A quarter-century of statistical research has shown that census coverage surveys, valuable as they are in offering a report card on each decennial census, do not provide usable estimates of geographical differences in coverage. The determining reason is the large number of “doubly missing” people missing both from the census enumeration and from coverage survey estimates. Future coverage surveys should be designed to meet achievable goals, foregoing efforts at spatial specificity. One implication is a sample size no more than about 30,000, setting free resources for controlling processing errors and investing in coverage improvement. Possible integration of coverage measurement with the American Community Survey would have many benefits and should be given careful consideration.
References
[1] Anderson, M. and Fienberg, S. E. (1999). Who Counts? The Politics of Census-Taking in Contemporary America. Russell Sage Foundation, New York.
[2] Breiman, L. (1994). The 1991 census adjustment: Undercount or bad data? (with discussion). Statist. Sci. 9 458–537.
[3] Brown, L. D., Eaton, M. L., Freedman, D. A., Klein, S. P., Olshen, R. A., Wachter, K. W., Wells, M. T. and Ylvisaker, D. (1999). Statistical controversies in Census 2000. Jurimetrics 9 347–375.
[4] Brown, L. D. and Zhao, A. (2007). Alternative formulas for synthetic dual system estimation in the 2000 census. In Probability and Statistics: Essays in Honor of David A. Freedman (D. Nolan and T. Speed, eds.) 90–113. Institute of Mathematical Statistics.
[5] Cork, D. and Voss, P., eds. (2006). Once, Only Once, and in the Right Place. National Academy Press, Washington, D. C.
[6] Fay, R. E. and Thompson, J. H. (1993). The 1990 post enumeration survey: Statistical lessons, in hindsight. In Proceedings, Bureau of the Census Annual Research Conference. Washington, D. C. Bureau of the Census.
[7] Freedman, D. A. and Wachter, K. W. (2003). On the likelihood of improving the accuracy of the census through statistical adjustment. In A Festschrift for Terry Speed (D. Goldstein and S. Dudoit, eds.) 197–230. Institute of Mathematical Statistics.
[8] Hogan, H. (1993). The 1990 post-enumeration survey: Operations and results. J. Amer. Statist. Assoc. 88 1047–1060.
[9] Office of the Secretary of Commerce (1991). Decision on Whether or Not a Statistical Adjustment of the 1990 Decennial Census of Population Should Be Made for Coverage Deficiencies Resulting in an Overcount or Undercount of the Population, Explanation. Three volumes. Reprinted in part in Federal Register 56 33582–33642 (July 22). U.S. Department of Commerce, Washington, D. C.
[10] Robinson, J. G., West, K. K. and Adlakha, A. (2002). Coverage of the population in census 2000: Results from demographic analysis. Population Research and Policy Review 21 19–38.
[11] U. S. Census Bureau (2003). American Community Survey Operations Plan. U.S. Department of Commerce, Washington, D. C.
[12] Wachter, K. W. (1993). The census adjustment trial: An exchange. Jurimetrics 34 107–115.
[13] Wachter, K. W. and Freedman, D. A. (2000a). The fifth cell. Evaluation Review 24 191–211.
[14] Wachter, K. W. and Freedman, D. A. (2000b). Measuring local heterogeneity with 1990 U. S. census data. Demographic Research 3 1–22.
