Census Bureau Blog-Protecting The Statistics

This blog was originally posted by the United States Census Bureau on August 17.


By Dr. John M. Abowd, Chief Scientist and Associated Director for Research and Methodology

The U.S. Census Bureau’s commitment to data stewardship—protecting respondent privacy and confidentiality at every stage of the data lifecyle—is grounded in law that is straightforward, robust, and strong. From the time we collect the data, through processing, publication and storage, we are bound by Title 13 of the United States Code to ensure that information about any specific individual, household, or business is never revealed, even indirectly through our published statistics.

We call the steps we take to prevent any outside entity from identifying individuals or businesses in the statistics we publish “disclosure avoidance.” This is the first of two Research Matters Blogs where I discuss the ongoing work at the Census Bureau to modernize how we protect respondent confidentiality when we publish statistics on the U.S. population and economy.

Throughout our history, we have been leaders in statistical data protection, which we call disclosure avoidance. Other statistical agencies use the terms “disclosure limitation” and “disclosure control.” These terms are all synonymous. Disclosure avoidance methods have evolved since the censuses of the early 1800s, when the only protection used was simply removing names. Executive orders, and a series of laws modified the legal basis for these protections, which were finally codified in the 1954 Census Act (13 U.S.C. Sections 8(b) and 9). We have continually added better and stronger protections to keep the data we publish anonymous and underlying records confidential.

However, historical methods cannot completely defend against the threats posed by today’s technology. Growth in computing power, advances in mathematics, and easy access to large, public databases pose a significant threat to confidentiality. These forces have made it possible for sophisticated users to ferret out common data points between databases using only our published statistics. If left unchecked, those users might be able to stitch together these common threads to identify the people or businesses behind the statistics as was done in the case of the Netflix Challenge. 1

The Census Bureau has been addressing these issues from every feasible angle and changing rapidly with the times to ensure that we protect the data our census and survey respondents provide us. We are doing this by moving to a new, advanced, and far more powerful confidentiality protection system, which uses a rigorous mathematical process that protects respondents’ information and identity in all of our publications.

The new tool is based on the concept known in scientific and academic circles as “differential privacy.” It is also called “formal privacy” because it provides provable mathematical guarantees, similar to those found in modern cryptography, about the confidentiality protections that can be independently verified without compromising the underlying protections.

“Differential privacy” is based on the cryptographic principle that an attacker should not be able to learn any more about you from the statistics we publish using your data than from statistics that did not use your data. After tabulating the data, we apply carefully constructed algorithms to modify the statistics in a way that protects individuals while continuing to yield accurate results. We assume that everyone’s data are vulnerable and provide the same strong, state-of-the-art protection to every record in our database.

The Census Bureau did not invent the science behind differential privacy. 2 However, we were the first organization anywhere to use it when we incorporated differential privacy into the OnTheMap application in 2008. It was used in this event to protect block-level residential population data. 3 Recently, Google, Apple, Microsoft, and Uber have all followed the Census Bureau’s lead, adopting differentially privacy systems as the standard for protecting user data confidentiality inside their browsers (Chrome), products (iPhones), operating systems (Windows 10), and apps (Uber).

Expanding these hardened and tested confidentiality protections to our flagship products, beginning with the 2020 Census, is a complicated task that the Bureau has taken years to meticulously plan and implement. Nothing on this scope and scale has ever been done before by a statistical agency or a private business.

The first Census Bureau product that will use the new system will be prototype redistricting data from the 2018 Census Test. This confidentiality protection system will provide the foundation for safeguarding all the data of the 2020 Census. It will then be adapted to protect publications from the American Community Survey, economic censuses, and eventually all of our statistical releases.

Narayanan, Arvind and Vitaly Shmatikov. 2008. “Robust De-anonymization of Large Sparse Datasets,” SP’08, pp. 111-124. Washington, DC, USA:IEEE Computer Society, DOI:10.1109/SP.2008.33.

2. Dwork, Cynthia, Frank McSherry, Kobbi Nissim, and Adam Smith. 2006. “Calibrating Noise to Sensitivity in Private Data Analysis,” TCC’06, pp. 265-284. Berlin, Heidelberg: Springer-Verlag, DOI: 10.1007/11681878_14.

3. Machanavajjhala, Ashwin, Daniel Kifer, John Abowd, Johannes Gehrke, and Lars Vilhuber. 2008. Privacy: Theory meets Practice on the Map. In Proceedings of the 2008 IEEE 24th International Conference on Data Engineering (ICDE ’08). IEEE Computer Society, Washington, DC, USA, 277-286. DOI: 10.1109/ICDE.2008.4497436.

Complete Count Efforts Underway in Some States and Communities

Across the country some states and communities are gearing up to encourage their local populations to participate in the 2020 Census count with local dollars behind the effort. But the effort, so far, is spotty.

