Disease mapping models: an empirical evaluation. Disease Mapping Collaborative Group.

@article{citeulike:2635998, abstract = {The analysis of small area disease incidence has now developed to a degree where many methods have been proposed. However, there are few studies of the relative merits of the methods available. While many Bayesian models have been examined with respect to prior sensitivity, it is clear that wider comparisons of methods are largely missing from the literature. In this paper we present some preliminary results concerning the goodness-of-fit of a variety of disease mapping methods to simulated data for disease incidence derived from a range of models. These simulated models cover simple risk gradients to more complex true risk structures, including spatial correlation. The main general results presented here show that the gamma-Poisson exchangeable model and the Besag, York and Mollie (BYM) model are most robust across a range of diverse models. Mixture models are less robust. Non-parametric smoothing methods perform badly in general. Linear Bayes methods display behaviour similar to that of the gamma-Poisson methods.}, address = {Department of Mathematical Sciences, King's College, University of Aberdeen, UK.}, author = {Lawson, A. B. and Biggeri, A. B. and Boehning, D. and Lesaffre, E. and Viel, J. F. and Clark, A. and Schlattmann, P. and Divino, F. }, citeulike-article-id = {2635998}, issn = {0277-6715}, journal = {Statistics in medicine}, number = {17-18}, pages = {2217--2241}, posted-at = {2008-04-07 03:47:33}, priority = {2}, title = {Disease mapping models: an empirical evaluation. Disease Mapping Collaborative Group.}, url = {http://view.ncbi.nlm.nih.gov/pubmed/10960849}, volume = {19}, year = {2000} }

TY - JOUR ID - citeulike:2635998 L3 - citeulike-article-id:2635998 TI - Disease mapping models: an empirical evaluation. Disease Mapping Collaborative Group. JF - Statistics in medicine VL - 19 IS - 17-18 SP - 2217 EP - 2241 AD - Department of Mathematical Sciences, King's College, University of Aberdeen, UK. SN - 0277-6715 N2 - The analysis of small area disease incidence has now developed to a degree where many methods have been proposed. However, there are few studies of the relative merits of the methods available. While many Bayesian models have been examined with respect to prior sensitivity, it is clear that wider comparisons of methods are largely missing from the literature. In this paper we present some preliminary results concerning the goodness-of-fit of a variety of disease mapping methods to simulated data for disease incidence derived from a range of models. These simulated models cover simple risk gradients to more complex true risk structures, including spatial correlation. The main general results presented here show that the gamma-Poisson exchangeable model and the Besag, York and Mollie (BYM) model are most robust across a range of diverse models. Mixture models are less robust. Non-parametric smoothing methods perform badly in general. Linear Bayes methods display behaviour similar to that of the gamma-Poisson methods. AU - Lawson, AB AU - Biggeri, AB AU - Boehning, D AU - Lesaffre, E AU - Viel, JF AU - Clark, A AU - Schlattmann, P AU - Divino, F PY - 2000///0 UR - http://view.ncbi.nlm.nih.gov/pubmed/10960849 ER -