Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2010 Fall;74(3):551-569.
doi: 10.1093/poq/nfq033. Epub 2010 Aug 13.

The Polls-Review: Inaccurate Age and Sex Data in the Census Pums Files: Evidence and Implications

J Trent Alexander, Michael Davern, Betsey Stevenson

The Polls-Review: Inaccurate Age and Sex Data in the Census Pums Files: Evidence and Implications

J Trent Alexander et al. Public Opin Q. 2010 Fall.

Abstract

We discover and document errors in public-use microdata samples ("PUMS files") of the 2000 Census, the 2003-2006 American Community Survey, and the 2004-2009 Current Population Survey. For women and men age 65 and older, age- and sex-specific population estimates generated from the PUMS files differ by as much as 15 percent from counts in published data tables. Moreover, an analysis of labor-force participation and marriage rates suggests the PUMS samples are not representative of the population at individual ages for those age 65 and over. PUMS files substantially underestimate labor-force participation of those near retirement age and overestimate labor-force participation rates of those at older ages. These problems were an unintentional byproduct of the misapplication of a newer generation of disclosure-avoidance procedures carried out on the data. The resulting errors in the public-use data could significantly impact studies of people age 65 and older, particularly analyses of variables that are expected to change by age.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Population estimates from 2000 five-percent Census PUMS as a percentage of Census 2000 published data. Sources: Published population counts are from Census 2000 Summary File 4, Table PCT3 (http://factfinder.census.gov); population estimates are calculated using Census 2000 five-percent sample, IPUMS-USA (http://usa.ipums.org/usa/).
Figure 2
Figure 2
Population estimates from ACS 2006 PUMS as a percentage of ACS 2006 published data. Sources: Published data population counts are from 2006 ACS Table B01001 (http://factfinder.census.gov); population estimates are calculated using 2006 ACS PUMS, IPUMS-USA (http://usa.ipums.org/usa/).
Figure 3
Figure 3
ACS PUMS estimates as a percentage of ACS PUMS published estimates, women only. Sources: Published population counts are from ACS Table B01001 (2004–2007); ACS Table P004 (2002–2003); 2001 Supplementary Survey Table P004 (http://factfinder.census.gov); ACS PUMS estimates are calculated using 2001–2008 ACS PUMS, IPUMS-USA (http://usa.ipums.org/usa/).
Figure 4
Figure 4
Ratio of men to women in CPS PUMS, ACS PUMS, and published data. Sources: Ratios are calculated from published population counts of men and women taken from ACS Table B01001 (2004–2008); ACS Table P004 (2002–2003); 2001 Supplementary Survey Table P004 (http://factfinder.census.gov); 2001–2008 ACS PUMS, IPUMS-USA (http://usa.ipums.org/usa/); 2001–2009 CPS ASEC samples, IPUMS-CPS (http://cps.ipums.org/cps/).
Figure 5
Figure 5
Labor-force participation estimates by age and sex, 2000 five-percent PUMS as a percentage of 2000 Census published data. Sources: Labor-force population counts are taken from Census 2000 Summary File 4, Table PCT70 (http://factfinder.census.gov); labor-force estimates are calculated using Census 2000 five-percent sample, IPUMS-USA (http://usa.ipums.org/usa/).
Figure 6
Figure 6
Percentage of women who were married in the 2006 and 2007 ACS. Sources: Percent of women married is calculated using the 2006 and 2007 ACS PUMS, IPUMS-USA (http://usa.ipums.org/usa/). Percent married includes only those married with a spouse present. Similar results are obtained for calculations that included spouses who are absent.
See this image and copyright information in PMC

References

    1. Blewett Lynn A., Davern Michael. Distributing State Children’s Health Insurance Funds: A Critical Review of the Design and Implementation of the Funding Formula. Journal of Health Politics, Policy, and Law. 2007;32(3):415–55. - PubMed
    1. Census 2000 Advisory Committee The Public Use Microdata Samples of the U.S. Census: Research Applications and Privacy Issues. Prepared for Census 2000 Users’ Conference on PUMS Data. 2000 Available at http://usa.ipums.org/usa/2000PUMSReport_full.pdf.
    1. Glied Sherry, Remler Dahlia K., Zivin Joshua Graff. Inside the Sausage Factory: Improving Estimates of the Effects of Health Insurance Expansion Proposals. Milbank Quarterly. 2002;80(4):603–35. - PMC - PubMed
    1. King Miriam, Ruggles Steven, Alexander Trent, Leicach Donna, Sobek Matthew. Integrated Public Use Microdata Series, Current Population Survey: Version 2.0. [Machine-readable database] Minneapolis: Minnesota Population Center [producer and distributor]; 2009. Available at http://cps.ipums.org/cps/
    1. Office of Management and Budget Statistical Policy Working Paper 31: Measuring and Reporting Sources of Error in Surveys. Statistical Policy Office, Office of Information and Regulatory Affairs. 2001 Jul; Available at http://www.fcsm.gov/01papers/SPWP31_final.pdf.