Stateline traces national activity and noted the state of California has already funded tens of millions of dollars for its own in-state outreach.  Another article, published by Reuters, adds additional detail to these efforts.

Meanwhile, in Houston, similar outreach is already underway.

These efforts will be important since both political representation and billions of federal dollars for such things as Medicaid, highways and roads, school lunch programs, housing assistance and Head Start are guided by census numbers.

Congressional Rural Caucus Discussion on Census-Guided Financial Assistance To Rural America

This blog was originally posted by the Insights Association on October 22.


By Howard Fienberg, VP, Advocacy, The Insights Association and Co-director, The Census Project


On October 11, 2018, the Congressional Rural Caucus hosted a panel discussion on Capitol Hill about the importance of census-guided financial assistance to rural America. A new study from the George Washington Institute of Public Policy and the Census Project found that major rural-targeted programs that are guided by census data total about $30 billion a year.

Study author Dr. Andrew Reamer, research professor at the Institute, expanded upon details of his research, “Census-Guided Financial Assistance To Rural America,” for the audience of about 40 staff. Arthur Scott, associate legislative director for the National Association of Counties, explained some of the impact of those rural aid programs to counties his association represents, as well as ways in which county leaders use Census data further to benefit their communities. Finally, Howard Fienberg, VP advocacy for the Insights Association and co-director of the Census Project, focused on some of the challenges facing the 2020 Census in counting rural communities, which are surprisingly hard to count.

Opening with some Census history, Reamer sketched out the decennial headcount’s origins, back when Rep. James Madison proposed amending the Census Act of 1790 to include questions on population characteristics beyond those needed for apportionment so that Congress might “adapt the public measures to the particular circumstances of the community.” Over time, those questions and more became the statutorily-defined way to decide on the distribution of federal assistance programs.

In FY2016, Reamer said, about 320 funding programs used census-derived data to divvy up about $900 billion across the country. A sizeable majority of such assistance programs benefit both urban and rural areas, like Medicaid and the Special Supplemental Nutrition Program for Women, Infants, and Children (WIC). At the same time, 55 census-guided assistance programs are only targeted for rural communities and distributed $30.7 billion in FY2016.

Drilling down into the six large rural assistance programs at the U.S. Department of Agriculture (USDA), Reamer found more than $25 billion distributed per year to states, localities and households in the rural U.S., including for: low to moderate income housing loans; rural electrification; loans and loan guarantees; water and waste disposal systems for rural communities; rural rental assistance programs; business and industry loans; and the cooperative extension service.

According to Reamer, “the fair and equitable distribution of billions of dollars in federal financial assistance to rural communities depends on the accuracy and completeness of the 2020 Census.”

The ten states with the largest funding in Fiscal Year 2016 from rural programs, according to the study, were:

  1. Georgia – $1,435,939,900
  2. North Carolina- $1,369,804,196
  3. Virginia – $1,176,559,104
  4. South Carolina – $975,637,656
  5. Texas – $957,457,542
  6. Tennessee – $947,115,350
  7. Florida – $907,186,691
  8. Kentucky – $902,493,126
  9. Michigan – $862,138,937
  10. Missouri – $808,786,169

Attendees asked a wide variety of questions afterwards, including: expected impact of the added citizenship question on 2020 rural response; the state of funding for the decennial; what the sparsity of broadband access in some rural areas might mean for the new online 2020 response option; what Congressional offices can do to help increase rural response; and panelists’ opinions on Census Director nominee Steven Dillingham.

(For further reference, see the briefs from the Census Project and the Georgetown Law Center on Poverty and Inequality on “Why the 2020 Census Matters for Rural America” and “Counting Rural America.”)


Background Information on Rural Report/2020 Census

Last week, the Census Project co-sponsored a briefing on Capitol Hill for the Congressional Rural Caucus.

The Congressional aides were briefed on the recently released report from George Washington University linking $25 billion per year in federal aid to rural areas and the fairness and accuracy of the 2020 Census.

George Washington’s Dr. Andrew Reamer prepared slides especially for the session.

Finally, Georgetown Law’s Center on Poverty and Inequality prepared two fact sheets on the rural report for the Congressional briefing.

Citizenship Suit Back and Forth

Six separate lawsuits challenging the Trump Administration’s proposal to add a citizenship question to the 2020 Census form are coming to a head.

The Washington Post, in two separate articles published today, captures the legal back and forth in the lead suit in federal district court in New York.

In addition, The Hill newspaper has an interesting new development.

American Constitution Society Background Brief and Webinar on 2020 Census

The American Constitution Society (ACS) recently published a very informative background brief on the challenges facing the 2020 Census. In addition, the ACS will be sponsoring a webinar on October 18 on the issues raised by the brief’s co-authors John Thompson, former Census Bureau Director and Robert Yablon, Assistant Professor of Law at the University of Wisconsin Law School. Register for the webinar here.