-
Integrating Multiple U.S. Census Bureau Data Assets to Create Standardized Profiles of Program Participants
January 2026
Working Paper Number:
CES-26-01
The Foundations for Evidence-Based Policymaking Act of 2018 (Evidence Act) directed federal agencies to systematically use data when making policy decisions. In response, the U.S. Census Bureau established the Evidence Group within its Center for Economic Studies (CES). With an interdisciplinary team of economists, sociologists, and statisticians, the Evidence Group can support the broader federal government in their efforts to use existing data to improve program operations without increasing respondent burden. For federal agencies administering social safety net and business assistance programs in particular, the team provides a no-cost evidence-building service that links program records to Census Bureau data assets and creates a series of standardized tables describing participants, their economic outcomes prior to program entry, and the communities where they live. These tables provide partner agencies with the detailed information they need to better understand their participants and potentially make their programs more accountable and effective in reaching their target populations. In this working paper, we describe the standardized tables themselves as well as the data assets available at the Census Bureau to create these tables, the data files produced by the table production process, and the methodology used to merge and harmonize data on participants and subsequently calculate unbiased and accurate estimates. We conclude with a brief discussion of steps taken to ensure confidentiality and data security. This documentation is intended to facilitate proper use and understanding of the standardized tables by partner agencies as well as researchers who are interested in leveraging these tools to explore characteristics of their samples of interest.
View Full
Paper PDF
-
School-Based Disability Identification Varies by Student Family Income
December 2025
Authors:
Quentin Brummet,
Andrew Penner,
Emily Penner,
Leah R. Clark,
Michelle Spiegel,
Paul Y. Yoo,
Paul Hanselman,
Nicholas J. Ainsworth,
Christopher Cleveland,
Jacob Hibel,
Andrew Saultz,
Juan Camilo Cristancho
Working Paper Number:
CES-25-74
Currently, 18 percent of K-12 students in the United States receive additional supports through the identification of a disability. Socioeconomic status is viewed as central to understanding who gets identified as having a disability, yet limited large-scale evidence examines how disability identification varies for students from different income backgrounds. Using unique data linking information on Oregon students and their family income, we document pronounced income-based differences in how students are categorized for two school-based disability supports: special education services and Section 504 plans. We find that a quarter of students in the lowest income percentile receive supports through special education, compared with less than seven percent of students in the top income percentile. This pattern may partially reflect differences in underlying disability-related needs caused by poverty. However, we find the opposite pattern for 504 plans, where students in the top income percentiles are two times more likely to receive 504 plan supports. We further document substantial variation in these income-based differences by disability category, by race/ethnicity, and by grade level. Together, these patterns suggest that disability-related needs alone cannot account for the income-based differences that we observe and highlight the complex ways that income shapes the school and family processes that lead to variability in disability classification and services.
View Full
Paper PDF
-
Gifted Identification Across the Distribution of Family Income
December 2025
Authors:
Quentin Brummet,
Andrew Penner,
Emily Penner,
Leah R. Clark,
Michelle Spiegel,
Paul Hanselman,
Nicholas J. Ainsworth,
Aaron J. Ainsworth,
Christopher Cleveland,
Jacob Hibel,
Andrew Saultz
Working Paper Number:
CES-25-73
Currently, 6.1 percent of K-12 students in the United States receive gifted education. Using education and IRS data that provide information on students and their family income, we show pronounced differences in who schools identify as gifted across the distribution of family income. Under 4 percent of students in the lowest income percentile are identified as gifted, compared with 20 percent of those in the top income percentile. Income-based differences persist after accounting for student test scores and exist across students of different sexes and racial/ethnic groups, underscoring the importance of family resources for gifted identification in schools.
