Estimates for small area compositions subjected to informative missing data
Estimates for small area compositions subjected to informative missing data
Estimation of small area (or domain) compositions may suffer from informative missing data, if the probability of missing varies across the categories of interest as well as the small areas. We develop a double mixed modeling approach that combines a random effects mixed model for the underlying complete data with a random effects mixed model of the differential missing-data mechanism. The effect of sampling design can be incorporated through a quasi-likelihood sampling model. The associated conditional mean squared error of prediction is approximated in terms of a three-part decomposition, corresponding to a naive prediction variance, a positive correction that accounts for the hypothetical parameter estimation uncertainty based on the latent complete data, and another positive correction for the extra variation due to the missing data. We illustrate our approach with an application to the estimation of Municipality household compositions based on the Norwegian register household data, which suffer from informative under-registration of the dwelling identity number.
data analysis, estimation methods, forecasting, households, models, sample data, small area data
191-201
Zhang, Li-Chun
a5d48518-7f71-4ed9-bdcb-6585c2da3649
December 2009
Zhang, Li-Chun
a5d48518-7f71-4ed9-bdcb-6585c2da3649
Zhang, Li-Chun
(2009)
Estimates for small area compositions subjected to informative missing data.
Survey Methodology, 35 (2), .
Abstract
Estimation of small area (or domain) compositions may suffer from informative missing data, if the probability of missing varies across the categories of interest as well as the small areas. We develop a double mixed modeling approach that combines a random effects mixed model for the underlying complete data with a random effects mixed model of the differential missing-data mechanism. The effect of sampling design can be incorporated through a quasi-likelihood sampling model. The associated conditional mean squared error of prediction is approximated in terms of a three-part decomposition, corresponding to a naive prediction variance, a positive correction that accounts for the hypothetical parameter estimation uncertainty based on the latent complete data, and another positive correction for the extra variation due to the missing data. We illustrate our approach with an application to the estimation of Municipality household compositions based on the Norwegian register household data, which suffer from informative under-registration of the dwelling identity number.
Text
__soton.ac.uk_ude_PersonalFiles_Users_yl1m11_mydocuments_REF2014_REF outputs_UoA 10 outputs_345170.pdf
- Other
Restricted to Repository staff only
Request a copy
More information
Published date: December 2009
Keywords:
data analysis, estimation methods, forecasting, households, models, sample data, small area data
Organisations:
Statistical Sciences Research Institute
Identifiers
Local EPrints ID: 345170
URI: http://eprints.soton.ac.uk/id/eprint/345170
ISSN: 0714-0045
PURE UUID: 238dd122-b05b-4ebe-99ac-6900ef1b21c0
Catalogue record
Date deposited: 12 Nov 2012 10:14
Last modified: 15 Mar 2024 03:45
Export record
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics