Benchmarking


Chair: William R. Bell

This session contains three contributions dealing with benchmarking and calibration. The first contribution gives constrained empirical Bayes estimation in multiplicative area-level models with risk analysis under an asymmetric loss function. The second contributions introduces benchmark estimators for a small area mean under a one-fold nested regression model. Finally, the third contribution gives a two-level hybrid calibration technique for small area estimation


Constrained Empirical Bayes Estimation in Multiplicative Area-Level Models with Risk Analysis Under an Asymmetric Loss Function

Consider the problem of benchmarking small area estimates under multiplicative models with positive parameters where estimates are constrained to aggregate to direct estimates for the larger geographical areas. Constrained (hierarchical) empirical Bayes estimators of positive small area parameters under the conventional squared error loss function can take negative values. In this paper, we propose a […]

Benchmark estimators for a small area mean under a one-fold nested regression model

The authors develop a number of small area estimation procedures using a unit level linear regression model and survey weights: these weights incorporate the auxiliary information at the sample level. In particular, they propose three ways to ensure that the You-Rao (2002), Prasad-Rao (1999) and EBLUP small area estimators add up to estimates over the […]

A two-level hybrid calibration technique for small area estimation

Calibration constitutes a flexible tool for design-based inference for finite populations. We introduce here a new calibration method we call two-level hybrid calibration. Hybrid calibration (Lehtonen and Veijanen 2015) combines some of the favorable properties of model-free calibration (Deville and Särndal 1992) and model calibration (Wu and Sitter 2001). Benefits of model-free calibration are the […]