Joshua Snoke is an associate statistician at RAND. His primary research focuses on novel estimation procedures when data are unavailable due to privacy restrictions. These methods seek to increase researchers’ ability to answer policy questions using hard to obtain data due to privacy concerns. He has expertise broadly in the field and have published papers on topics such as the release of synthetic datasets, the enabling of model estimation across multiple databases, and the creation of differentially private algorithms. Outside of privacy, he has worked on numerous projects evaluating programs and institutions for individuals’ outcomes. On the defense side, he works on manpower and personnel questions, such as evaluating marketing and recruitment strategies, evaluating predictors of success in enlisted personnel, and staffing models. His work, both privacy related and otherwise, has involved a variety of administrative datasets, such as from the U.S. Census Bureau, the UK Administrative Data Research Network, the U.S. Army Recruiting Command, and the American Educator Panels. His broader methodological interests include estimation, model selection, non-parametric modeling and classification, machine learning, and causal inference. He received his Ph.D. in statistics with a graduate minor in social data analytics from the Pennsylvania State University. He received his B.S. in mathematics and economics from Wheaton College.
- Comparative Study of Differentially Private Synthetic Data Algorithms and Evaluation Standards
- Evaluation and Research Services Relating to the Connections to Care Initiative
- Relationship of Marketing Campaigns to Prospect, Parent, and General Population Attitudes and to Enlistment-Related Actions
- American Educator Panels
Snoke, J., Raab, G. M., Nowok, B., Dibben, C., and Slavković, A., "General and specific utility measures for synthetic data.," Journal of the Royal Statistical Society: Series A (Statistics in Society), 181(3), 2018
Snoke, Joshua, Brick, T. R., Slavković, A., and Hunter, M. D., "Providing accurate models across private partitioned data: Secure maximum likelihood estimation.," The Annals of Applied Statistics, 12(2), 2018
Snoke, J. and Slavković, A.. "pMSE Mechanism: Differentially Private Synthetic Data with Maximal Distributional Similarity.," in , Privacy in Statistical Databases. pp. 138-159, Springer, 2018