A moderated nonlinear factor model for the development of commensurate measures in integrative data analysis
Patrick Curran, Ph.D.
University of North Carolina-Chapel Hill
Integrative data analysis (IDA) is a methodological framework that allows for the fitting of models to data that have been pooled across 2 or more independent sources. IDA offers many potential advantages including increased statistical power, greater subject heterogeneity, higher observed frequencies of low base-rate behaviors, and longer developmental periods of study. However, a core challenge is the estimation of valid and reliable psychometric scores that are based on potentially different items with different response options drawn from different studies. This talk will focus on a five-step procedure for building measurement models in IDA and demonstrate this approach using data drawn from n = 1,972 individuals ranging in age from 11 to 34 years pooled across three independent studies to examine the factor structure of 17 binary items assessing depressive symptomatology. A series of nonlinear factor models are estimated and individual- and time-specific scores are obtained for subsequent analysis. Potential limitations of this approach are discussed, as are future directions for ongoing methodological development.