|
Activity Number:
|
387
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 11, 2004 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #301703 |
|
Title:
|
Quality Control of Data Entry for the American Community Survey and the Impact of Errors on Data Quality
|
|
Author(s):
|
Andre L. Williams*+ and Rita J. Petroni and Bryan D. Garrett
|
|
Companies:
|
U.S. Census Bureau and U.S. Census Bureau and U.S. Census Bureau
|
|
Address:
|
4700 Silver Hill Rd. STOP 9200, Washington, DC, 20233-9200,
|
|
Keywords:
|
mail-out ; keying ; data capture ; consequential errors ; quality control
|
|
Abstract:
|
The American Community Survey (ACS) is being developed by the Census Bureau to replace the decennial census long form. ACS collects important socioeconomic data continuously in three-month cycles. ACS mails out questionnaires during month one, then follows nonrespondents with computer assisted telephone and personal interviewing in months two and three, respectively. The paper questionnaires from mail-out are keyed. ACS has a quality control program which samples keyed documents and estimates keying error rates. A sample of errors from the 2002 ACS was examined to measure the impact of keying errors on data quality. Examination of these errors led to the classification of some errors as inconsequential since they were not expected to affect data quality. This paper estimates ACS keying error rates, provides a preliminary estimate of the proportion of errors that affect data quality, compares ACS error rates of related data capture methods used by Census 2000, and describes the distribution of the main types of keying errors.
|
