|
Activity Number:
|
278
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 14, 2002 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods*
|
| Abstract - #301908 |
|
Title:
|
Variance Estimation for Census 2000 A.C.E. Subsamples
|
|
Author(s):
|
Douglas Olson*+
|
|
Affiliation(s):
|
U.S. Census Bureau
|
|
Address:
|
SFC 223012, Stop #76, Suitland, Maryland, 20233, USA
|
|
Keywords:
|
|
|
Abstract:
|
The Census 2000 Accuracy and Coverage Evaluation (A.C.E.) used a sample of clusters of blocks that was selected using a two-phase design, in which stratification was used in both phases to partition the sampling universes. Additional subsamples of the A.C.E. were taken for production and evaluation purposes that ignored the stratification used in the A.C.E. sampling. Extensive work was necessary to design the variance estimation system for the A.C.E. estimates. But the sampling variances for estimates from the additional subsamples were computed under the assumption that the earlier stratifications used in the A.C.E. sample design could be ignored with minimal loss of accuracy. In this paper, variance estimates for one of those subsamples, Targeted Extended Search Phase Three (TES-3), are compared using theoretical computations, simulations, and standard variance estimation techniques.
|
- 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 |
