The Social and Decision Analytics Laboratory advances statistical and quantitative social science methods to deliver a more comprehensive understanding of social problems. Our research aims to transform all data into actionable knowledge, integrating novel sources of information, such as mobile technology, embedded sensors, blogs, social media, and location-based tools.
The Social Decision and Analytics Laboratory was founded in September of 2013, headquartered in the Virginia Tech National Capital Region. Its world-class statistical and data science capabilities support the Biocomplexity Institute’s overarching mission to predict, explain, and visualize the behavior of massively interacting systems.
Since its founding, SDAL has established long-term partnerships with a variety of organizations including Arlington County, Procter & Gamble, the Robert Wood Johnson Foundation, the United States Census Bureau, and the Department of Housing and Urban Development.
The Biocomplexity Institute works with local, regional, national and international media to provide journalists with accurate information about current developments in our scientific field. To schedule an interview with one of our experts or request assistance in developing story ideas based on their research, please contact our communications department.
Systems and Data Engineer
Experience includes developing models to conduct experiments related to online interactions, including social media. His research focuses on developing methods to bring more reproducible and replicable reearch to the social sciences. His area of applied research are social media analysis, modeling cascade behaviors, identifying trends of metaphors in blogs, and modeling population level behaviors using theories in statistical mechanics.
Modeling of environmental and physical systems, inverse problems in hydrology and imaging, statistical modeling in ecology, environmental science, statistical computing
Research Assistant Professor
Modeling of complex social systems using computational methods, integrating agent-based models with geographic information systems and social networks to represent human behavior and movement across physical environments.
Research focuses on the applicability of data to understanding quantifications of complex social systems. This includes assessing the use of data for predictive modeling of measurable events, as well as data linkage where their true relationships are unknowable. His work in these domains emphasizes computational efficiency, scalability, and reproducibility in an open source framework.