|
Activity Number:
|
207
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #305327 |
|
Title:
|
The Quality of ACS Estimates for Small Population Groups
|
|
Author(s):
|
Alfredo Navarro*+ and Michael D. Starsinic
|
|
Companies:
|
U.S. Census Bureau and U.S. Census Bureau
|
|
Address:
|
21523 Manor View Cir, Germantown, MD, 20876,
|
|
Keywords:
|
ACS ; Long form ; Reliability ; Lag
|
|
Abstract:
|
This paper discusses the quality and usefulness of estimates from the American Community Survey (ACS), specifically estimates for very small areas and population groups. The ACS is intended to replace the long form survey in the 2010 census. Since the long form is unique as a source of information about smaller population groups, a priority objective of the ACS design has been to provide good quality estimates and information about smaller groups. The foundation and general premise of the ACS design is that by spreading the "long form" sample across several years, it is possible to provide comparable information to the long form for all sizes of population groups. The paper focuses on assessing the quality of ACS estimates for small and very small population groups by exploring two aspects: reliability and the concept of period estimates. It shows the trade-off between lag and reliability.
|
