Analyzing longitudinal changes in mental health: Integrating variable-centered and person-centered approaches

Abstract

While variable-centered approaches to data continue to be widely employed in public health, psychology and many other disciplines, the use of person-centered approaches have become increasingly common. A third type of approaches, which integrates both variable- and person-centered approaches, has been rapidly developed and adopted in research which involves longitudinal data. In this workshop, we will first compare these three approaches. Then, drawing on a longitudinal study which examines the trajectory patterns in maternal depressive symptoms across pre- and postnatal periods, we will go through the steps of conducting general mixture modeling, an analytical procedure combining variable- and person-centered approaches. We will also discuss how this integrated approach can help to address research questions which are difficult to answer otherwise.