I am an Associate Professor in the Quantitative Methods (QM) program within the Department of Psychology and Human Development at Vanderbilt University.
My research focuses on methodological issues that commonly arise in psychology applications — particularly in the context of developmental psychopathology research.
For instance, developmental psychopathologists may expect unobserved heterogeneity in the longitudinal course of problem behaviors. They often employ mixture models to describe and predict heterogeneity in change. Some of my research involves developing methods to handle alternative kinds of missing data when fitting mixture models, studying how mixtures can be used to recover interactive relationships, and disseminating pedagogical information about mixtures to clarify how they can be interpreted in practice.
Furthermore, developmental psychopathologists often encounter complex nesting structures (e.g., patients partially-nested within therapy groups), highly unbalanced measurement schedules, or unequal selection probabilities. My research investigates how traditional structural equation and multilevel models can be adapted to accommodate such real-world issues.
Sometimes developmental psychopathologists may have many categorical or nonnormal symptom indicators of a latent factor and may consider item parceling. My research also studies consequences of this practice.
Finally, I have a long-term interest in relating data analytic decision-making and ethics in order to improve statistical practice.
© 2010-2017, Sonya K. Sterba