Policy-related small-area estimation

Abstract

A method of small-area estimation with a utility function is developed. The utility characterises a policy planned to be implemented in each area, based on the area's estimate of a key quantity. It is shown by simulations that the commonly applied composite and empirical Bayes estimators are inefficient for a wide range of asymmetric utility functions. Adaptations for limited budget to implement the policy are explored. An argument is presented for a closer integration of estimation and (regional) policy making because no single small- area estimator is suitable for a wide range of purposes.