Social and Decision Analytics Division

The Social and Decision Analytics Division consists of statisticians, social scientists, and behavioral scientists who use big data to develop evidence-based research and use quantitative methods to improve the impact of policy decisions.

Our Approach

Cities, towns, and counties want to be responsive to their residents, improve their quality of life, determine what services are needed, and stimulate economic growth. During the course of administering public services and allocating resources, an abundance of data is generated. The stories of these communities are in these data. The Science of All Data can bring these stories to life.

Working shoulder-to-shoulder with our partners from communities, academia, government and industry, SDAD innovations apply statistical rigor and the creative application of data redistribution based on synthetic populations. With this approach, we can establish baselines for future comparisons and also policy simulation.

Science of All Data

Quality data sources are a cornerstone of effective policymaking and timely research. As information is captured in ever-increasing quantities and varieties, it’s essential that our data repositories evolve to keep pace. SDAD research is helping to guide the growth of these key resources, developing new methods to help them scale without sacrificing accuracy or security.

Policy Informatics

Community information-sharing is a complex process, involving diverse populations, interconnected infrastructure, and a steady stream of daily interactions. Our data science research can help decision-makers develop a deeper understanding of how their communities spread new knowledge, providing the resources they need to make sure their messaging reaches its intended audience.

Our Team

Leveraging data to solve real-world problems requires a broad range of scientific expertise. The SDAL team includes thought leaders in a wide variety of fields: statistics, economics, information architecture, computational social science, and public policy.

Sallie Keller, Director and Professor of Public Health Sciences: research interests - social and decision informatics, the statistical underpinnings of data science, and data access and confidentiality
Stephanie S. Shipp, Deputy Director and Research Professor: research interests - economic and demographic analyses of social issues, identifying novel approaches to measuring innovation and competitiveness, and evaluating public programs
Gizem Korkmaz, Research Associate Professor, Economics: research interests - conducting theoretical and empirical analysis of social and economic networks and combining traditional economics with big data using tools from social network analysis and machine learning
Aaron Schroeder, Research Associate Professor, Data Science, Public Policy: research interests - developing approaches, methods and platform related to the secure integration, storage, retrieval, sharing, and optimal use of public-sector administrative data
Vicki Lancaster, Principal Scientist and Statistician: research interests - applying statistical logic and methodologies to high-profile interdisciplinary investigations and presenting results using novel visualization approaches
Joshua Goldstein, Research Assistant Professor, Statistician: research interests - spatial modeling of infectious disease, Markov chain Monte Carlo methods, and generating synthetic populations
Joy Tobin, Principal Scientist
Devika Nair, Research Scientist
Teja Pristavec, Research Associate: research interests - quantitative methods, health, and inequality

Assembling data to examine the interrelationships across domains into Community-Scapes yields a unique view of integrated social, economic, health, and well-being indicators.

The first step toward a Community-Scape is to gather information and data across sectors. We assemble comprehensive data—on the demographic and socioeconomic characteristics of community populations. And, depending on the study, other data would be included such as clinical data from health care, emergency medical, and trauma systems; behavioral health care; crime/forensics data; education statistics; environmental data and more. This rich data environment will enable in-depth analytics and modeling; on a more practical and more immediate level, it can help answer key questions that are currently unanswered questions and target quantitative evidence to specific geographic domains or institutions relevant to decision makers, policy implications, education, and interventions.

This will set the stage for more in-depth analysis of the potential benefits and return on investment of various policy options. Subsequently, we can apply quantitative methods to inform policy decision-making.

Community Learning Through Data-Driven Discovery (CLD3)

Working with communities, industry and government, SDAD brings our Community Learning Through Data Driven Discovery process to address issues and questions facing our partners. The problems we have addressed range from emergency first responders, public transportation, the effects of air pollution on health and optimizing supply chain dynamics.

Data Science for the Public Good
Data Science for the Public Good program (DSPG) engages young scholars in finding solutions to some of the most pressing social issues of our time. DSPG fellows conduct research at the intersection of statistics, computation, and the social sciences to determine how information generated within every community can be leveraged to improve quality of life.