Reliability and validity of structural equation modeling applied to neuroimaging data: A simulation study

Abstract

Structural equation modeling aims at quantifying the strength of causal relationships within a set of interacting variables. Although the literature emphasizes that large sample sizes are required, this method is increasingly used with neuroimaging data of a limited number of subjects to study the relationships between cerebral structures. Here, we use a simulation approach to evaluate its ability to provide accurate information under the constraints of neuroimaging. Artificial samples representing the activity of a virtual set of structures were generated under both recursive and non-recursive connectivity models. Structural equation modeling was performed on these samples, and the quality of the analyses was evaluated by directly comparing the estimated path coefficients with the original ones. The validity and the reliability are shown to decrease with sample size, but the estimated models respect the relative strength of path coefficients in a large percentage of cases. The “smoothing method” appears to be the most appropriate to prevent improper solutions. Both the experimental error and the external structures influencing the network have a weak influence. Accordingly, structural equation modeling can be applied to neuroimaging data, but confidence intervals should be presented together with the path coefficient estimation.