Spatial prediction of counts and rates
- 14 April 2003
- journal article
- research article
- Published by Wiley in Statistics in Medicine
- Vol. 22 (9) , 1415-1432
- https://doi.org/10.1002/sim.1523
Abstract
In this paper we provide both theoretical and empirical comparisons of marginal and conditional methods for analysing spatial count data. We focus on methods for spatial prediction developed from a generalized linear mixed model framework and compare them with the traditional linear (kriging) predictor. Prediction methods are illustrated and compared through a case study based on real data and through a detailed simulation study. The paper emphasizes a better understanding of the strengths and weaknesses of each approach. Published in 2003 by John Wiley & Sons, Ltd.Keywords
This publication has 29 references indexed in Scilit:
- A Generalized Linear Model Approach to Spatial Data Analysis and PredictionJournal of Agricultural, Biological and Environmental Statistics, 1997
- Kriging the Local Risk of a Rare Disease from a Register of DiagnosesGeographical Analysis, 1994
- Approximate Inference in Generalized Linear Mixed ModelsJournal of the American Statistical Association, 1993
- A Comparison of Spatial Semivariogram Estimators and Corresponding Ordinary Kriging PredictorsTechnometrics, 1991
- An application of density estimation to geographical epidemiologyStatistics in Medicine, 1990
- Spatial Modeling of Regional VariablesJournal of the American Statistical Association, 1989
- Longitudinal data analysis using generalized linear modelsBiometrika, 1986
- Decomposition of Prediction ErrorJournal of the American Statistical Association, 1985
- Geographic patterns of oral cancer in the United States: Etiologic implicationsJournal of Chronic Diseases, 1977
- Best Linear Unbiased Prediction in the Generalized Linear Regression ModelJournal of the American Statistical Association, 1962