Activity Number:
|
19
- 2020 Census Post-Enumeration Survey Estimation Methods: Research and Challenges
|
Type:
|
Topic Contributed
|
Date/Time:
|
Sunday, August 7, 2022 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Survey Research Methods Section
|
Abstract #322144
|
|
Title:
|
Research on Reducing Correlation Bias in Dual-System Estimates
|
Author(s):
|
Krista Heim* and Courtney Hill
|
Companies:
|
U.S. Census Bureau and U.S. Census Bureau
|
Keywords:
|
post-enumeration survey;
dual system estimation;
correlation bias;
census;
coverage;
demographic analysis
|
Abstract:
|
The concept of independence is central to dual-system estimation. One way this independence assumption can fail is if being included in the Census makes someone more or less likely to be included in the subsequent post-enumeration survey. The resulting correlation bias could reflect a systematic overestimation or underestimation of the true population by dual-system estimation. If violations to independence are present, adjustments can be made to improve estimates. Previous post-enumeration surveys have relied on sex ratios from Demographic Analysis to increase adult male estimates that display signs of correlation bias. Different adjustments could be made to Demographic Analysis data to improve estimates, such as downweighting female estimates or proportionally adjusting both sex groups. This paper will survey some of the methods that have been used in the past and explore new ways to reduce correlation bias.
|
Authors who are presenting talks have a * after their name.