Category Archives: Blog

Items in this category show up on apdu.org/blog

APDU Member Post: Assessing the Use of Differential Privacy for the 2020 Census: Summary of What We Learned from the CNSTAT Workshop

By:

Joseph Hotz, Duke University

Joseph Salvo, New York City Department of City Planning

Background

The mission of the Census Bureau is to provide data that can be used to draw a picture of the nation, from the smallest towns and villages to the neighborhoods of the largest cities. Advances in computer science, better record linkage technology, and the proliferation of large public data sets have increased the risk of disclosing information about individuals in the census.

To assess these threats, the Census Bureau conducted a simulated attack, reconstructing person-level records from published 2010 Census tabulations using its previous Disclosure Avoidance System (DAS) that was based in large part on swapping data records across households and localities. When combined with information in commercial and publicly available databases, these reconstructed data suggested that 18 percent of the U.S. population could be identified with a high level of certainty. The Census Bureau concluded that, if adopted for 2020, the 2010 confidentiality measures would lead to a high risk of disclosing individual responses violating Title 13 of the U.S. Code, the law that prohibits such disclosures.

Thus, the Census Bureau was compelled to devise new methods to protect individual responses from disclosure. Nonetheless, such efforts – however well-intentioned – may pose a threat to the content, quality and usefulness of the very data that defines the Census Bureau’s mission and that demographers and statisticians rely on to draw a portrait of the nation’s communities.

The Census Bureau’s solution to protecting privacy is a new DAS based on a methodology referred to as Differential Privacy (DP). In brief, it functions by leveraging the same database reconstruction techniques that were used to diagnose the problem in the previous system: the 2020 DAS synthesizes a complete set of person- and household-level data records based on an extensive set of tabulations to which statistical noise has been added. Viewed as a continuum between total noise and total disclosure, the core of this method involves a determination regarding the amount of privacy loss or e, that can be accepted without compromising data privacy while ensuring the utility of the data. The key then becomes “where to set the dial”—set e too low and privacy is ensured at the cost of utility, but set e too high and utility is ensured but privacy in compromised. In addition to the overall level of e, its allocation over the content and detail of the census tabulations for 2020 is important. For example, specific block-level tabulations needed for redistricting may require a substantial allocation of the privacy-loss budget to achieve acceptable accuracy for this key use, but the cost is that accuracy of other important data (including for blocks, such as persons per household) will likely be compromised. Finding ways to resolve these difficult tradeoffs represents a serious challenge for the Census Bureau and users of its data.

The CNSTAT Workshop

In order to test how well this methodology worked in terms of the accuracy of noise-infused data, the Census Bureau issued special 2010 Census files subject to the 2020 DAS. The demonstration files applied the 2020 Census DAS to the 2010 Census confidential data — that is, the unprotected data from the 2010 Census that are not publicly available. The demonstration data permit scientific inquiry into the impact of DP. In addition, the Census commissioned the Committee on National Statistics (CNSTAT) of the National Academies of Sciences, Engineering and Medicine to host a 2-day Workshop on 2020 Census Data Products: Data Needs and Privacy Considerations, held in Washington, DC, on December 11-12, 2019. The two-fold purpose of the workshop was:

  • To assess the utility of the tabulations in the 2010 Demonstration Product for specific use cases/real-life data applications.
  • Generate constructive feedback for the Census Bureau that will be useful in setting the ultimate privacy loss budget and on the allocation of shares of that budget over the broad array of possible tables and geographic levels.

We both served as the co-chairs of the Committee that planned the Workshop. The Workshop brought together a diverse group of researchers who presented findings for a wide range of use cases that relied on data from past censuses.

These presentations, and the discussions surrounding them, provided a new set of evidence-based findings on the potential consequences of the Census Bureau’s new DAS. In what follows, we summarize “what we heard” or learned from the Workshop. This summary is ours alone; we do not speak for the Workshop’s Planning Committee, CNSTAT, or the Census Bureau. Nonetheless, we hope that the summary below provides the broader community of users of decennial census data with a better understanding of some of the potential consequences of the new DAS for the utility of the 2020 Census data products. Moreover we hope it fosters an on-going dialogue between the user community and the Census Bureau on ways to help ensure that data from the 2020 Census are of high quality, while still safeguarding the privacy and confidentiality of individual responses.

