Data Sampling & Measurement
Understanding the representativeness of different subpopulations is complex when developing nationally representative surveys, but it is even more challenging when building samples from publicly shared user posts. MDI researchers work to understand how to reweight samples to make them more representative of populations of interest. They also develop standards for constructing different types of variables and determining the reliability of different types of measurements. This is particularly important when developing measurements using big data sources, e.g. social media, newspapers, mobile phones, satellite images, etc. Representative samples and reliable measurements are necessary for developing evidence-based public policy.
Faculty
Colonel William J. Walsh Professor of American Government, Department of Government and McCourt School of Public Policy
Department of Biology, Provost’s Distinguished Associate Professor
Department of Communication Culture and Technology, Provost’s Distinguished Associate Professor
McDonough School of Business Entrepreneurship and Finance, Akkaway Professor
Robin Dillon-Merrill (She/Her)
McDonough School of Business Operations and Analytics, Professor and Area Head
McCourt School of Public Policy, Associate Professor
McCourt School and Department of Government, Associate Professor
McCourt School of Public Policy, Associate Professor
Department of Health Management & Policy and MSPP, Professor
Department of Psychology, Professor
McCourt School of Public Policy, Assistant Professor
Director, Massive Data Institute
Sonneborn Chair | Chair and Professor, Department of Computer Science | Professor, McCourt School of Public Policy