Empirical Bayes methods for disease mapping

Alastair H Leyland; Carolyn A Davies

doi:10.1191/0962280205sm387oa

Empirical Bayes methods for disease mapping

Stat Methods Med Res. 2005 Feb;14(1):17-34. doi: 10.1191/0962280205sm387oa.

Authors

Alastair H Leyland¹, Carolyn A Davies

Affiliation

¹ MRC Social and Public Health Sciences Unit, University of Glasgow, Glasgow, Scotland, UK. a.leyland@msoc.mrc.gla.ac.uk

PMID: 15690998
DOI: 10.1191/0962280205sm387oa

Abstract

This paper reviews empirical Bayes methods for disease mapping. A distinction is made between spatial models (which take into account the geographical distribution of disease) and nonspatial models. Several estimators are presented, and methods of estimation are described. Empirical Bayes methods are compared with full Bayes methods, and we argue that both have their place.

Publication types

Research Support, Non-U.S. Gov't
Review

MeSH terms

Algorithms
Bayes Theorem*
Disease*
Empirical Research
Epidemiologic Studies
Humans
Models, Statistical
Scotland / epidemiology