Home > Research > Publications & Outputs > Model-based geostatistics (with discussion).
View graph of relations

Model-based geostatistics (with discussion).

Research output: Contribution to journalJournal article

Published

Standard

Model-based geostatistics (with discussion). / Diggle, Peter; Moyeed, R. A.; Tawn, J. A.

In: Journal of the Royal Statistical Society: Series C (Applied Statistics), Vol. 47, No. 3, 1998, p. 299-350.

Research output: Contribution to journalJournal article

Harvard

Diggle, P, Moyeed, RA & Tawn, JA 1998, 'Model-based geostatistics (with discussion).', Journal of the Royal Statistical Society: Series C (Applied Statistics), vol. 47, no. 3, pp. 299-350. https://doi.org/10.1111/1467-9876.00113

APA

Diggle, P., Moyeed, R. A., & Tawn, J. A. (1998). Model-based geostatistics (with discussion). Journal of the Royal Statistical Society: Series C (Applied Statistics), 47(3), 299-350. https://doi.org/10.1111/1467-9876.00113

Vancouver

Diggle P, Moyeed RA, Tawn JA. Model-based geostatistics (with discussion). Journal of the Royal Statistical Society: Series C (Applied Statistics). 1998;47(3):299-350. https://doi.org/10.1111/1467-9876.00113

Author

Diggle, Peter ; Moyeed, R. A. ; Tawn, J. A. / Model-based geostatistics (with discussion). In: Journal of the Royal Statistical Society: Series C (Applied Statistics). 1998 ; Vol. 47, No. 3. pp. 299-350.

Bibtex

@article{a7705cbafb72406b9d11a49d6f157b26,
title = "Model-based geostatistics (with discussion).",
abstract = "Conventional geostatistical methodology solves the problem of predicting the realized value of a linear functional of a Gaussian spatial stochastic process S(x) based on observations Yi = S(xi) + Zi at sampling locations xi, where the Zi are mutually independent, zero-mean Gaussian random variables. We describe two spatial applications for which Gaussian distributional assumptions are clearly inappropriate. The first concerns the assessment of residual contamination from nuclear weapons testing on a South Pacific island, in which the sampling method generates spatially indexed Poisson counts conditional on an unobserved spatially varying intensity of radioactivity; we conclude that a conventional geostatistical analysis oversmooths the data and underestimates the spatial extremes of the intensity. The second application provides a description of spatial variation in the risk of campylobacter infections relative to other enteric infections in part of north Lancashire and south Cumbria. For this application, we treat the data as binomial counts at unit postcode locations, conditionally on an unobserved relative risk surface which we estimate. The theoretical framework for our extension of geostatistical methods is that, conditionally on the unobserved process S(x), observations at sample locations xi form a generalized linear model with the corresponding values of S(xi) appearing as an offset term in the linear predictor. We use a Bayesian inferential framework, implemented via the Markov chain Monte Carlo method, to solve the prediction problem for non-linear functionals of S(x), making a proper allowance for the uncertainty in the estimation of any model parameters.",
keywords = "Generalized linear mixed model • Geostatistics • Kriging • Markov chain Monte Carlo method • Spatial prediction",
author = "Peter Diggle and Moyeed, {R. A.} and Tawn, {J. A.}",
year = "1998",
doi = "10.1111/1467-9876.00113",
language = "English",
volume = "47",
pages = "299--350",
journal = "Journal of the Royal Statistical Society: Series C (Applied Statistics)",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "3",

}

RIS

TY - JOUR

T1 - Model-based geostatistics (with discussion).

AU - Diggle, Peter

AU - Moyeed, R. A.

AU - Tawn, J. A.

PY - 1998

Y1 - 1998

N2 - Conventional geostatistical methodology solves the problem of predicting the realized value of a linear functional of a Gaussian spatial stochastic process S(x) based on observations Yi = S(xi) + Zi at sampling locations xi, where the Zi are mutually independent, zero-mean Gaussian random variables. We describe two spatial applications for which Gaussian distributional assumptions are clearly inappropriate. The first concerns the assessment of residual contamination from nuclear weapons testing on a South Pacific island, in which the sampling method generates spatially indexed Poisson counts conditional on an unobserved spatially varying intensity of radioactivity; we conclude that a conventional geostatistical analysis oversmooths the data and underestimates the spatial extremes of the intensity. The second application provides a description of spatial variation in the risk of campylobacter infections relative to other enteric infections in part of north Lancashire and south Cumbria. For this application, we treat the data as binomial counts at unit postcode locations, conditionally on an unobserved relative risk surface which we estimate. The theoretical framework for our extension of geostatistical methods is that, conditionally on the unobserved process S(x), observations at sample locations xi form a generalized linear model with the corresponding values of S(xi) appearing as an offset term in the linear predictor. We use a Bayesian inferential framework, implemented via the Markov chain Monte Carlo method, to solve the prediction problem for non-linear functionals of S(x), making a proper allowance for the uncertainty in the estimation of any model parameters.

AB - Conventional geostatistical methodology solves the problem of predicting the realized value of a linear functional of a Gaussian spatial stochastic process S(x) based on observations Yi = S(xi) + Zi at sampling locations xi, where the Zi are mutually independent, zero-mean Gaussian random variables. We describe two spatial applications for which Gaussian distributional assumptions are clearly inappropriate. The first concerns the assessment of residual contamination from nuclear weapons testing on a South Pacific island, in which the sampling method generates spatially indexed Poisson counts conditional on an unobserved spatially varying intensity of radioactivity; we conclude that a conventional geostatistical analysis oversmooths the data and underestimates the spatial extremes of the intensity. The second application provides a description of spatial variation in the risk of campylobacter infections relative to other enteric infections in part of north Lancashire and south Cumbria. For this application, we treat the data as binomial counts at unit postcode locations, conditionally on an unobserved relative risk surface which we estimate. The theoretical framework for our extension of geostatistical methods is that, conditionally on the unobserved process S(x), observations at sample locations xi form a generalized linear model with the corresponding values of S(xi) appearing as an offset term in the linear predictor. We use a Bayesian inferential framework, implemented via the Markov chain Monte Carlo method, to solve the prediction problem for non-linear functionals of S(x), making a proper allowance for the uncertainty in the estimation of any model parameters.

KW - Generalized linear mixed model • Geostatistics • Kriging • Markov chain Monte Carlo method • Spatial prediction

U2 - 10.1111/1467-9876.00113

DO - 10.1111/1467-9876.00113

M3 - Journal article

VL - 47

SP - 299

EP - 350

JO - Journal of the Royal Statistical Society: Series C (Applied Statistics)

JF - Journal of the Royal Statistical Society: Series C (Applied Statistics)

SN - 0035-9254

IS - 3

ER -