@article {2667, title = {Generating Partially Synthetic Geocoded Public Use Data with Decreased Disclosure Risk Using Differential Smoothing}, journal = {Journal of the Royal Statistical Society - Series A}, year = {2016}, abstract = {When collecting geocoded confidential data with the intent to disseminate, agencies often resort to altering the geographies prior to making data publicly available due to data privacy obligations. An alternative to releasing aggregated and/or perturbed data is to release multiply-imputed synthetic data, where sensitive values are replaced with draws from statistical models designed to capture important distributional features in the collected data. One issue that has received relatively little attention, however, is how to handle spatially outlying observations in the collected data, as common spatial models often have a tendency to overfit these observations. The goal of this work is to bring this issue to the forefront and propose a solution, which we refer to as "differential smoothing." After implementing our method on simulated data, highlighting the effectiveness of our approach under various scenarios, we illustrate the framework using data consisting of sale prices of homes in San Francisco.}, url = {https://arxiv.org/abs/1507.05529}, author = {Quick, H. and Holan, S.H. and Wikle, C.K.} } @article {2039, title = {Bayesian Marked Point Process Modeling for Generating Fully Synthetic Public Use Data with Point-Referenced Geography}, journal = {Spatial Statistics}, volume = {14}, year = {2015}, month = {08/2015}, pages = {439--451}, doi = {10.1016/j.spasta.2015.07.008}, url = {http://www.sciencedirect.com/science/article/pii/S2211675315000718}, author = {Quick, Harrison and Holan, Scott H. and Wikle, Christopher K. and Reiter, Jerome P.} } @article {2015arXiv:1407.7795, title = {Bayesian Marked Point Process Modeling for Generating Fully Synthetic Public Use Data with Point-Referenced Geography}, journal = {ArXiv}, year = {2015}, abstract = {Many data stewards collect confidential data that include fine geography. When sharing these data with others, data stewards strive to disseminate data that are informative for a wide range of spatial and non-spatial analyses while simultaneously protecting the confidentiality of data subjects{\textquoteright} identities and attributes. Typically, data stewards meet this challenge by coarsening the resolution of the released geography and, as needed, perturbing the confidential attributes. When done with high intensity, these redaction strategies can result in released data with poor analytic quality. We propose an alternative dissemination approach based on fully synthetic data. We generate data using marked point process models that can maintain both the statistical properties and the spatial dependence structure of the confidential data. We illustrate the approach using data consisting of mortality records from Durham, North Carolina.}, url = {http://arxiv.org/abs/1407.7795}, author = {Quick, H. and Holan, S.~H. and Wikle, C.~K. and Reiter, J.~P.} } @conference {Quick2014a, title = {A Fully Bayesian Approach for Generating Synthetic Marks and Geographies for Confidential Data}, booktitle = {International Indian Statistical Association}, year = {2014}, month = {July}, publisher = {IISA}, organization = {IISA}, author = {Quick, H.} } @techreport {handle:1813:37750, title = {NCRN Meeting Fall 2014: Bayesian Marked Point Process Modeling for Generating Fully Synthetic Public Use Data with Point-Referenced Geography}, number = {1813:37750}, year = {2014}, institution = {NCRN Coordinating Office}, type = {Preprint}, abstract = {NCRN Meeting Fall 2014: Bayesian Marked Point Process Modeling for Generating Fully Synthetic Public Use Data with Point-Referenced Geography Quick, Harrison; Holan, Scott; Wikle, Christopher; Reiter, Jerry Presentation from NCRN Fall 2014 meeting}, url = {http://hdl.handle.net/1813/37750}, author = {Quick, Harrison and Holan, Scott and Wikle, Christopher and Reiter, Jerry} }