Taking advantage of sampling deisgns in Bayesian spatial small ares survey studies

TL;DR

This paper introduces a spatial model for small area survey studies that leverages spatial dependence, sampling design, and supplementary variables to improve estimation accuracy, merging spatial and sampling approaches.

Contribution

It proposes a novel spatial model that incorporates sampling design and supplementary variables for small area surveys, extending methods used in exhaustive data contexts.

Findings

Effective integration of sampling design improves estimate reliability.

Model demonstrates enhanced accuracy over traditional methods.

Combines spatial dependence with sampling information for better small area estimates.

Abstract

Spatial small area estimation models have become very popular in some contexts, such as disease mapping. Data in disease mapping studies are exhaustive, that is, the available data are supposed to be a complete register of all the observable events. In contrast, some other small area studies do not use exhaustive data, such as survey based studies, where a particular sampling design is typically followed and inferences are later extrapolated to the entire population. In this paper we propose a spatial model for small area survey studies, taking advantage of spatial dependence between units, which is the key assumption used for yielding reliable estimates in exhaustive data based studies. In addition, and in contrast to most spatial survey studies, we take the approach of also considering information on the sampling design and additional supplementary variables in order to yield small area estimates. This makes it possible to merge spatial and sampling based approaches into a common proposal