Rebecca C. Steorts

Home Research Papers Software Teaching Group Bio

I am an Assistant Professor of Statistical Science at Duke University. Previously, I was a Visiting Assistant Professor in the Department of Statistics at Carnegie Mellon University from 2012 -- 2015, working with Stephen E. Fienberg. My PhD is from the University of Florida under the supervision under the supervision of Malay Ghosh.  My research interests are in computationally scalable approaches to social science applications, where I focus on recovering high dimensional objects from degraded data and determining how to recover the underlying structure. Methods used for this are entity resolution, small area estimation, locality sensitive hashing, and privacy-preserving record linkage as applied to medical studies, fmri studies, human rights violations, and estimation of poverty rates in hard to reach domains.

Research interests: entity resolution (record linkage), clustering, Bayesian methodology and applications, machine learning, locality sensitive hashing, privacy-preserving record linkage, decision theory, survey methodology, small area estimation, and Markov chain Monte Carlo methods.

If you are a student interested in working with my research group, please set up a time to meet with me via email (and also first take a look at my research page and current projects that we are working on).

• Andee Kaplan joins research group as postdoctoral fellow, August 2017
• Steorts receives NSF Career Award, April 2017
• Angie Shen receives Honorable Mention for Faculty Scholar Award, Duke University, 2017
• Angie Shen receives Sirena WuDunn Memorial Scholarship, Duke University, 2016 and 2017
• Started program Youth in Machine Learning (YiML) program Launch of Youth in Machine Learning (YiML) program!
• Postdoctoral student Brenda Betancourt wins Foerster-Bernstein Postdoctoral Fellowship, December 2015.
• Upcoming short course on Teaching Bayes: the Essential Parts with Abbas Zaidi.
• Our paper on microclustering Bayesian nonparameteric clustering tasks with sublinear growth received a spotlight presentation at the BNP NIPS workshops NIPS 2015
• Check out our Blocking Methods Applied to Casualty Records from the Syrian Conflict paper applying locality sensitive hashing to the Syrian conflict
• Our paper A Bayesian Approach to Graphical Record Linkage and De-duplication is to appear in JASA, Theory and Applications.
• Check out our empirically motivated record linkage paper in special issue of Bayesian Analysis 2015 and Finalist for the 2016 Lindley Prize.
• Received a 2015 Collaborative NSF Research Grant on Record Linkage and Privacy-Preserving Methods for Big Data joint with Aleksandra B. Slavkovic
• Awarded a 2014 Metknowledge Network Grant via the John Templeton Foundation
• Awarded the 35 Innovator's under 35 by MIT review Magazine MIT 35 under 35, September/October Issue.
• Gave spotlight talk for 35 under 35 Innovator's Award EmTech 2015, for humanitarian software applied to Syrian conflict.