The aim of Small Area Estimation (SAE) is to compute a set of reliable estimates for each small area for the target variable(s) of interest, whenever the direct estimates (see “Weighting and Estimation – Main Module” and “Weighting and Estimation – Generalised Regression Estimator”) cannot be considered enough reliable, i.e., the correspondent variances (see the module “Quality Aspects – Quality of Statistics”) are too high to make those estimates releasable.
Small area methods provide a set of techniques to obtain the estimates of interest in the National Statistical Institutes (NSIs) large scale survey, where more detailed information is required, and the sample size is not large enough to guarantee release of direct estimation. SAE methods which increase the reliability of estimates ’borrowing strength’ from a larger area.
The unit level EBLUP estimator, which is described in this module, is a linear combination of the direct information and a regression synthetic prediction of non-sampled units. The fixed part of the model links the target values to some known auxiliary variables, for each units belonging to the larger area to which the small areas of interest belong to. The area specific random effects is instead introduced in order to take into account the correlation among the units with each small area (between area variation).
To read the entire document, please access the pdf file (link under "Related Documents" on the right-hand-side of this page).
Your feedback is appreciated. Please send your remarks, suggestions for improvement, etc. to email@example.com.