@article {2238, title = {Using partially synthetic microdata to protect sensitive cells in business statistics}, journal = {Statistical Journal of the International Association for Official Statistics}, volume = {32}, year = {2016}, month = {2016}, pages = {69-80}, chapter = {69}, abstract = {We describe and analyze a method that blends records from both observed and synthetic microdata into public-use tabulations on establishment statistics. The resulting tables use synthetic data only in potentially sensitive cells. We describe different algorithms, and present preliminary results when applied to the Census Bureau{\textquoteright}s Business Dynamics Statistics and Synthetic Longitudinal Business Database, highlighting accuracy and protection afforded by the method when compared to existing public-use tabulations (with suppressions).}, keywords = {confidentiality protection, gross job flows, local labor markets, Statistical Disclosure Limitation, Synthetic data, time-series}, doi = {10.3233/SJI-160963}, url = {http://content.iospress.com/download/statistical-journal-of-the-iaos/sji963}, author = {Miranda, Javier and Vilhuber, Lars} } @techreport {handle:1813:42339, title = {Using Partially Synthetic Microdata to Protect Sensitive Cells in Business Statistics}, number = {1813:42339}, year = {2015}, institution = {Cornell University}, type = {Preprint}, abstract = {Using Partially Synthetic Microdata to Protect Sensitive Cells in Business Statistics Vilhuber, Lars; Miranda, Javier We describe and analyze a method that blends records from both observed and synthetic microdata into public-use tabulations on establishment statistics. The resulting tables use synthetic data only in potentially sensitive cells. We describe different algorithms, and present preliminary results when applied to the Census Bureau{\textquoteright}s Business Dynamics Statistics and Synthetic Longitudinal Business Database, highlighting accuracy and protection afforded by the method when compared to existing public-use tabulations (with suppressions).}, url = {http://hdl.handle.net/1813/42339}, author = {Vilhuber, Lars and Miranda, Javier} } @techreport {handle:1813:40852, title = {Using partially synthetic data to replace suppression in the Business Dynamics Statistics: early results}, number = {1813:40852}, year = {2014}, institution = {Cornell University}, type = {Preprint}, abstract = {Using partially synthetic data to replace suppression in the Business Dynamics Statistics: early results Miranda, Javier; Vilhuber, Lars The Business Dynamics Statistics is a product of the U.S. Census Bureau that provides measures of business openings and closings, and job creation and destruction, by a variety of cross-classifications (firm and establishment age and size, industrial sector, and geography). Sensitive data are currently protected through suppression. However, as additional tabulations are being developed, at ever more detailed geographic levels, the number of suppressions increases dramatically. This paper explores the option of providing public-use data that are analytically valid and without suppressions, by leveraging synthetic data to replace observations in sensitive cells.}, url = {http://hdl.handle.net/1813/40852}, author = {Miranda, Javier and Vilhuber, Lars} }