What We Heard

  • Population counts for some geographic units and demographic characteristics were not adversely affected by Differential Privacy (DP). Based on results presented at the Workshop, it appears that there were not, in general, differences in population counts between the 2010 demonstration file at some levels of geography. For the nation as a whole and for individual states, the Census’s algorithm, ensured that that counts were exact, i.e., counts at these levels were held invariant by design. Furthermore, the evidence presented also indicated that the counts in the demonstration products and those for actual 2010 data were not very different for geographic areas that received direct allocations of the privacy budget, including most counties, metro areas (aggregates of counties) and census tracts. Finally, for these geographic areas, the population counts by age in the demonstration products were fairly accurate when using broader age groupings (5-10 year groupings or broader ones), as well as for some demographic characteristics (e.g., for non-Hispanic whites, and sometimes for Hispanics).
  • Concerns with data for small geographic areas and units and certain population groups. At the same time, evidence presented at the Workshop indicated that most data for small geographic areas – especially census blocks – are not usable given the privacy-loss level used to produce the demonstration file. With some exceptions, applications demonstrated that the variability of small-area data (i.e., blocks, block groups, census tracts) compromised existing analyses. Many Workshop participants indicated that a larger privacy loss budget will be needed for the 2020 Census products to attain a minimum threshold of utility for small-area data. Alternatively, compromises in the content of the publicly-released products will be required to ensure greater accuracy for small areas.

The Census did not include a direct allocation of the privacy-loss budget 2010 demonstration file to all geographic areas, such as places and county subdivisions, or to detailed race groups, such as American Indians. As noted by numerous presenters, these units and groups are very important for many use cases, as they are the basis for political, legal, and administrative decision-making. Many of these cases involve small populations and local officials rely on the census as a key benchmark; in many cases, it defines who they are.

  • Problems for temporal consistency of population counts. Several presentations highlighted the problem of temporal inconsistency of counts, i.e., from one census to the next using DP. The analyses presented at the Workshop suggested that comparisons of 2010 Census data under the old DAS to 2020 Census data under DP may well show inexplicable trends, up or down, for small geographic areas and population groups. (And comparisons of 2030 data under DP with 2020 data under DP may also show inconsistencies over time). For example, when using counts as denominators to monitor disease rates or mortality at finer levels of geography by race, by old vs young, etc., the concern is that it will be difficult to determine real changes in population counts, and, thus, real trends in disease or mortality rates, versus the impact of using DP.
  • Unexpected issues with the post-processing of the proposed DAS. The Top-Down algorithm (TDA) employed by the Census Bureau in constructing the 2010 demonstration data produced histograms at different levels of geography that are, by design, unbiased —but they are not integers and include negative counts. The post-processing required to produce a microdata file capable of generating tabulations of persons and housing units with non-negative integer counts produced biases that are responsible for many anomalies observed in the tabulations. These are both systematic and problematic for many use cases. Additional complications arise from the need to hold some data cells invariant to change (e.g., total population at the state level) and from the separate processing of person and housing unit tabulations.

The application of DP to raw census data (the Census Edited File [CEF]) produces estimates that can be used to model error, but the post-processing adds a layer of complexity that may be very difficult to model, making the creation of “confidence intervals” problematic.

  • Implications for other Census Bureau data products. Important parts of the planned 2020 Census data products cannot be handled by the current 2020 DAS and TDA approach. They will be handled using different but as-yet-unspecified methods that will need to be consistent with the global privacy-loss budget for the 2020 Census. These products were not included in the demonstration files and were out of scope for the Workshop. Nonetheless, as noted by several presenters and participants in the Workshop, these decisions raise important issues for many users and use cases going forward. To what extent will content for detailed race/Hispanic/nationality groups be available, especially for American Indian and Alaska Native populations? To what degree will data on household-person combinations and within-household composition be possible under DAS?

For example, while the Census Bureau has stated that 2025 will be the target date for the possible application of DP to the ACS, they indicated that the population estimates program will be subject to DP immediately following 2020. These estimates would then then be used for weighting and post-stratification adjustments to the ACS.

  • Need plan to educate and provide guidance for users of the 2020 Census products. Regardless of what the Census Bureau decides with respect to ε and how it is allocated across tables, the Workshop participants made clear that a major re-education plan for data users’ needs to be put in place, with a focus on how best to describe key data and the shortcomings imposed by privacy considerations and error in general. Furthermore, as many at the Workshop voiced, such plans must be in place when the 2020 Census products are released to minimize major disruptions to and problems with the myriad uses made of these data and the decisions based on them.
  • Challenging privacy concerns and their potential consequences for the success of the 2020 Census. Finally, the Workshop included a panel of experts on privacy. These experts highlighted the disclosure risks associated with advances in linking information in public data sources, like the decennial census, with commercial data bases containing information on bankruptcies and credit card debt, driver licenses, and federal, state and local government databases on criminal offenses, public housing, and even citizenship status. While there are federal and state laws in place to protect the misuse of these governmental databases as well as the census (i.e., Title 13), their adequacy is challenged by advances in data linkage technologies and algorithms. And, as several panelists noted, these potential disclosure risks may well undercut the willingness of members of various groups – including immigrants (whether citizens or not), individuals violating public housing codes, or those at risk of domestic violence – to participate in the 2020 Census.

