Distinguished lectures in social sciences are named in honor of John Patrick Crecine, dean of the College of Humanities and Social Sciences at Carnegie Mellon University from 1976 to 1983. This semester, we welcome Jeff Gill, Distinguished Professor, Department of Government, Professor, Department of Mathematics and Statistics, American University. He will be speaking on “The present and future of data science”.
Abstract: This is a lecture about how data science is changing the world. We are in the middle of a dynamic era of human history easily comparable to the agricultural revolution or the industrial revolution. Data is literally everywhere from institutionalized sources, satellite geocoding, sensor data, internet traffic, genetic/genomic coding, social networking, digitized video, and more. According to common estimates approximately 3 quintillion bytes of new data are produced every day, and in the last two years more than 90% of the data ever produced by humans were created reaching a total of 44 zettabytes. Yet, less than 1% of these data are ever meaningfully analyzed. Or so we think. Such quantification is an incredibly difficult estimation problem because of the massive volume, the incredible variety, and the phenomenal rate of transmission. Every person, every government, every university, and every business is currently affected by staggering changes that continue unabated and at an accelerating pace. This general-audience talk covers the associated challenges confronted by researchers and citizens such as statistical analysis of big data, storage and transmission, real-time processing, privacy issues, and the shortage of skilled data scientists.
About the speaker:
Jeff Gill is currently Distinguished Professor in the Department of Government, Department of Mathematics & Statistics, a member of the Center for Behavioral Neuroscience, and the Director for the Center for Data Science, all at American University. He has done extensive work in the development of Bayesian hierarchical models, nonparametric Bayesian models, elicited prior development from expert interviews, as well in fundamental issues in statistical inference. Dr. Gill has extensive expertise in statistical computing, Markov chain Monte Carlo (MCMC) and related tools in particular, applying them to problems in the biomedical and social sciences. His current theoretical work includes developing new hybrid algorithms for statistical estimation with multilevel specifications and complex time-series and spatial relationships, as well clustering detection within algorithms. His current applied work includes Bayesian spatial modeling of national ideology and unemployment, Bayesian Frailty Models for Complex Multilevel Survival Data, analysis of survey modes in complex designs, biomarkers for pediatric traumatic brain injury, and the development of synthetic blood for critical care medicine.