Used confirmatory factor analysis (CFA), hypothesized factors that were less than the number of variables, and then examined how well the intercorrelations were reproduced. Results help explain that the type of correlation matrix and estimation method affect factor loadings and fit functions. Suggests some alternative approaches. (SLD)

The Schmid-Leiman (J. Schmid and J. M. Leiman, 1957) decomposition of a hierarchical factor model converts the model to a constrained case of a bifactor model with orthogonal common factors that is equivalent to the hierarchical model. This article discusses the equivalence of the hierarchical and bifactor models. (Author/SLD)

Using higher order factor models, this article illustrates latent curve analysis for the purpose of modeling longitudinal change directly in a latent construct. Provides examples with simultaneous estimation of covariance and mean structures for a single-group and two-group structure. (SLD)

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)

Focuses on the four-step method (four nested models) of structural equation modeling advocated by S. Mulaik (1997, 1998), discussing the limitations of the approach and considering the tests and criteria to be used in moving among the four steps. (SLD)

Defends the four-step approach to structural equation modeling based on testing sequences of models and points out misunderstandings of opponents of the approach. The four-step approach allows the separation of respective constraints within a structural equation model. (SLD)

Neither the four-step model nor the one-step procedure can actually tell whether the researcher has the right number of factors in structural equation modeling. In fact, for reasons discussed, a simple formulaic approach to the correct specification of models does not yet exist. (SLD)

Replies to commentaries on the four-step approach to structural equation modeling, pointing out the strengths and weaknesses of each argument and ultimately concluding that the four-step model is subject to criticisms that can be addressed to factor analysis as well. (SLD)

Quality of life (QOL) has become an important concept for health care. As QOL is a multidimensional concept that is best evaluated by a number of latent constructs, it is well recognized that latent variable models, such as exploratory factor analysis (EFA) and confirmatory factor analysis (CFA) are useful tools for analyzing QOL data. Recently,…

Treating Likert rating scale data as continuous outcomes in confirmatory factor analysis violates the assumption of multivariate normality. Given certain requirements pertaining to the number of categories, skewness, size of the factor loadings, and so forth, it seems nevertheless possible to recover true parameter values if the data stem from a…

Rasch measurement is preferable to factor analysis for reducing complex data matrices to unidimensional variables because factor analysis can mistake ordinally labeled stochastic observations for linear measures, and it does not construct linear measurement. Guidelines and instructions on how to use Rasch measurement to replace factor analysis are…

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)

Used nine different confirmatory factor analysis models to test the factorial structure of Rosenberg's (M. Rosenberg, 1965) self-esteem scale with a sample of 430 crack-cocaine users. Results partly support earlier research to show a single global self-esteem factor underlying responses to the Rosenberg scale, method effects associated with item…

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.…

We illustrate testing measurement invariance in a second-order factor model using a quality of life dataset (n = 924). Measurement invariance was tested across 2 groups at a set of hierarchically structured levels: (a) configural invariance, (b) first-order factor loadings, (c) second-order factor loadings, (d) intercepts of measured variables,…