The Census Bureau has recently stated that it plans to have CNSTAT organize a follow-up set of expert meetings to “document improvements and overcome remaining challenges in the 2020 DAS.” In our view, such efforts, however they are organized, need to ensure meaningful involvement and feedback from the user community. Many within that community remain skeptical of the Bureau’s adoption of Differential Privacy and its consequences for their use cases. So, not only is it important that Census try to address the various problems identified by Workshop presenters and others who evaluated the 2010 demonstration products, it also is essential that follow-up activities are designed to involve a broader base of user communities in a meaningful way.

We encourage members of the census data user community to become engaged in this evaluation process, agreeing, if asked, to become involved in these follow-up efforts. Such efforts will be essential to help ensure that the Census Bureau meets its dual mandate of being the nation’s leading provider of quality information about its people and economy while safeguarding the privacy of those who provide this information.

2020 APDU Conference Call for Proposals

#Trending in 2020: Data Privacy, Accuracy, and Access

APDU is welcoming proposals on any topic related to the privacy, accuracy, and access of public data.  Proposals can be for a single presentation or panel, whether based on a particular project, data practice, or formal paper.  In keeping with the theme of the conference, our interest is in highlighting the breadth of public data to both producers and consumers of public data.  Some examples of topics might cover:

  • Privacy
    • Differential privacy and tiered data
    • State/local data privacy issues
    • Data Suppression
    • Corporate data privacy (ex. Facebook’s use of differential privacy)
  • Accuracy
    • Machine learning and the use of programming languages
    • How data accuracy will affect redistricting or federal allocations
    • Federal agencies data protection actions’ impact on other agency data
    • Synthetic or administrative data
    • Decennial Census
      • Citizenship question
      • Complete Count Committee
  •  Access
    • Future public data and policy developments
    • Current availability of public data (health, education, the economy, energy, the environment, climate, and other areas)
    • Federal statistical microdata such as ResearchDataGov
    • Federal Data Strategy updates and advocacy

Proposal Deadline: February 28, 2020.

You may submit ideas for a single presentation or a full panel (three presenters, plus a moderator). However, it is possible that we will accept portions of panel submissions to combine with other presenters. Submissions will be evaluated on the quality of work, relevance to APDU Conference attendees, uniqueness of topic and presenter, and thematic fit.

Please submit your proposal using the Survey Monkey collection window below.  Proposals will need to be submitted by members of APDU, and all presenters in a panel must register for the conference (full conference registration comes with a free APDU membership).  Proposers will be notified of our decision by March 13, 2020.

About APDU

The Association of Public Data Users (APDU) is a national network that links users, producers, and disseminators of government statistical data. APDU members share a vital concern about the collection, dissemination, preservation, and interpretation of public data.  The conference is in Arlington, VA on July 29-30, 2020, and brings together data users and data producers for conversations and presentations on a wide variety of data and statistical topics.

Create your own user feedback survey

The 2020 Census is Here and Businesses can Help

Companies make strategic decisions every day that rely on accurate data about customers, employees and markets. In the United States, the information gleaned from the decennial population census is an important ingredient in much of the data that companies use to make a range of decisions such as where to locate new stores/facilities, how to market products, and what services to offer customers. The federal government also uses census information to distribute more than $1.5 trillion for programs like roads, education and workforce development that help to strengthen the economy.

The next nationwide count starts in most of the country this March, and companies can help ensure its accuracy by encouraging employees and customers to participate.

Below are a series of resources from the US Census Bureau and ReadyNation that businesses and business membership organizations may find helpful when developing plans to support the count:

  • Newsletter language: Templates for (i) business organizations to engage their membership and (ii) companies to engage their employees.

FY20 Budget Moves from House to Senate

The House has passed appropriations bills to the Senate for FY2020, and there are important developments for statistical agencies. The Census Bureau, Bureau of Labor Statistics (BLS), and Bureau of Economic Analysis (BEA) each received modest to substantial increases in their budgets.

With massive increases in spending by the Census Bureau needed to successfully complete the Decennial Census, Congress appropriated $7.558B for the Census Bureau, with $274M for Current Surveys and Programs and $7.284B for Periodic Censuses and Programs. Importantly, this provides 6.696B for the Decennial Census, which is the minimum requested to complete the count effectively.

