Statistical Modelling 11 (2011), 137157
An assessment of empirical Bayes and composite estimators for small areas
Nicholas T Longford
SNTL and Department d’Economia i Empresa,
Universitat Pompeu Fabra,
2527 Ramon trias Fargas
E08005 Barcelona
Spain
eMail: NTL@SNTL.co.uk
Abstract:
We compare the classes of empirical Bayes and composite estimators of the
population means of the districts (small areas) of a country and show that the
commonly adopted modelling strategy of searching for a well-fitting random
coefficient (two-level) model and using it for estimation of the district-level
means can be ineffective. In particular, we show that variables with small
district-level variation are not useful as covariates even when they are strong
predictors of the target variable.
Keywords:
composite estimator; empirical Bayes estimation; mean squared error;
small-area estimation
Downloads:
Example data and code in
zipped archive
back