Used analysis of covariance structures to test for the equivalence of a well-known measuring instrument across two culturally diverse groups, exploring three possible determinants of the resulting nonvariance. Example data comprised item responses to the four nonacademic subscales of the Self Description Questionnaire for Australian and Nigerian…

Evaluated the sample invariance of item discrimination statistics in a case study using real data, responses of 10 random samples of 500 people to a depression scale. Results lend some support to the hypothesized superiority of a two-parameter item response model over the common form of structural equation modeling, at least when responses are…

Naquin and Holton report how the NEO Five-Factor Inventory and Positive and Negative Affectivity Schedule were used to measure motivation to improve work through learning of 239 trainees. Positive affect, work commitment, and extraversion were significant antecedents of motivation. Invited reaction by Rodney A. McCloy and Lauress L. Wise raises…

Developed a Bayesian approach for a general multigroup nonlinear factor analysis model that simultaneously obtains joint Bayesian estimates of the factor scores and the structural parameters subjected to some constraints across different groups. (SLD)

Estimation of polychoric correlations is seen as a special case of the theory of parametric inference in contingency tables. the asymptotic covariance matrix of the estimated polychoric correlations is derived for the case when thresholds are estimated from univariate marginals and polychoric correlations are estimated from bivariate marginals for…

B. O. Muthen (1984) formulated a general model and estimation procedure for structural equation modeling with a mixture of dichotomous, ordered categorical, and continuous measures of latent variables that was implemented in the LISCOMP program. This paper extends the description of the asymptotics and shows how the formulas can be derived.…

Used an intervening mechanism design (H. Chen, 1990) in conjunction with structural equation modeling to test the plausibility of a model of participatory evaluation in a study involving 315 teachers participating in the British Columbia (Canada) school-accreditation program. Results support the model as an explanation of how participatory…

Explores the use of the Friedman method of ranks (H. Friedman, 1937) as an inferential procedure for evaluating competing models in structural-equation modeling. Describes the attractive features of this approach, but raises important issues regarding the lack of independence of observations and the power of the test. (SLD)

SOLAS is a general-purpose program for univariate statistical analysis with the ability to perform multiple imputation (MI) for dealing with missing data. Several completed data sets can be obtained and analyzed separately, and results can be combined so that extra variability due to missing data is taken into account. (SLD)

Proposes a method for obtaining standard errors and confidence intervals of composite reliability coefficients based on bootstrap methods and using a structural-equation-modeling framework for estimating the composite reliability of congeneric measures (T. Raykov, 1997). Demonstrates the approach with simulated data. (SLD)

Confirmatory factor analysis was used to test models of the relationship between inspection time (IT) and psychometric measures of intelligence in a sample of 134 healthy adults in the United Kingdom. A nested structural equation modeling approach shows that IT is most strongly associated with the Perceptual-Organizational factor of the Wechsler…

Assessed the robustness of an estimation method for multilevel and path analysis with hierarchical data proposed by B. Muthen (1989) with unequal groups and small sample sizes and in the presence of a low or high intraclass correlation. Simulation results show the effects of varying these conditions on the within-group and between-groups part of…

Discusses the design and analysis of Monte Carlo experiments, with special reference to structural equation modeling. Outlines three fundamental challenges of Monte Carlo approaches and suggests some alternative procedures that challenge conventional wisdom. Asserts that comprehensive Monte Carlo studies can be done with a personal computer if the…

Examines some positions in various arguments related to the proper number of factors and proper number of steps when using structural equation models. Defines the issue in estimating structural equation models as a problem of specifying a model appropriately based on theoretical concerns and then diagnosing ills in the model as well as possible.…

Provides select power and sample size tables and interpolation strategies associated with the root mean square error of approximation test of not close fit under standard assumed conditions. The goal is to inform researchers conducting structural equation modeling about power limitations when testing a model. (SLD)