|
Activity Number:
|
99
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, July 30, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #309033 |
|
Title:
|
Analysis of Variance Estimates from American Community Survey Multiyear Estimates
|
|
Author(s):
|
Michael Starsinic*+ and Anthony Tersine, Jr.
|
|
Companies:
|
U.S. Census Bureau and U.S. Census Bureau
|
|
Address:
|
14607 London Lane, Bowie, MD, 20715,
|
|
Keywords:
|
American Community Survey ; Variance estimation
|
|
Abstract:
|
The American Community Survey (ACS) will produce a series of three- and five-year period estimates for 34 ACS counties using data from 1999--2005. This series of period estimates will provide a large amount of information regarding the variance distributions for multi-year ACS estimates for the first time. The focus of this paper is on answering three questions: how much a new weighting methodology reduced variances at the place and census tract levels, what are the variance characteristics of estimates at the block group level (the smallest geographic level published in the ACS five-year products), and the relationship between the variances of one-, three-, and five-year period estimates for specific characteristics. We will share the results of this research.
|
