A comparison of the hierarchical likelihood and Bayesian approaches to spatial epidemiological modelling
Authors:
- 12 September 2007
- journal article
- research article
- Published by Wiley in Environmetrics
- Vol. 18 (7) , 809-821
Abstract
Recently Bayesian methods have been widely used in disease mapping. Hierarchical (h‐) likelihood methods allow reliable likelihood inference in random‐effect models and it is therefore interesting to compare h‐likelihood and Bayesian methods. For comparison we consider three examples: low birth weight and cancer mortality data in South Carolina and lip cancer data in Scotland. Mean estimates from both h‐likelihood and Bayesian approaches are almost identical, while variance‐component estimates can be somewhat different, depending upon choice of priors. Copyright © 2007 John Wiley & Sons, Ltd.Keywords
This publication has 28 references indexed in Scilit:
- Model selection for multi‐component frailty modelsStatistics in Medicine, 2007
- A comparison of Bayesian and likelihood-based methods for fitting multilevel modelsBayesian Analysis, 2006
- Comment on article by Browne and DraperBayesian Analysis, 2006
- Double Hierarchical Generalized Linear Models (With Discussion)Journal of the Royal Statistical Society Series C: Applied Statistics, 2006
- Bayesian Measures of Model Complexity and FitJournal of the Royal Statistical Society Series B: Statistical Methodology, 2002
- Disease mapping models: an empirical evaluationStatistics in Medicine, 2000
- Bias Correction in Generalized Linear Mixed Models with Multiple Components of DispersionJournal of the American Statistical Association, 1996
- Approximate Inference in Generalized Linear Mixed ModelsJournal of the American Statistical Association, 1993
- Empirical Bayes Procedures for Stabilizing Maps of U.S. Cancer Mortality RatesJournal of the American Statistical Association, 1989
- Spatial Modeling of Regional VariablesJournal of the American Statistical Association, 1989