David A. Cole

Testing Mediational Models With Longitudinal Data: Questions and Tips in the Use of Structural Equation Modeling.

R. M. Baron and D. A. Kenny (1986; see record 1987-13085-001) provided clarion conceptual and methodological guidelines for testing mediational models with cross-sectional data. Graduating from cross-sectional to longitudinal designs enables researchers to make more rigorous inferences about the causal relations implied by such models. In this transition, misconceptions and erroneous assumptions are the norm. First, we describe some of the questions that arise (and misconceptions that sometimes emerge) in longitudinal tests of mediational models. We also provide a collection of tips for structural equation modeling (SEM) of mediational processes. Finally, we suggest a series of 5 steps when using SEM to test mediational processes in longitudinal designs: testing the measurement model, testing for added components, testing for omitted paths, testing the stationarity assumption, and estimating the mediational effects.

Bias in Cross-Sectional Analyses of Longitudinal Mediation.

Most empirical tests of mediation utilize cross-sectional data despite the fact that mediation consists of causal processes that unfold over time. The authors considered the possibility that longitudinal mediation might occur under either of two different models of change: (a) an autoregressive model or (b) a random effects model. For both models, the authors demonstrated that cross-sectional approaches to mediation typically generate substantially biased estimates of longitudinal parameters even under the ideal conditions when mediation is complete. In longitudinal models where variable M completely mediates the effect of X on Y, cross-sectional estimates of the direct effect of X on Y, the indirect effect of X on Y through M, and the proportion of the total effect mediated by M are often highly misleading.

A longitudinal look at the relation between depression and anxiety in children and adolescents.

Elementary school students (n = 330) and their parents (n = 228) participated in a 3-year longitudinal study of the temporal relation between anxiety and depressive symptoms in children. Every 6 months, children and parents completed depression and anxiety questionnaires for a total of 6 waves. Structural equation modeling revealed that individual differences on all measures were remarkably stable over time. Nevertheless, high levels of anxiety symptoms at 1 point in time predicted high levels of depressive symptoms at subsequent points in time even after controlling for prior levels of depression symptoms. These findings were consistent across self- and parent reports. Results support the temporal hypothesis that anxiety leads to depression in children and adolescents.

Bias in Cross-Sectional Analyses of Longitudinal Mediation: Partial and Complete Mediation Under an Autoregressive Model

Maxwell and Cole (2007) showed that cross-sectional approaches to mediation typically generate substantially biased estimates of longitudinal parameters in the special case of complete mediation. However, their results did not apply to the more typical case of partial mediation. We extend their previous work by showing that substantial bias can also occur with partial mediation. In particular, cross-sectional analyses can imply the existence of a substantial indirect effect even when the true longitudinal indirect effect is zero. Thus, a variable that is found to be a strong mediator in a cross-sectional analysis may not be a mediator at all in a longitudinal analysis. In addition, we show that very different combinations of longitudinal parameter values can lead to essentially identical cross-sectional correlations, raising serious questions about the interpretability of cross-sectional mediation data. More generally, researchers are encouraged to consider a wide variety of possible mediation models beyond simple cross-sectional models, including but not restricted to autoregressive models of change.

Mesolimbic dopamine reward system hypersensitivity in individuals with psychopathic traits

Psychopathy is a personality disorder that is strongly linked to criminal behavior. Using [18F]fallypride positron emission tomography and blood oxygen level–dependent functional magnetic resonance imaging, we found that impulsive-antisocial psychopathic traits selectively predicted nucleus accumbens dopamine release and reward anticipation-related neural activity in response to pharmacological and monetary reinforcers, respectively. These findings suggest that neurochemical and neurophysiological hyper-reactivity of the dopaminergic reward system may comprise a neural substrate for impulsive-antisocial behavior and substance abuse in psychopathy.

Models of cognitive mediation and moderation in child depression.

Negative cognitive errors, attributional style, positive and negative events, peer-nominated competence, and self-reported depression were assessed in 356 fourth, sixth, and eighth graders. Data supported theoretical models in which attributional style and cognitive errors mediated the relation of competence to depression. Data did not support models in which attributional style moderated the relation between either life events or competence and depression; however, weak support emerged for a moderational model involving negative life events and cognitive errors. The viability of diathesis-stress models in childhood, especially in which cognitive style is the diathesis, is critically examined.

The Development of Multiple Domains of Child and Adolescent Self‐Concept: A Cohort Sequential Longitudinal Design

The development of child and adolescent self-concept was examined as a function of the self-concept domain, social/developmental/educational transitions, and gender. In two overlapping age cohorts of public school students (Ns = 936 and 984), five dimensions of self-concept were evaluated every 6 months in a manner that spanned grades 3 through 11 (representing the elementary, middle, and high school years). Domains of self-concept included academic competence, physical appearance, behavioral conduct, social acceptance, and sports competence. Structural equation modeling addressed questions about the stability of individual differences over time. Multilevel modeling addressed questions about mean-level changes in self-concept over time. Significant effects emerged with regard to gender, age, dimension of self-concept, and educational transition.

Relation of social and academic competence to depressive symptoms in childhood

Relation of depressive symptoms to social and academic competence was examined in 750 4th-grade students. Self-report, peer-nomination, and teacher-rating measures of all three constructs were obtained. The multitrait-multimethod data were examined with confirmatory factor analysis and multivariate analysis of variance. Stronger correlations than have previously been reported were found between depressive symptoms and both kinds of competence. Social and academic incompetence had an additive effect on depressive symptoms. Children who were both socially and academically less competent had more symptoms of depression than children who had only one problem area. Children with only one problem area had more symptoms of depression than did children who were neither socially nor academically less competent. Gender differences in other-rated measures of competence were also evident. Implications for a competency-based model of depression are discussed.

Modeling Causal Relations Between Academic and Social Competence and Depression: A Multitrait-Multimethod Longitudinal Study of Children

The authors obtained self-reports, peer nominations, teacher ratings, and parent reports of depression and social and academic competence on 490 3rd graders and 455 6th graders near the beginning and end of the school year. Confirmatory factor analysis and structural equation modeling revealed that (a) measures showed significant convergent and discriminant validity; (b) within-wave correlations between constructs were large and significant, although the depression-social competence correlation was larger than the depression-academic competence correlation; (c) the cross-wave stability of all constructs was remarkably high; and (d) social competence at Wave 1 predicted depression at Wave 2 for 6th graders after controlling for depression at Wave 1. Depression did not predict change in either academic or social competence over time. Implications for competence-based and failure-based models of child depression are discussed.

The insidious effects of failing to include design-driven correlated residuals in latent-variable covariance structure analysis.

In practice, the inclusion of correlated residuals in latent-variable models is often regarded as a statistical sleight of hand, if not an outright form of cheating. Consequently, researchers have tended to allow only as many correlated residuals in their models as are needed to obtain a good fit to the data. The current article demonstrates that this strategy leads to the underinclusion of residual correlations that are completely justified on the basis of measurement theory and research design. In many designs, the absence of such correlations will not substantially harm the fit of the model; however, failure to include them can change the meaning of the extracted latent variables and generate potentially misleading results. Recommendations include (a) returning to the full multitrait-multimethod design when measurement theory implies the existence of shared method variance and (b) abandoning the evil-but-necessary attitude toward correlated residuals when they reflect intended features of the research design.