|
Activity Number:
|
170
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 13, 2002 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods*
|
| Abstract - #301877 |
|
Title:
|
The Effect of Person Duplication in Census 2000 on the Population Undercount
|
|
Author(s):
|
Robert Fay*+
|
|
Affiliation(s):
|
U.S. Census Bureau
|
|
Address:
|
4700 Silver Hill Road, Stop 9001, Washington, District of Columbia, 20233-9001, USA
|
|
Keywords:
|
Census duplication ; Matching ; Erroneous enumeration
|
|
Abstract:
|
The net undercount of the population by the decennial censuses arises from the balance between: 1.) omissions of persons that the census should count but misses and 2.) erroneous enumerations that the census incorrectly includes. Duplication, where typically a person is counted correctly once but also counted incorrectly elsewhere, is a form of erroneous enumeration. Coverage measurement surveys, such as the 2000 Accuracy and Coverage Evaluation (A.C.E.), must account for the effect of census duplication in order to accurately measure the net undercount. Evidence that the A.C.E. did not fully measure the effect of census duplicates and related forms of erroneous enumerations was one of the principal reasons that the U.S. Census Bureau decided in October 2001 not to incorporate the A.C.E. results into the remaining data products from Census 2000. The paper summarizes a preliminary analysis, conducted primarily in October 2001, of the interrelationship of census duplication with other forms of erroneous enumeration and the apparent limitations of the A.C.E. in fully accounting for these errors.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2002 program |
