1-a) percent level of confidence, is demonstrated and compared to other procedures. (JD)