|
Activity Number:
|
191
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #306348 |
|
Title:
|
Framework for Census Coverage Error Components
|
|
Author(s):
|
Mary Mulry*+ and Donna Kostanich
|
|
Companies:
|
U.S. Census Bureau and U.S. Census Bureau
|
|
Address:
|
2884 Manorwood Trail, Fort Worth, TX, 76109,
|
|
Keywords:
|
erroneous enumerations ; omissions ; undercount ; dual system estimation ; 2010 Census
|
|
Abstract:
|
A major goal and challenge for coverage measurement in 2010 is to design a survey that measures the components of coverage error, namely erroneous enumerations and omissions. The U.S. Census Bureau's previous coverage measurement surveys were designed primarily to estimate net census error using dual system estimation (DSE). To improve the accuracy of estimates of net error, the U.S. Census Bureau's DSE has relied on balancing some of the components of error, meaning some census omissions offset some erroneous inclusions in a manner that preserved the net error. As a result, the process produced inflated estimates of omissions and erroneous inclusions. This paper provides a framework for overcoming these inflated estimates of component errors. It also explicitly defines the components of error and discusses how they relate to traditional net error concepts.
|
