Zita Oravecz

• Institute for Computational and Data Sciences
• QuantDev Methodology

• intensive longitudinal data analysis
• cognitive process modeling
• multilevel Bayesian modeling
• affective science
• ecological momentary assessment and intervention

Zita Oravecz has been working towards building a framework that provides for delivery and assessment of real-time, context-aware, person-centered interventions for improving health and maximizing human potential.  She has been developing hierarchical Bayesian process models, which offer a framework for testing theories by disentangling and quantifying latent processes that become confounded in observed data. By design, parameters of a process model correspond to theory-backed concepts such as dynamical regulatory mechanisms (see, e.g., Oravecz, Tuerlinckx, & Vandekerckhove, 2016) or cognitive ability levels (see, e.g., Oravecz, Anders & Batchelder, 2015), and allow us to make statements about these concepts directly. She casts these models into the hierarchical/multilevel framework to study the data generating processes in the context of both population- and individual-level questions. She implements models in the Bayesian statistical framework, and been devoted to the dissemination of the advantages of Bayesian methods, for example via developing user-friendly software tools (see, e.g., Oravecz & Muth, 2018).

Wear-IT: using mobile technology to develop individualized interventions to prevent relapse in addiction; developing longitudinal and cognitive process models

Research interest in studying individual differences from a process modeling perspective. The general goal is to develop and apply state-of-the-art statistical approaches to particular areas of substantive research (in my case emotion and cognition) that would be difficult or impossible to study without novel methods of analysis.