Some relevant aspects in the application of the small area estimation models can be assessed when we try to show the impact that some data have on the model estimation itself. The main feature of the paper is to highlight the impact of some subjects (areas, or cluster of areas in time-dependent data) on the MSE of the Eblup estimator in area-level models. This result is achieved when we focus our analysis on the subject-deletion from the available data. The study is conducted as cluster (subject) deletion diagnostics analysis on every component of the MSE of the Eblup, in the case of the restricted maximum likelihood (Reml) estimation method. The paper gives all the results in the general linear model framework.
The diagnostics of the mean squared error of the Eblup in small area estimation models
SALVATORE, Renato;PAGLIARELLA, Maria Chiara
2012-01-01
Abstract
Some relevant aspects in the application of the small area estimation models can be assessed when we try to show the impact that some data have on the model estimation itself. The main feature of the paper is to highlight the impact of some subjects (areas, or cluster of areas in time-dependent data) on the MSE of the Eblup estimator in area-level models. This result is achieved when we focus our analysis on the subject-deletion from the available data. The study is conducted as cluster (subject) deletion diagnostics analysis on every component of the MSE of the Eblup, in the case of the restricted maximum likelihood (Reml) estimation method. The paper gives all the results in the general linear model framework.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.