Download:
|
by J. Andrew Royle, L. Mark Berliner
Journal of Agricultural, Biological, and Environmental Statistics
http://www.cgd.ucar.edu/stats/royle/applied2.ps
Add To MetaCart
Abstract:
We propose a hierarchical model for multivariate spatial modeling and prediction under which one specifies a joint distribution for a multivariate spatial process indirectly through specification of simpler conditional models. This approach is similar to standard methods known as cokriging and "kriging with an external drift", but avoids some of the inherent difficulties in these two approaches including specification of valid joint covariance models and restriction to exhaustively sampled covariates. Moreover, both existing approaches can be formulated in this hierarchical framework. The hierarchical approach is ideally suited for, but not restricted for use in, situations in which known "cause/effect" relationships exist. Because the hierarchical approach models dependence between variables in conditional means, as opposed to cross-covariances, very complicated relationships are more easily parameterized. We suggest an iterative estimation procedure which combines generalized least-squares with imputation of missing values using the Best Linear Unbiased Predictor. An example is given which involves prediction of a daily ozone summary from maximum daily temperature in the Midwest.
Citations
|
635
|
Generalized Additive Models
– Hastie, Tibshirani
- 1990
|
|
574
|
Bayesian Theory
– Bernardo, Smith
- 1994
|
|
493
|
Statistics for spatial data
– Cressie
- 1993
|
|
445
|
Statistical analysis with missing data
– Little, Rubin
- 1986
|
|
267
|
Nonparametric regression and Generalized Linear Models
– Green, Silverman
- 1994
|
|
188
|
Statistical Inference
– Casella, Berger
- 1990
|
|
96
|
Mining geostatistics
– Journel, Huijbregts
- 1978
|
|
95
|
Random-effects models for longitudinal data
– Laird, Ware
- 1982
|
|
71
|
Nonlinear statistical models
– Gallant
- 1987
|
|
31
|
Maximum likelihood estimation of models for residual covariance in spatial regression
– Mardia, Marshall
- 1984
|
|
21
|
Multivariate spatial interpolation and exposure to air pollutants
– Brown, Le, et al.
- 1994
|
|
20
|
Multivariate Geostatistics
– Wackernagel
- 1998
|
|
19
|
Fitting variogram models by weighted least square
– Cressie
- 1985
|
|
16
|
Application of Least Squares Regression to Relationships Containing Autocorrelated Error Terms
– Cochrane, Orcutt
- 1949
|
|
6
|
Applied Linear Statistical Models, 3rd edition
– Neter, Wasserman, et al.
- 1990
|
|
6
|
Design of air quality monitoring networks
– Nychka, Saltzman
- 1998
|
|
6
|
Multivariable Spatial Prediction
– Hoef, M, et al.
- 1993
|
|
6
|
Constructing and Fitting Models for Cokriging and Multivariable Spatial Prediction
– Hoef, J, et al.
- 1998
|
|
5
|
Matrix formulation of co-kriging
– Myers
- 1982
|
|
5
|
A Hierarchical spatial model for constructing wind fields from scatterometer data in the Labrador Sea
– Royle, Berliner, et al.
- 1997
|
|
4
|
Use of auxiliary data for spatial interpolation of ozone exposure in Southeastern forests
– Phillips, E, et al.
- 1997
|
|
4
|
Description of a computer program for analyzing multivariate spatially distributed data
– Wackernagel
- 1989
|
|
3
|
Geostatistical Methods for Incorporating Auxiliary Information in the Prediction of Spatial Variables
– Gotway, Hartford
- 1996
|
|
3
|
On approximations to geopotential and wind-field correlation structures
– Thiebaux
- 1985
|
|
3
|
Geostatistical techniques for interpreting multivariate spatial information
– Wackernagel
- 1988
|
|
2
|
Comparison of Geostatistical Methods for Estimating Transmissivity Using Data on Transmissivity and Specific Capacity
– Ahmed, Marsily
- 1987
|
|
2
|
Improving the kriging of a soil variable using slope gradient as external drift
– Bourennane, King, et al.
- 1996
|
|
2
|
Multivariate spatial prediction in the presence of non-linear trend and covariance non-stationarity
– Haas
- 1996
|
|
1
|
Universal kriging and cokriging as a regression procedure
– Stein, Corsten
- 1991
|
