Enriching factor rotation algorithms with the capacity to conduct repeated searches from random starting points can make the tendency to converge to optima that are merely local a way to catch rotations of the input factors that might otherwise elude discovery. Use of the HYBALL computer program is discussed. (SLD)

Accuracy was compared for three methods of implementing parallel analysis with mean eigenvalues (regression, interpolation, and computation with three samples of random data). The accuracy of parallel analysis with 95th percentile eigenvalues (through regression and interpolation) was also considered. No evidence of differential accuracy emerged…

Technology education practitioners (n=225) identified how often 27 mental processes were used in solving technological problems. Analysis resulted in five factors: researching the problem, searching for solutions, creating innovative solutions, analyzing data, and evaluating results. (SK)

Confirmatory factor analysis of the Pictorial Scale of Perceived Competence and Social Acceptance for Young Children supported the hypothesis that kindergarteners' self-concepts are multidimensional. Both theoretical and practical measurement concerns are discussed. (Author)

Used simulated data to test the integrity of orthogonal factor solutions when varying sample size, factor pattern/structure coefficient magnitude, method of extraction, number of variables, number of factors, and degree of overextraction. Discusses implications of results with regard to overextraction. (SLD)

Factor analysis is often neglected in survey research, despite the fact that it removes metric redundancies and extracts the common thread from a set of observed variables. Likert-based extension surveys would benefit from factor analysis. (SK)

Explores the four-step procedure for testing structural equation models and outlines some problems with the approach advocated by L. Hayduk and D. Glaser (2000) and S. Mulaik and R. Milsap (2000). Questions the idea that there is a "correct" number of constructs for a given phenomenon. (SLD)

Simulated data for factor analytic models is used in the evaluation of three methods for controlling Type I errors: (1) the standard approach that involves testing each parameter at the 0.05 level; (2) the Bonferroni approach; and (3) a simultaneous test procedure (STP). Advantages offered by the Bonferroni approach are discussed. (SLD)

Two theorems are presented that describe the conditions under which intercept differences can exist under factorial invariance. In such cases, intercept differences do not result from measurement bias in either the tests or the criterion. The conditions of the theorems are testable, and the test procedures are illustrated. (SLD)

Adjustment of observed cell means in factor designs reduces the chance of misinterpreting the interaction effect. The process of adjusting cell means for lower-order effects in two- and three-factor designs is described. Identifying and testing interaction contrasts are covered, and examples from the counseling literature are presented.…

Simulation studies indicate that, for responses to complete tests, construction of Rasch measures from observational data, followed by principal components factor analysis of Rasch residuals, provides an effective means of identifying multidimensionality. The most diagnostically useful residual form was found to be the standardized residual. (SLD)

This study assessed the accuracy of parallel analysis, a technique in which observed eigenvalues are compared to eigenvalues from simulated data when no real factors are present. Three studies with manipulated sizes of real factors and sample sizes illustrate the importance of modeling the data more closely when parallel analysis is used. (SLD)

A hierarchical factor solution on the Minnesota Multiphasic Personality Inventory-2 standardization sample found a general psychopathology factor and four primary factors similar to those reported by Butcher, Dahlstrom, Graham, Tellegen, and Kaemmer (1989). (Contains 29 references and 2 tables.) (Author)

Effects of sample size and composition are systematically examined on the replicability of principal components, using observer ratings of personality from the California Adult Q-Set for 192 series of principal components analyses. Results indicate that dimensionality cannot be inferred from component robustness; they are empirically and logically…

Factor analysis of 1,030 adults' responses on the Myers Briggs Type Indicator (MBTI) were used to test 4 alternative models. Results support a four-factor structure similar to the original Jungian structure. Elimination of 12 MBTI items was recommended. (SK)