The Annals of Applied Statistics

Incompatibility of trends in multi-year estimates from the American Community Survey

Tucker McElroy

Full-text: Open access

Abstract

The American Community Survey (ACS) provides one-year (1y), three-year (3y) and five-year (5y) multi-year estimates (MYEs) of various demographic and economic variables for each “community,” although the 1y and 3y may not be available for communities with a small population. These survey estimates are not truly measuring the same quantities, since they each cover different time spans. Using some simplistic models, we demonstrate that comparing different period-length MYEs results in spurious conclusions about trend movements. A simple method utilizing weighted averages is presented that reduces the bias inherent in comparing trends of different MYEs. These weighted averages are nonparametric, require only a short span of data, and are designed to preserve polynomial characteristics of the time series that are relevant for trends. The basic method, which only requires polynomial algebra, is outlined and applied to ACS data. In some cases there is an improvement to comparability, although a final verdict must await additional ACS data. We draw the conclusion that MYE data is not comparable across different periods.

Article information

Source
Ann. Appl. Stat., Volume 3, Number 4 (2009), 1493-1504.

Dates
First available in Project Euclid: 1 March 2010

Permanent link to this document
https://projecteuclid.org/euclid.aoas/1267453949

Digital Object Identifier
doi:10.1214/09-AOAS259

Mathematical Reviews number (MathSciNet)
MR2752143

Zentralblatt MATH identifier
1185.62199

Keywords
Filtering nonstationary time series weighted averages

Citation

McElroy, Tucker. Incompatibility of trends in multi-year estimates from the American Community Survey. Ann. Appl. Stat. 3 (2009), no. 4, 1493--1504. doi:10.1214/09-AOAS259. https://projecteuclid.org/euclid.aoas/1267453949


Export citation

References

  • Alexander, C. (1998). Recent developments in the American Community Survey. In Proceedings of the Survey Research Methods Section 92–100. Amer. Statist. Assoc., Alexandria, VA.
  • Alexander, C. (2001). Still rolling: Leslie Kish’s “rolling samples” and the American Community Survey. In Proceedings of Statistics Canada Symposium 2001, Achieving Data Quality in a Statistical Agency: A Methodological Perspective, Statistics Canada: Ottawa, Ontario, Canada.
  • Beaghen, M. and Weidman, L. (2008). Statistical issues of interpretation of the American Community Survey’s one-, three-, and five-year period estimates. U.S. Census Bureau, 2008 American Community Survey Research Memorandum Series #ACS08-R-4.
  • Bell, W. (1998). Borrowing information over time in small area estimation: Thoughts with reference to the American Community Survey. Unpublished paper presented at the American Community Survey workshop, September 13, 1998, Michael Cohen (workshop study director), Committee on National Statistics, Commission on Behavioral and Social Sciences and Education, National Research Council, Washington, DC.
  • Breidt, F. (2007). Alternatives to the multiyear period estimation strategy for the American Community Survey. In Using the American Community Survey: Benefits and Challenges, National Research Council, Panel on the Functionality and Usability of Data from the American Community Survey (C. F. Citro and G. Kalton, ed.) Appendix C. The National Academies Press, Washington, DC.
  • Brockwell, P. and Davis, R. (1991). Introduction to Time Series and Forecasting. Springer, New York.
  • Census Bureau, U.S. (2006). Design and methodology, American Community Survey. Technical Paper 67. Available at: http://www.census.gov/acs/www/Downloads/tp67.pdf.
  • Citro, C. and Kalton, G., eds. (2007). Using the American Community Survey: Benefits and Challenges, National Research Council, Panel on the Functionality and Usability of Data from the American Community Survey. The National Academies Press, Washington, DC.
  • Engle, R. and Granger, C. (1987). Co-integration and error correction: Representation, estimation, and testing. Econometrica 55 251–276.
  • Fay, R. (2005). Model-assisted estimation for the American Community Survey. In Proceedings of the 2005 Joint Statistical Meetings on CD-ROM 3016–3023. Amer. Statist. Assoc., Alexandria, VA.
  • Fay, R. (2006). Using administrative records with model-assisted estimation for the American Community Survey. In Proceedings of the 2006 Joint Statistical Meetings on CD-ROM 2995–3001. Amer. Statist. Assoc., Alexandria, VA.
  • Fay, R. (2007). Imbedding model-assisted estimation into ACS estimation. In Proceedings of the 2007 Joint Statistical Meetings on CD-ROM 2946–2953. Amer. Statist. Assoc., Alexandria, VA.
  • Granger, C. (2004). Time series analysis, cointegration, and applications. Amer. Econom. Rev. 94 421–425.
  • Kish, L. (1981). Using Cumulated Rolling Samples to Integrate Census and Survey Operations of the Census Bureau. U.S. Government Printing Office, Washington, DC.
  • Kish, L. (1998). Space/time variations and rolling samples. Journal of Official Statistics 14 31–46.
  • McElroy, T. (2009). Supplement to “Incompatibility of Trends in Multi-Year Estimates from the American Community Survey.” DOI: 10.1214/09-AOAS259SUPP.
  • Starsinic, M. and Tersine, A. (2007). Analysis of variance estimates from American Community Survey multiyear estimates. In Proceedings of the 2007 Joint Statistical Meetings on CD-ROM 3011–3017. Amer. Statist. Assoc., Alexandria, VA.
  • Tersine, A. and Asiala, M. (2007). Methodology for the production of American Community Survey multiyear estimates. In Proceedings of the 2007 Joint Statistical Meetings on CD-ROM 3018–3023. Amer. Statist. Assoc., Alexandria, VA.
  • Torrieri, N. (2007). America is changing, and so is the census: The American Community Survey. Amer. Statist. 61 16–21.

Supplemental materials