Blog Archives

First 2020 Census Data Released; 7 Congressional Seats Change Hands

On April 26, the Census Bureau released the first data from the 2020 Census, including each state’s apportionment population counts (used to allocate seats to the U.S. House of Representatives and electoral college votes), resident population accounts, and overseas population counts. The release of the Constitutionally-required information was delayed due to the operational challenges of the COVID-19 pandemic and the additional time needed to correct duplicate and incomplete responses. Overall, seven Congressional seats will shift as a result of the 2020 Census. California, Illinois, Michigan, New York, Ohio, Pennsylvania, and West Virginia will each lose one Congressional seat, while Colorado, Florida, Oregon, Montana, and North Carolina will each gain one seat. Texas will gain two Congressional seats.

More detailed data on the populations of smaller geographic areas that states will use to redraw their individual Congressional districts is expected to be released in August. The next release will also include more detailed demographic information on race, ethnicity, age, and gender. As states await the publication of this information, several lawsuits are progressing through the courts attempting to force the Bureau to release the data earlier and to prevent it from adopting differential privacy techniques to keep individuals’ data anonymous. Stay tuned to all of COSSA’s 2020 Census coverage here.

Tagged with: , , ,
Posted in Issue 9 (April 27), Update, Volume 40 (2021)

Census Releases Updated Demonstration Data Products

The Census Bureau has released a new set of demonstration data products that show how its new disclosure avoidance strategy (DAS) will impact the quality of its 2020 Census data products (see previous coverage). The Census Bureau is releasing a set of benchmark metrics to track the impact of the ongoing development and improvements to its privacy-protecting algorithm on data accuracy. These metrics will be updated every six weeks so data users can track the ongoing improvements Bureau staff are making to the algorithm. In addition, the Census Bureau has released a set of privacy-protected microdata files (PPMF) to allow users to assess the impact of the disclosure avoidance strategy for their own specific use cases. The Bureau notes that “while the data in the PPMFs look like individual records, all of the data are privacy-protected. The microdata records generated by the DAS ensure respondent privacy through the application of differentially private statistical noise. The microdata included in the PPMF do not include any actual census responses.”

Data users can submit feedback or questions to the Census Bureau by emailing More information about the new data products is available on the Census Bureau website.

Back to this issue’s table of contents.

Tagged with: , , ,
Posted in Issue 14 (July 7), Update, Volume 39 (2020)

Census Bureau Releases Update on 2020 Census Disclosure Avoidance Strategy

On March 13, John Abowd, the Census Bureau’s Chief Scientist, and Victoria Velkoff, the Bureau’s Associate Director for Demographic Programs, published a blog post to give a status update on the Census Bureau’s strategy for avoiding disclosure of personal information as a result of data released from the 2020 Census. The Bureau had previously announced that it planned to implement the move to a standard called “differential privacy” (which uses an algorithm to injects precise amounts of random noise into data until it reaches a desired threshold of obfuscation). It released demonstration data products to give users a chance to see how 2010 Census data would have been affected under these conditions and sponsored a National Academies workshop to collect feedback (see COSSA’s article on this issue in ASA Footnotes).

In their blog post, Abowd and Velkoff note that feedback from the Academies workshop and elsewhere identified “unacceptable” errors created during the processing phase of the disclosure avoidance process: “To put it succinctly, the resounding message was that this interim version of the DAS [disclosure avoidance strategy] is generating significant error in the data that we need to resolve prior to the production of the 2020 Census Data Products.”

Abowd and Velkoff list several potential solutions that Census Bureau staff are exploring, including “changes to the geographic hierarchy used within the DAS, alternative estimation techniques to correct for the known biases of Non-Negative Least Squares optimization, and multiphase estimation of key statistics during post-processing.” They share that the Bureau is compiling “fitness-for-use” measures to evaluate the effectiveness of the solutions developed for different use-cases and situations. COSSA will continue to share information on these measures and solutions as details are released in the coming months.

Back to this issue’s table of contents.

Tagged with: , , ,
Posted in Issue 6 (March 17), Update, Volume 39 (2020)

Census Bureau Releases “Demonstration” Decennial Data Products, Working with National Academies to Collect Public Input

On October 29, the Census Bureau released a set of demonstration data products that show how the privacy measures planned for 2020 Census data would have applied to data from the 2010 Census. In a blog post, Census Bureau Chief Scientist John Abowd and Associate Director for Demographic Programs Victoria Velkoff assert that the “methods we used to protect the 2010 Census and earlier statistics can no longer adequately defend against today’s privacy threats.” They describe the new disclosure avoidance techniques planned to protect 2020 Census data and invite researchers and data users to experiment with the new demonstration products and determine if they meet their needs.

To assess the adequacy of the proposed data products, the Census Bureau is sponsoring a workshop on the demonstration data products on December 11-12 conducted by the National Academies of Sciences, Engineering, and Medicine’s Committee on National Statistics (CNSTAT). CNSTAT is requesting public comments from users of decennial data products—regardless of whether the demonstration products apply to their work—to inform the agenda of the workshop and to inform the Census Bureau’s final decision making about the 2020 products. CNSTAT seeks detailed input from data users on whether the demonstration products would be adequate, how critical the data products are to their research, how comparable the new products are to the 2010 products, and how to address the tension between privacy and accuracy of 2020 Census data. Full details on information requested and how to submit comments are available on the CNSTAT website. While there is no hard deadline for comments, comments received by December 4 will be the most helpful for the workshop organizers’ planning.

Back to this issue’s table of contents.

Tagged with: , , , , ,
Posted in Issue 22 (November 12), Update, Volume 38 (2019)


Click here to subscribe to the COSSA Washington Update, our biweekly newsletter.


Looking for something from a previous issue of the COSSA Washington Update? Try our archive.


Browse by Month