Matching Error in the 2000 Accuracy and Coverage Evaluation

• Activity Number: 348
• Type: Topic Contributed
• Date/Time: Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
• Sponsor: Section on Survey Research Methods*
• Author(s): Susanne Bean*+
• Affiliation(s): U.S. Census Bureau
• Keywords: nonsampling error ; clerical matching ; Accuracy and Coverage Evaluation ; Dual System Estimation

Abstract

The U.S. Bureau of the Census conducted an Accuracy and Coverage Evaluation (A.C.E.) to estimate the differential coverage of the U.S. population in Census 2000. The A.C.E., comprised of two overlapping samples, used Dual System Estimation to produce this estimate. A potential source of error in the coverage estimates was a clerical matching operation, which determined whether people in the A.C.E. population sample (P-sample) were enumerated in the census and whether the census enumerations in the enumeration sample (E-sample) were correct. To evaluate this source of nonsampling error, the Matching Error Study (MES) conducted an independent rematch and reconciliation in a subsample of the A.C.E. block clusters called the evaluation sample. This paper will examine the differences between the original A.C.E. and the MES matching operations and how matching error in the A.C.E. affected the Dual System Estimates.