Hierarchical Modeling and Analysis for Spatial DataCRC Press, 2003 M12 17 - 472 páginas Among the many uses of hierarchical modeling, their application to the statistical analysis of spatial and spatio-temporal data from areas such as epidemiology And environmental science has proven particularly fruitful. Yet to date, the few books that address the subject have been either too narrowly focused on specific aspects of spatial analysis, |
Contenido
1 Overview of Spatial Data Problems | 1 |
2 Basics of Pointreferenced Data Models | 19 |
3 Basics of Areal Data Models | 67 |
4 Basics of Bayesian Inference | 96 |
5 Hierarchical Modeling for Univariate Spatial Data | 124 |
6 Spatial Misalignment | 169 |
7 Multivariate Spatial Modeling | 211 |
8 Spatiotemporal Modeling | 257 |
9 Spatial Survival Models | 302 |
10 Special Topics in Spatial Process Modeling | 344 |
Appendices | 379 |
| 423 | |
Author Index | 439 |
| 448 | |
Otras ediciones - Ver todas
Hierarchical Modeling and Analysis for Spatial Data Sudipto Banerjee,Bradley P. Carlin,Alan E. Gelfand Vista previa limitada - 2003 |
Hierarchical Modeling and Analysis for Spatial Data Sudipto Banerjee,Bradley P. Carlin,Alan E. Gelfand Sin vista previa disponible - 2003 |
Términos y frases comunes
algorithm analysis approach approximate areal arises associated assume average Bayesian block choice coefficient component compute conditional consider continuous correlation function corresponding covariance covariance function data set defined denotes density dependence directional discussion distance distribution effects equation error estimates example expected fact Figure Finally frailty full conditional function Gaussian Gibbs given hazard Hence hierarchical illustrate increasing independent indicator inference interest interval introduce inverse joint likelihood linear locations marginal matrix MCMC mean measurements median methods multivariate normal Note observed obtain parameters particular plot population positive posterior predictive prior problem provides random random effects range referred region relative requires risk sample scale shows simply spatial process spatiotemporal specification square standard stationary structure Subsection suggests suppose surface Table unit valid values variables variance variogram vector