View Full
Paper PDF
-
The Hidden Costs of Decline: Health Disparities in America's Diminishing Micropolitan Areas
September 2025
Working Paper Number:
CES-25-70
This study examines the relationship between long-term population change and health outcomes in U.S. micropolitan areas, with a focus on life expectancy and mortality disparities. Using a county typology based on the historical population trajectories of micropolitan cores from 1940 to 2020, this analysis reveals that health outcomes are substantially worse in places that experienced sustained decline. These disparities persist even after controlling for demographic and socioeconomic characteristics, suggesting that population loss itself is a key driver of poor public health. Declining micropolitan areas are older, less educated, and report high rates of behavioral risk factors, including smoking, excessive drinking, and physical inactivity. By linking historical demographic trends to tract-level data, this analysis highlights the distinct challenges facing the urban cores of shrinking micropolitan areas. Population decline emerges not only as a demographic trend, but as a marker of structural disadvantage with measurable consequences for community health.
View Full
Paper PDF
-
Optimal Stratified Sampling for Probability-Based Online Panels
September 2025
Working Paper Number:
CES-25-69
Online probability-based panels have emerged as a cost-efficient means of conducting surveys in the 21st century. While there have been various recent advancements in sampling techniques for online panels, several critical aspects of sampling theory for online panels are lacking. Much of current sampling theory from the middle of the 20th century, when response rates were high, and online panels did not exist. This paper presents a mathematical model of stratified sampling for online panels that takes into account historical response rates and survey costs. Through some simplifying assumptions, the model shows that the optimal sample allocation for online panels can largely resemble the solution for a cross-sectional survey. To apply the model, I use the Census Household Panel to show how this method could improve the average precision of key estimates. Holding fielding costs constant, the new sample rates improve the average precision of estimates between 1.47 and 17.25 percent, depending on the importance weight given to an overall population mean compared to mean estimates for racial and ethnic subgroups.
View Full
Paper PDF
-
Manufacturing Dispersion: How Data Cleaning Choices Affect Measured Misallocation and Productivity Growth in the Annual Survey of Manufactures
September 2025
Working Paper Number:
CES-25-67
Measurement of dispersion of productivity levels and productivity growth rates across businesses is a key input for answering a variety of important economic questions, such as understanding the allocation of economic inputs across businesses and over time. While item nonresponse is a readily quantifiable issue, we show there is also misreporting by respondents in the Annual Survey of Manufactures (ASM). Aware of these measurement issues, the Census Bureau edits and imputes survey responses before tabulation and dissemination. However, edit and imputation methods that are suitable for publishing aggregate totals may not be suitable for estimating other measures from the microdata. We show that the methods used dramatically affect estimates of productivity dispersion, allocative efficiency, and aggregate productivity growth. Using a Bayesian approach for editing and imputation, we model the joint distributions of all variables needed to estimate these measures, and we quantify the degree of uncertainty in the estimates due to imputations for faulty or missing data.
View Full
Paper PDF
-
'Class of Customer' Question from the US Economic Census
September 2025
Working Paper Number:
CES-25-66
The Economic Census (EC) collects detailed information on the class of customers served by establishments'for example, the share of an establishment's sales to other businesses or to government entities'for a subset of sectors in the economy. In this paper, we evaluate the data from the 'Class of Customer' question from the EC, with a particular focus on sales to the government. These data have seldom been used in empirical research and are unique in that they enable researchers to link establishment-level Census data with information on government procurement.
We compile and analyze large volumes of publicly available tabulated data about the class of customer question over time. Using these data, we document three main findings. First, total sales to government from establishments covered by the class of customer question account for approximately 4 percent of GDP'just under half of total government procurement as measured in the national accounts. Second, the sectoral distribution of government expenditure is significantly different from that of private sector spending. Certain industries, such as Construction and Professional, Scientific, and Technical Services, account for a much larger share of government expenditure relative to private sector expenditure. Third, sales to the government make up a substantial portion of total sales in several sectors'for instance, 70 percent in Facilities Support Services, 30 percent in Waste Treatment and Disposal, and 17 percent in Construction. Finally, we use the microdata to examine nonresponse rates to the class of customer question across establishments based on the number of employees.
