Indirect estimators for small areas use auxiliary variables to borrow strength from related areas through a linking model. Precision of indirect estimators depends on the validity of such a model. To protect against possible model failures, benchmarking procedures make the total of small area stimates match a design consistent estimate for a larger area. This is also particularly important for National Institutes of Statistics to ensure coherence between small area estimates and direct estimates produced at higher level planned domains. We investigate a self-benchmarked estimator in the case of a unit level logistic mixed model for a binary response, propose an estimator for its mean squared error and compare its performance with competing estimators through a simulation study.
A comparison of small area estimators of counts aligned with direct higher level estimates
MONTANARI, Giorgio Eduardo;RANALLI, Maria Giovanna;VICARELLI, CECILIA
2010
Abstract
Indirect estimators for small areas use auxiliary variables to borrow strength from related areas through a linking model. Precision of indirect estimators depends on the validity of such a model. To protect against possible model failures, benchmarking procedures make the total of small area stimates match a design consistent estimate for a larger area. This is also particularly important for National Institutes of Statistics to ensure coherence between small area estimates and direct estimates produced at higher level planned domains. We investigate a self-benchmarked estimator in the case of a unit level logistic mixed model for a binary response, propose an estimator for its mean squared error and compare its performance with competing estimators through a simulation study.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
