We obtain a limit of a hierarchical Bayes estimator of a finite population mean when the sample size is large. The limit is in the sense of ordinary calculus, where the sample observations are treated as fixed quantities. Our result suggests a simple way to correct the hierarchical Bayes estimator to achieve design-consistency, a well-known property in the traditional randomization approach to finite population sampling. We also suggest three different measures of uncertainty of our proposed estimator.
Publié le : 2007-04-14
Classification:
Design-consistency,
generalized linear mixed models,
mathematical limit,
small area estimation,
62D05,
62F15
@article{1183667290,
author = {Lahiri, P. and Mukherjee, Kanchan},
title = {On the design-consistency property of hierarchical Bayes estimators in finite population sampling},
journal = {Ann. Statist.},
volume = {35},
number = {1},
year = {2007},
pages = { 724-737},
language = {en},
url = {http://dml.mathdoc.fr/item/1183667290}
}
Lahiri, P.; Mukherjee, Kanchan. On the design-consistency property of hierarchical Bayes estimators in finite population sampling. Ann. Statist., Tome 35 (2007) no. 1, pp. 724-737. http://gdmltest.u-ga.fr/item/1183667290/