Skip this top of page navigation
![]() |
![]() |
![]() |
![]() |
||||||
![]() |
![]() |
![]() |
|||||||
![]() |
![]() |
||||||||
![]() |
![]() |
||||||||
![]() |
![]() |
|
![]() |
||||||
![]() |
![]() |
![]() |
|||||||
![]() |
Confidentiality ResearchThe mission of national statistical institutes is to collect and disseminate data while protecting the confidentiality of individual respondents. The latter part of the mission is taken very seriously—under Title 13 of the U.S. Code, Census Bureau employees are subject to a $250,000 fine and/or 5 years in jail if confidentiality is breached. All analysis of Census Bureau data must be for statistical purposes only, for approved projects, by Census Bureau employees. There are considerable security procedures: in particular, LED program staff work with anonymized data, with full audit logs and full disclosure review before data are released outside the Title 13 secure environment. The LED program, with the support of the National Science Foundation, has made a considerable investment in the development of confidentiality protection techniques. These techniques enable more information to be released, while preserving the statistical integrity of the data and protecting respondent confidentiality. SummaryThe LED program uses noise addition methodology to protect tabular information. It is also developing a multiple imputation approach to protect micro-data. Documentation
[PDF] or | ![]() |
|||||||
![]() |
![]() |
![]() |
![]() |
![]() |
|||||
![]() |
|||||||||
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |
![]() |