At the U.S. Census Bureau, the Disclosure Review Board is best known as the team that establishes and reviews official Census Bureau disclosure avoidance policies for the public release of data products that do not reveal any information about the survey respondents. Yet, the boards’ members also serve other important and lesser known roles. For example, they work with researchers in the Center for Disclosure Avoidance Research to determine the effectiveness of current disclosure avoidance techniques in protecting data products. In addition, these researchers study and develop new techniques that may be applied to future releases of data products.

This work is critical in meeting the guidelines established under Title 13 and Title 26 of the U.S. Code, which states that the Census Bureau is required to protect the confidentiality of individual respondents when it releases data to the public .

This seemly simple mission can often pose challenges. For example, what occurs if a researcher wants to release counts and demographic characteristics of individuals in every county in the United States? What if a researcher wants to release an infinite number of variables in a Public Use File? What should a researcher do if they encounter small cell sizes within their data product?

These types of questions and others, along with their solutions, will be presented in a topic-contributed session at the 2016 Joint Statistical Meetings on Wednesday, August 3, 2016, titled ”Innovations in Disclosure Avoidance at the U.S. Census Bureau.” We explain specific issues and walk through some of the methods and techniques that are used to ensure the Disclosure Review Board meets its mission. That is, to support the Data Stewardship Executive Policy Committee in its efforts to ensure that the Census Bureau protects all Title 13 and Title 26 respondent confidentiality of publicly released data products.

Looking to the future, the Disclosure Review Board will also continue to face other challenges. It is likely that Census Bureau and other researchers will need to develop, test, and apply new methodologies and techniques to Census Bureau data, particularly as the quantity of potentially linkable data outside of the Census Bureau increases.