View Full
Paper PDF
-
Job Tasks, Worker Skills, and Productivity
September 2025
Authors:
John Haltiwanger,
Lucia Foster,
Cheryl Grim,
Zoltan Wolf,
Cindy Cunningham,
Sabrina Wulff Pabilonia,
Jay Stewart,
Cody Tuttle,
G. Jacob Blackwood,
Matthew Dey,
Rachel Nesbit
Working Paper Number:
CES-25-63
We present new empirical evidence suggesting that we can better understand productivity dispersion across businesses by accounting for differences in how tasks, skills, and occupations are organized. This aligns with growing attention to the task content of production. We link establishment-level data from the Bureau of Labor Statistics Occupational Employment and Wage Statistics survey with productivity data from the Census Bureau's manufacturing surveys. Our analysis reveals strong relationships between establishment productivity and task, skill, and occupation inputs. These relationships are highly nonlinear and vary by industry. When we account for these patterns, we can explain a substantial share of productivity dispersion across establishments.
View Full
Paper PDF
-
Estimating the Graduate Coverage of Post-Secondary Employment Outcomes
September 2025
Working Paper Number:
CES-25-61
This paper proposes a new methodology for estimating the coverage rate of the Post-Secondary Employment Outcomes data product (PSEO), both as a share of new graduates and as a share of total working-age degree holders in the United States. This paper also assesses how representative PSEO is of the broader population of college graduates across an array of institutional and individual characteristics.
View Full
Paper PDF
-
A Simulated Reconstruction and Reidentification Attack on the 2010 U.S. Census
August 2025
Authors:
Lars Vilhuber,
John M. Abowd,
Ethan Lewis,
Nathan Goldschlag,
Michael B. Hawes,
Robert Ashmead,
Daniel Kifer,
Philip Leclerc,
Rolando A. Rodríguez,
Tamara Adams,
David Darais,
Sourya Dey,
Simson L. Garfinkel,
Scott Moore,
Ramy N. Tadros
Working Paper Number:
CES-25-57
For the last half-century, it has been a common and accepted practice for statistical agencies, including the United States Census Bureau, to adopt different strategies to protect the confidentiality of aggregate tabular data products from those used to protect the individual records contained in publicly released microdata products. This strategy was premised on the assumption that the aggregation used to generate tabular data products made the resulting statistics inherently less disclosive than the microdata from which they were tabulated. Consistent with this common assumption, the 2010 Census of Population and Housing in the U.S. used different disclosure limitation rules for its tabular and microdata publications. This paper demonstrates that, in the context of disclosure limitation for the 2010 Census, the assumption that tabular data are inherently less disclosive than their underlying microdata is fundamentally flawed. The 2010 Census published more than 150 billion aggregate statistics in 180 table sets. Most of these tables were published at the most detailed geographic level'individual census blocks, which can have populations as small as one person. Using only 34 of the published table sets, we reconstructed microdata records including five variables (census block, sex, age, race, and ethnicity) from the confidential 2010 Census person records. Using only published data, an attacker using our methods can verify that all records in 70% of all census blocks (97 million people) are perfectly reconstructed. We further confirm, through reidentification studies, that an attacker can, within census blocks with perfect reconstruction accuracy, correctly infer the actual census response on race and ethnicity for 3.4 million vulnerable population uniques (persons with race and ethnicity different from the modal person on the census block) with 95% accuracy. Having shown the vulnerabilities inherent to the disclosure limitation methods used for the 2010 Census, we proceed to demonstrate that the more robust disclosure limitation framework used for the 2020 Census publications defends against attacks that are based on reconstruction. Finally, we show that available alternatives to the 2020 Census Disclosure Avoidance System would either fail to protect confidentiality, or would overly degrade the statistics' utility for the primary statutory use case: redrawing the boundaries of all of the nation's legislative and voting districts in compliance with the 1965 Voting Rights Act.
View Full
Paper PDF
