Abstract:
|
In October 2001 the U.S. Census Bureau recommended that unadjusted Census 2000 data be used for non-redistricting purposes. This followed a similar decision, made in March 2001, to use unadjusted data for redistricting. The October decision was based on new evidence that the Accuracy and Coverage Evaluation (A.C.E.) overstated the net undercount by at least 3 million persons. This paper will first outline the initial A.C.E. evaluation program, then review the six specific research areas which were pursued during a second round of evaluations. These six topics were explored further to address concerns that were identified during eliberations leading to the March decision: demographic analysis, measurement of erroneous enumerations, measurement of census omissions, missing data studies, balancing error, and synthetic error. Research results from these areas led us to concentrate on one of them: the measurement of erroneous enumerations, including duplication. Findings from these studies will be used to enhance both census and coverage measurement methods for future censuses.
|