Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Topics
Data & Maps
Surveys & Programs
Resource Library
Effects of Missing Data on Modeling Enumeration Status in the U.S. Census
Effects of Missing Data on Modeling Enumeration Status in the U.S. Census
RRS2012-14
Abstract
The Census Coverage and Measurement program at the U.S. Census Bureau uses dual system estimation to measure the accuracy of the decennial census. Construction of the dual system estimator involves first estimating the percentage of correctly enumerated persons in the decennial census within different domains. This estimation is complicated by the presence of unresolved census enumerations (missing data) for which enumeration status (correct or erroneous) can not be determined. Furthermore, there is concern that the propensity to respond depends on enumeration status, that is, that the missing data are not missing at random. This paper is an exploration of different missing data models and their effect on the prediction of enumeration status, and in particular a comparison of missing at random and not missing at random data models.
Others in Series
Working Paper
Benchmarking Small Area Estimators
Benchmarking Small Area Estimators
Working Paper
Exploring Re-identification Risks in Public Domains
Exploring Re-identification Risks in Public Domains
Working Paper
The Multiple Testing Problem for Box-Pierce Statistics
The Multiple Testing Problem for Box-Pierce Statistics
Related Information
WORKING PAPER
Statistical Research Reports and Studies
Page Last Revised - October 28, 2021
✕
Is this page helpful?
Yes
No
Yes
No✕
NO THANKS
255 characters maximum
255 characters maximum reached
255 characters maximum reached
✕
Thank you for your feedback.
Comments or suggestions?
Comments or suggestions?
