Online Program

Small Area Estimation in Practice
*Ray Chambers, University of Wollongong, Australia 


We use data derived from a farm economic survey to illustrate the application of model-based small area estimation (SAE) techniques to the problem of estimating regional farm business performance. Both well known small area estimators, such as the empirical best linear unbiased predictor (EBLUP), as well as more recently proposed small area estimators, such as the M-quantile estimator, the outlier robust EBLUP and the model-based direct estimator, are considered. The issue of mean squared error estimation is discussed, as is the construction of confidence intervals. Since model-fitting is a crucial part of SAE, we place special emphasis on model diagnostics for specifying the small area working model, on diagnostic measures for validating the reliability of direct and indirect (model-based) small area estimators and on providing practical guidelines to the prospective user of small area estimation techniques