BEA received $107.9M, which assumes full funding for efforts to produce annual GDP for Puerto Rico. In addition, Congress apportioned $1.5M to the Outdoor Recreation Satellite Account, and $1M to develop income growth indicators.

After several years of flat funding, the BLS operational budget has been increased to $655M. This includes $587M for necessary expenses for the Bureau of Labor Statistics, including advances or reimbursements to State, Federal, and local agencies and their employees for services rendered, with no more than $68M that may be expended from the Employment Security Administration account in the Unemployment Trust Fund. This number includes $27M for the relocation of the BLS headquarters to the Suitland Federal Center and $13M for investments in BLS such as an annual supplement to the Current Population Survey on contingent work, restoration of certain Local Area Unemployment Statistics data, and development of a National Longitudinal Survey of Youth.

2019 APDU Data Viz Award Winners Announced

APDU received many excellent submissions for the 2019 APDU Data Viz Awards, and our expert review committee has concluded their deliberations. This was a difficult process with such great options to choose from – we are very grateful for the work put into developing and submitting these visualizations.

We would like to thank our review committee for their time and effort in evaluating the submissions. This year, Mark Mather of the Population Reference Bureau and Steven Romalewski of the Center for Urban Research at The Graduate Center/CUNY served on the committee.

Without further ado, the winners this year include:

State and Local Governments

2018 Vintage Population Estimates Dashboard

  • Tim Kuhn, Tennessee State Data Center @ Boyd Center for Business and Economic Research at Univ. Tenn

Federal Government

The Population 65 Years and Older: 2016

Megan Rabe, U.S. Census Bureau

Private Firms

Ididio Career Overviews

  • Kris Heim, Ripe Data
  • Elsa Schaefer, Ripe Data

Researchers and Students

What is in my water?

  • Xindi Hu, Harvard University; Mathematica
  • Paul von Chamier, Harvard University
  • Daniel Tompkins, Harvard University

Congratulations to this year’s winners! Register for the 2019 APDU Annual Conference today to learn from awardees about how they created these excellent visualizations.

APDU Board Member: Why Do We Attend the APDU Conference? Our Business Depends on It.

By: Elizabeth Nash, APDU Board Member

Although many APDU Conference attendees show up to share information about their government agencies’ data products, private companies like PolicyMap have a compelling business reason to attend:  it’s the easiest, most reliable way to learn about what’s in store for data, and data is our lifeblood.

As a board member of APDU, each year I get to put together a session at the conference.  This year, I’m responsible for the first day’s keynote on the Census Bureau’s challenge of balancing privacy and reliability.  I had heard about the so-called “differential privacy” solution to privacy concerns in Census products, but I was eager to learn more—particularly about how privacy concerns will affect the quality of the data products we rely on so heavily at PolicyMap.  We’ll get a chance to hear about the changes in store for Census 2020, the American Community Survey, and other data products.  We’ll also get a glimpse of the implications of those decisions for Census data users down the road.

After the keynote, I’m looking forward to an animated lunchtime roundtable and conversation about the subject, hearing reactions from data users and Census employees on these changes.

Join us on July 9th and 10th in Arlington, VA at the APDU Annual Conference to hear the latest updates from public data providers and users.

 

APDU Board Member: Stay updated on happenings on the Hill

By APDU Board Member Mary Jo Hoeksema

The 2019 Association of Public Data Users (APDU) Annual Conference, “Wide World of Data,” will be the place to be July 9-10!  The meeting will not only offer attendees cutting edge information about advances affecting public data collection, dissemination, and application, but also will provide them with insights into the politics and policies affecting federal statistical agencies and surveys.

The Washington Briefing panel scheduled for July 10 at 9:00 a.m. will be especially informative. A bipartisan panel comprised of three senior congressional staffers from the U.S. House of Representatives and U.S. Senate will discuss the latest developments on Capitol Hill affecting key federal statistical agencies. Mr. Allen Cutler, Professional Staff Member (Majority), U.S. Senate Commerce, Justice, Science Appropriations Subcommittee, will share news regarding funding for the Census Bureau and 2020 Census in Fiscal Year (FY) 2020.  Mr. Trelaine Ito, Legislative Assistant, Senator Brian Schatz (D-HI), will discuss the senator’s interests in 2020 Census operations, the proposed citizenship question on the 2020 Census, and federal data security policy. Ms. Leticia Mederos, Chief of Staff, Congresswoman Rosa DeLauro (D-CT), who chairs the House Labor, Health and Human Services and Education Appropriations Subcommittee, will address how agencies. including the Bureau of Labor Statistics, National Center for Health Statistics, and National Center for Education Statistics, are faring in the FY 2020 appropriations process.  All three panelists will answer questions and offer suggestions about how public data users can be effective advocates for federal statistical agencies and surveys.

