Structural equation models in medical research.

P M Bentler; J A Stein

doi:10.1177/096228029200100203

Home/Archive/PubMed

PubMed · 1341656

Structural equation models in medical research.

P M Bentler·J A Stein

View original source ↗Export metadata ↓

Abstract

Structural equation modelling (SEM) is a modern statistical method that allows one to evaluate causal hypotheses on a set of intercorrelated nonexperimental data. The sample variances and covariances, and possibly the means, are compared to those predicted by a theory-based hypothetical model after optimal estimation of the parameters of the model. The goodness-of-fit of the empirical data to the hypothesized model is evaluated statistically. This review describes the underlying statistical theory and rationale of SEM. Both confirmatory factor analysis and latent variable path models are discussed. The applicability of SEM to assessment of reliability and validity is noted. A detailed example is provided, and several examples from the medical literature are briefly reviewed. Cautions regarding the possible misuse or misinterpretation of the technique are also mentioned. Possible future directions for the use of SEM in medical research are suggested. Two appendices provide more technical details.

Explore related subjects

Factor Analysis, Statistical Forecasting Genetic Techniques Linear Models Models, Statistical Research Design Journal Article Research Support, U.S. Gov't, P.H.S.Review

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

P M Bentler, J A Stein. 1992. Structural equation models in medical research.. https://doi.org/10.1177/096228029200100203

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2006

Brief fear of negative evaluation scale-revised.

Rodebaugh et al. [2004: Psychol Assess 2:169-181] recently performed a confirmatory factor analysis (CFA) on the Brief Fear of Negative Evaluation scale (BFNE; Leary, 1983: Psychol Bull 9:371-375]. Their study resulted in the emergence of a two-factor solution comprising straightforwardly worded items and reverse-worded items. They concluded by recommending use of only the straightforwardly worded items in the BFNE. Our intent in this study was to evaluate this recommendation through replication and extension. Participants included 385 undergraduates from the Universities of Regina and Houston, who provided responses to a questionnaire battery including either the BFNE or a revision utilizing straightforwardly worded versions of the reverse-worded items (BFNE-II). A CFA of the BFNE, using the two-factor model proposed by Rodebaugh et al., supported their conclusion that the reverse-worded items comprise a separate, methodologically based factor. However, CFA of the BFNE-II resulted in an acceptable unitary model that conforms to the theoretical basis for the BFNE, without risking loss of sensitivity from item removal. Additional analyses suggest use of the BFNE-II rather than a shortened form.

Factor Analysis, Statistical↗

PubMed2006

Factorial validation of a French short-form of the Working Alliance Inventory.

Evaluation of the therapeutic alliance is crucial for understanding the therapeutic process and its results. However, few instruments are available in French. This article aims to validate a French short form of the Working Alliance Inventory (WAI). Unlike other questionnaires, the WAI is the most widely used in psychotherapy research as well as in social psychiatry. Confirmatory factor analyses were carried out on a sample of 150 client-case manager dyads in order to determine the validity of this short-form instrument. The results of these confirmatory factor analyses allowed us to answer different authors' questions (Horvath and Greenberg, 1989; Tracey and Kokotovic, 1989) regarding the factorial structure of the WAI. The results also indicated a unidimensional solution as being the most valid for the two samples. We suggest that, in future studies, only one score be considered for the evaluation of the WAI. We also suggest modifying two statements in the English and French versions in order to render a faithful comparison between the therapist and client versions.

Factor Analysis, Statistical↗

PubMed2006

Random intercept item factor analysis.

The common factor model assumes that the linear coefficients (intercepts and factor loadings) linking the observed variables to the latent factors are fixed coefficients (i.e., common for all participants). When the observed variables are participants' observed responses to stimuli, such as their responses to the items of a questionnaire, the assumption of common linear coefficients may be too restrictive. For instance, this may occur if participants consistently use the response scale idiosyncratically. To account for this phenomenon, the authors partially relax the fixed coefficients assumption by allowing the intercepts in the factor model to change across participants. The model is attractive when m factors are expected on the basis of substantive theory but m + 1 factors are needed in practice to adequately reproduce the data. Also, this model for single-level data can be fitted with conventional software for structural equation modeling. The authors demonstrate the use of this model with an empirical data set on optimism in which they compare it with competing models such as the bifactor and the correlated trait-correlated method minus 1 models.

Factor Analysis, Statistical↗