A general fit index for covariance structure models is obtained for all estimators that can be considered under generalized least squares (GLS) approaches including asymptotically efficient, robust, and resistant methods of estimation. This fit index is expressed as a function of the ratio of two trace functions. Normal theory ordinary least squares (OLS) and maximum likelihood (ML) fit indices previously given by Joreskog and Sorbom can be derived from this framework. Fit indices for normal theory and generic GLS approaches including robust/resistant estimation methods are also obtained.
The CES-D is a well-known index of acute depressive symptoms experienced over a 7-day period that has been used in literally hundreds of studies. This article presents the psychometric derivation of 8- and 4-item screening versions of the CES-D for use in research with community-based samples. These short depressive symptom indices can be used in those instances where a brief assessment is needed for broad screening or research purposes. Using data from a heterogeneous community sample of 411 women, the 8-item CES-D was found to correlate .93 with the full 20-item CES-D while the 4-item CES-D was found to correlate .87 with the full CES-D. In a second sample of 83 women in a residential drug abuse program, the 8- and 4-item measures correlated .54 and .47, respectively, with the BPI Depression scale.
Previous factor-analytic research examining the dimensionality of psychological distress and depression has generally minimized the importance of the interrelationships existing among primary components of depression and distress. Restricted hierarchical factor-analysis models that simultaneously test for the presence and necessity of both primary and second-order factors are developed for the Beck Depression Inventory and the Psychiatric Epidemiology Research Interview. Similarities in the latent structure of these two instruments are examined and implications for a taxonomy of psychological distress and depression are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.