Make your plans now to register and attend the 2019 APDU annual meeting! Take advantage of this unique opportunity to hear firsthand from influential policymakers who are working behind-the-scenes to ensure Congress considers the needs and challenges facing a wide range of federal statistical agencies.

APDU Board Member: Learn about new data sources at the APDU Annual Conference

By APDU Board Member Beth Jarosz

If you ask a data user to name public data sources, she might name the decennial census, American Community Survey, National Vital Statistics System, or Current Population Survey. Each of those sources provides robust, timely, accurate public data on important topics like population, housing, and employment. Yet the “big name” public data sources merely hint at the breadth and depth of data available, which includes information on consumer expenditures, healthcare access and utilization, and participation in the arts.

Do you know what share of the American public attends jazz concerts or reads poetry? Attendees will learn about trends in arts and leisure activities from the Survey of Public Participation in the Arts, which tracks arts attendance by detailed event type and state.

Do you know that the Consumer Expenditures Survey is one of the nation’s most complex surveys (by number of variables)? The Consumer Expenditures Survey captures a range of expenditures, incomes, and demographic characteristics. Attendees will learn about what types of questions can, and cannot, be answered with this dataset as well was the geographic detail currently available.

Did you know that the Medicare Current Beneficiary Survey now includes a de-identified public use file? With the public use file analysts can answer questions about Medicare beneficiary insurance status, socio-demographic characteristics, access to care, health status, preventive behaviors, falls, housing characteristics, and experiences with Medicare Advantage.

Join us in Arlington, Va. July 9th and 10th, 2019 at APDU’s Annual Conference to learn more about these, and other, under-the-radar public data sources.

APDU Board Member: Register for the conference today!

By APDU Board Member Sue Copella

Be sure to register for the 2019 APDU Annual Conference! The conference is being held at the Key Bridge Marriott in Arlington, VA on July 9-10. The agenda is set and there are some very exciting speakers. Along with the ever popular Washington Briefing and Data Viz Awards, this year the conference has three main themes: the breath of public data, diverse uses of public data and strengthening and supporting the public data system.

I am also very excited to present this year on the panel discussing Best Ways to Access the Census Data You Need.  As the State Data Center for Pennsylvania I will be presenting on the National State Data Center program and how the states and territories serve the information needs by disseminating demographic and economic data to academic institutions, businesses, non-profits and private citizens.  For the session I will be partnering with the Census Bureau who will be talking about the new dissemination platform and the Federal Statistical Research Data Center.

While I have been a member of APDU for years, last year was the first time I was able to attend the conference since it was held during the summer.  It is a great place for both data users and producers of pubic data to meet and share information on what others are doing in the public data world.  So, if you haven’t had a chance to register, please do so today.

APDU Conference Chair Invites You to the APDU Annual Conference

As 2019 APDU Annual Conference Committee Chair, I would like to cordially invite you to attend what is shaping up to be a fantastic 2019 APDU Annual Conference July 9 – 10 at the Key Bridge Marriott in Arlington, VA.  The 2019 Annual Conference “Wide World of Data” will focus on three main themes this year: the breadth of public data; diverse uses of public data; and what is being done to strengthen and support the public data system.  The conference will once again be an excellent opportunity for users and producers of public data to connect, share information, and learn.

I myself being an economist at the U.S Bureau of Economic Analysis (BEA) am excited as both a producer and user of public data to attend the APDU Annual Conference.  As a producer of public data I am eagerly looking forward to discussions about the pros and cons of using differential privacy with public data as well as the use of machine learning and algorithms with public data.  I want to hear an update about the latest information on the federal statistical agency reorganization proposed by the administration. I am looking forward for the opportunity to meet users of BEA data.

As a user of public data I am excited to hear the latest developments with regard to data from colleagues at the U.S Census Bureau, U.S Bureau of Labor Statistics, the National Endowment for the Arts, the Center for Medicaid and Medicare Services, and the Kentucky Center for Statistics.  I am looking forward to learning how public data is being used to inform decision making from speakers from Georgetown University, Indiana University Purdue University Indianapolis (IUPUI), the George Washington Institute of Public Policy, the University of Alabama Institute for Rural Health Research, the American Association of State Highway and Transportation Officials, and more. Finally, I am especially thrilled by the opportunity to hear from statistical agency leadership including, the Directors of both the U.S. Census Bureau and the U.S. Bureau of Economic Analysis.

I look forward to seeing you at the 2019 APDU Annual Conference.