measurement, except that we do make the assumption that field operations supporting matching in 2000 will be at least as successful as they were in 1990.

The substantial statistical literature highlights three specific concerns related to the use of census adjustment: (1) matching error and the bias from imputation of match status for unresolved cases, (2) unmodeled heterogeneity in census undercoverage for lower levels of geographic aggregation (violation of the so-called synthetic assumption), and (3) correlation bias, and the heterogeneity of probabilities of enumeration of individuals in the census and the integrated coverage measurement survey.2 These concerns are related to potential failures of the statistical assumptions that underlie the integrated coverage measurement estimators. Such assumptions are used only as approximations to the truth (which can never be known), and so the relevant point is not whether these assumptions obtain exactly but the extent to which they do and do not apply and the resulting effects on the quality of the adjusted census counts in comparison with the quality of the unadjusted counts.

Before proceeding, we must consider how one might assess whether adjusted counts are preferred to unadjusted counts, or, more generally, how any one set of estimated counts is preferred to another. In general, the "closer" a set of counts is to the true counts, the better. There are a variety of measures of disparity, known as loss functions, that measure how "close" a set of estimated counts is to the true counts. These loss functions are defined so that smaller values indicate more accurate counts. The many possible loss functions represent different uses of the data and varying notions of the costs of disparities. For example, the apportion-

2  

There are other concerns that we do not examine in this chapter. One is that a substantial data processing error in the initial computations for the 1990 post-enumeration survey has raised arguments that the ICM methodology is complex and therefore prone to error. There is always a chance for human error in data processing and computation, and the risk is somewhat larger with integrated coverage measurement than without. However, the panel believes that the risk is relatively low for the 2000 census given the testing that has already taken place and that is going on in the 1998 census dress rehearsal. A second concern is that the use of a post-enumeration survey (PES) does add sampling variance that can be noticeable at the level of the poststrata, and this additional variability can result in some adjusted counts for individual poststrata being inferior to unadjusted counts. In response, adjustment will likely improve accuracy overall even if the estimates for a minority of poststrata are made worse. Increasing the sample size of the post-enumeration survey, as is planned for 2000, reduces this problem, and increasing the number of poststrata worsens it, but in that case smoothing (which can mean various procedures) can reduce the additional variability at the poststratum level. Of course, the important estimates are not estimates for poststrata but estimates for areas, which are functions of the estimates for poststrata.



The National Academies | 500 Fifth St. N.W. | Washington, D.C. 20001
Copyright © National Academy of Sciences. All rights reserved.
Terms of Use and Privacy Statement