Results of using multimethod factor analysis and exploratory factor analysis for the analysis of three multitrait-multimethod matrices are compared. Results suggest that the two methods can give quite different impressions of discriminant validity. In the examples considered, the former procedure tends to support discrimination while the latter…

This article compares two methods for analyzing small sets of repeated measures data under normal and non-normal heteroscedastic conditions: a mixed model approach with the Kenward-Roger correction and a multivariate extension of the modified Brown-Forsythe (BF) test. These procedures differ in their assumptions about the covariance structure of…

Nonlinear factor analysis is a tool commonly used by measurement specialists to identify both the presence and nature of multidimensionality in a set of test items, an important issue given that standard Item Response Theory models assume a unidimensional latent structure. Results from most factor-analytic algorithms include loading matrices,…

Six major problems confronting attempts to use nonmetric multidimensional scaling to represent structures underlying similarity data are identified and the author's prospects for over-coming each of these problems are presented. (RC)

Three approaches to the graphic representation of similarity and dissimilarity matrices are compared and contrasted. Specifically, Kruskal's multidimensional scaling, Johnson's hierarchical clustering, and Waern's graphing techniques are employed to depict, in two dimensions, data representing the structure of a set of botanical concepts. Each of…

Procedures for analyzing common item effects on interscale structure were reviewed and a study using smallest space analysis of the California Psychological Inventory (CPI) reported. Solutions of three matrices--intercorrelation matrix of the original CPI scales, of reduced scales (with common items removed), and of the number of common…

Multiple matrix sampling (MMS) procedures were utilized to determine the necessary parameters of a Pearson Type I curve. Empirical norms distributions were approximated by both the Type I model and the negative hypergeometric model. Four existing ITED norms distributions, two subtests and two grades, were approximated by the MMS procedures. Two…

Populations of factorially simple and complex data were generated with first the oblique and orthogonal factor models, and then solutions based on special cases of the general orthomax criterion were compared on the basis of these characteristics. The results are discussed and implications noted. (DEP)

Examines the similarity between the coordinates which resulted when correlations were used as similarity measures and the factor loadings obtained by factor analyzing the same correlation matrix. Real data, a set of error free data, and some computer generated data containing deliberately introduced sampling error are analyzed. (RC)

An examination of methodological referencing patterns for actual physics, engineering, and sociology literature for the year 1983, using a Dunn planned comparison approach, indicates that physics differs from both engineering and sociology, while no difference was found between engineering and sociology. References are given in each sample…

This third in a series of edited transcripts based on a conference at Utah State University describes Merrill's Component Design Theory (CDT) and compares it to his earlier Component Display Theory. Topics discussed include concept structures, knowledge acquisition, components of an instructional design system, and a new CDT matrix. (10…

Discusses the use of citation networks for constructing measures of the relative standing of journals in scientific journal-to-journal networks. Topics addressed include eigenvectors; measuring the standing of national scientific communities; and an empirical comparison of two measures of standing, one considering the environment and one without…

Methods for analyzing the multitrait-multimethod matrix are reviewed and the results of their application to a classic data set are compared. It is shown that different analysis methods can yield different validity conclusions, and that the results obtained are partly dependent on the subjective judgments of the users. (Author/RC)

Two population raw data matrices were constructed by computer simulation techniques. Each consisted of 10,000 subjects and 12 variables, and each was constructed according to an underlying factorial model consisting of four major common factors, eight minor common factors, and 12 unique factors. The computer simulation techniques were employed to…

The Raven Advanced Progressive Matrices Test (APM) is a well-known measure of higher order general mental ability. The time to administer the test, 40 to 60 minutes, is sometimes regarded as a drawback. To meet efficiency needs, the APM can be administered as a 30-or 40-minute timed test, or one of two developed short versions could be used. In…