A revised theorem is presented concerning uniqueness of minimum rank solutions in common factor analysis. (Author)

Whether to factor the image correlation matrix or to use a new model with an alpha factor analysis of it is mentioned, with particular reference to the determinacy problem. It is pointed out that the distribution of the images is sensibly multivariate normal, making for "better" factor analyses. (Author/CTM)

Two studies were conducted to compare responses to matrix questionnaires with those to standard questionnaires. In the first study, the matrix format produced significantly fewer returns. A second study comparing matrix and standard questionnaires of equal size found similar response rates but more incomplete returns for the matrix form.…

An approach to the analysis of multitrait-multimethod matrices is proposed in which improper solutions are ruled out and convergence is guaranteed. The approach, based on constrained variants of components analysis, provides component scores that can relate components to external variables. It is illustrated through simulated and empirical data.…

An algorithm is described for fitting the DEDICOM model (proposed by R. A. Harshman in 1978) for the analysis of asymmetric data matrices. The method modifies a procedure proposed by Y. Takane (1985) to provide guaranteed monotonic convergence. The algorithm is based on a technique known as majorization. (SLD)

Use of the bootstrap method to approximate the sampling variation of eigenvalues is explicated, and its usefulness is amplified by an illustration in conjunction with two commonly used factor criteria. These criteria are eigenvalues larger than one and the Scree test. (TJH)

A means of transforming multitrait-multimethod (MTMM) matrices into a classical multiple group factor analysis is outlined. A reanalysis of two numerical illustrations shows that the classical procedure yields results similar to those reached by D. N. Jackson's (1975) two-step procedure for analysis of MTMM matrices. (TJH)

In Varimax rotation, permutations and reflections can give rise to the phenomenon that certain pairs of columns are consistently skipped in the iterative process, causing Varimax to terminate at a nonstationary point. This skipping phenomenon is demonstrated, and how to prevent it is described. (SLD)

Monotonically convergent algorithms are described for maximizing sums of quotients of quadratic forms. Six (constrained) functions are investigated. The general formulation of the functions and the algorithms allow for application of the algorithms in various situations in multivariate analysis. (SLD)

To assess association between rows of proximity matrices, H. de Vries (1993) introduces weighted average and row-wise average variants for Pearson's product-moment correlation, Spearman's rank correlation, and Kendall's rank correlation. For all three, the absolute value of the first variant is greater than or equal to the second. (SLD)

Demonstrates that traditional exploratory factor analytic methods, when applied to correlation matrices, cannot be used to estimate unattenuated factor loadings. Presents a mathematical basis for the accurate estimation of such values when the disattenuated correlation matrix or the covariance matrix is used as input. Explains how the equations…

The difference in statistical power between the original Bonferroni and five modified Bonferroni procedures that control the overall Type I error rate is examined in the context of a correlation matrix where multiple null hypotheses are tested. Power differences of less than 0.05 were typically observed for the modified Bonferroni procedures. (SLD)

Univariate procedures proposed by M. Brown and A. Forsythe (1974) and the multivariate procedures from D. Nel and C. van der Merwe (1986) were generalized to form five new multivariate alternatives to one-way multivariate analysis of variance (MANOVA) for use when dispersion matrices are heteroscedastic. These alternatives are evaluated for Type I…

The geometric properties and Euclidean nature of dissimilarity coefficients defined on finite sets are discussed. Several particular transformations are presented that preserve Euclideanarity. The study of a one-parameter family adds to current knowledge of the metric and Euclidean structure of coefficients based on binary data. (SLD)

An iterative majorization algorithm is proposed for orthogonal congruence rotation that is guaranteed to converge from every starting point. In addition, the algorithm is easier to program than the algorithm proposed by F. B. Brokken, which is not guaranteed to converge. The derivation of the algorithm is traced in detail. (SLD)