Bayesian Sample Size Determination for Planning Hierarchical Bayes Small Area Estimates

TL;DR

This paper introduces a Bayesian method for determining the optimal sample size in hierarchical small area estimation, ensuring estimator reliability while integrating traditional survey design tools.

Contribution

It presents a novel Bayesian sample size determination approach using a loss function based on posterior variance, combined with an efficient binary search algorithm.

Findings

Effective sample size targets align with official statistics criteria.

Case study demonstrates practical application in health prevalence estimation.

Method integrates Bayesian modeling with survey planning tools.

Abstract

This paper devises a fully Bayesian sample size determination method for hierarchical model-based small area estimation with a decision risk approach. A new loss function specified around a desired maximum posterior variance target implements conventional official statistics criteria of estimator reliability (coefficient of variation of up to 20 per cent). This approach comes with an efficient binary search algorithm identifying the minimum effective sample size needed to produce small area estimates under this threshold constraint. Traditional survey sampling design tools can then be used to plan appropriate data collection using the resulting effective sample size target. This approach is illustrated in a case study on small area prevalence of life limiting health problems for 6 age groups across 1,956 small areas in Northern England, using the recently developed Integrated Nested Laplace Approximation method for spatial generalised linear mixed hierarchical models.