Optimal predictive design augmentation for spatial generalised linear mixed models

Evangelos Evangelou, Zhengyuan Zhu

Research output: Contribution to journalArticle

6 Citations (Scopus)
61 Downloads (Pure)

Abstract

A typical model for geostatistical data when the observations are counts is the spatial generalised linear mixed model. We present a criterion for optimal sampling design under this framework which aims to minimise the error in the prediction of the underlying spatial random effects. The proposed criterion is derived by performing an asymptotic expansion to the conditional prediction variance. We argue that the mean of the spatial process needs to be taken into account in the construction of the predictive design, which we demonstrate through a simulation study where we compare the proposed criterion against the widely-used space-filling design. Furthermore, our results are applied to the Norway precipitation data and the rhizoctonia disease data.
Original languageEnglish
Pages (from-to)3242-3253
Number of pages12
JournalJournal of Statistical Planning and Inference
Volume142
Issue number12
Early online date31 May 2012
DOIs
Publication statusPublished - Dec 2012

Fingerprint

Generalized Linear Mixed Model
Augmentation
Prediction Variance
Conditional Variance
Spatial Process
Sampling Design
Random Effects
Asymptotic Expansion
Count
Simulation Study
Sampling
Minimise
Prediction
Demonstrate
Design
Generalized linear mixed model
Model

Cite this

Optimal predictive design augmentation for spatial generalised linear mixed models. / Evangelou, Evangelos; Zhu, Zhengyuan.

In: Journal of Statistical Planning and Inference, Vol. 142, No. 12, 12.2012, p. 3242-3253.

Research output: Contribution to journalArticle

@article{649120d349804857ac0976d8fd351b20,
title = "Optimal predictive design augmentation for spatial generalised linear mixed models",
abstract = "A typical model for geostatistical data when the observations are counts is the spatial generalised linear mixed model. We present a criterion for optimal sampling design under this framework which aims to minimise the error in the prediction of the underlying spatial random effects. The proposed criterion is derived by performing an asymptotic expansion to the conditional prediction variance. We argue that the mean of the spatial process needs to be taken into account in the construction of the predictive design, which we demonstrate through a simulation study where we compare the proposed criterion against the widely-used space-filling design. Furthermore, our results are applied to the Norway precipitation data and the rhizoctonia disease data.",
author = "Evangelos Evangelou and Zhengyuan Zhu",
year = "2012",
month = "12",
doi = "10.1016/j.jspi.2012.05.008",
language = "English",
volume = "142",
pages = "3242--3253",
journal = "Journal of Statistical Planning and Inference",
issn = "0378-3758",
publisher = "Elsevier",
number = "12",

}

TY - JOUR

T1 - Optimal predictive design augmentation for spatial generalised linear mixed models

AU - Evangelou, Evangelos

AU - Zhu, Zhengyuan

PY - 2012/12

Y1 - 2012/12

N2 - A typical model for geostatistical data when the observations are counts is the spatial generalised linear mixed model. We present a criterion for optimal sampling design under this framework which aims to minimise the error in the prediction of the underlying spatial random effects. The proposed criterion is derived by performing an asymptotic expansion to the conditional prediction variance. We argue that the mean of the spatial process needs to be taken into account in the construction of the predictive design, which we demonstrate through a simulation study where we compare the proposed criterion against the widely-used space-filling design. Furthermore, our results are applied to the Norway precipitation data and the rhizoctonia disease data.

AB - A typical model for geostatistical data when the observations are counts is the spatial generalised linear mixed model. We present a criterion for optimal sampling design under this framework which aims to minimise the error in the prediction of the underlying spatial random effects. The proposed criterion is derived by performing an asymptotic expansion to the conditional prediction variance. We argue that the mean of the spatial process needs to be taken into account in the construction of the predictive design, which we demonstrate through a simulation study where we compare the proposed criterion against the widely-used space-filling design. Furthermore, our results are applied to the Norway precipitation data and the rhizoctonia disease data.

UR - http://www.scopus.com/inward/record.url?scp=84865557480&partnerID=8YFLogxK

UR - http://dx.doi.org/10.1016/j.jspi.2012.05.008

U2 - 10.1016/j.jspi.2012.05.008

DO - 10.1016/j.jspi.2012.05.008

M3 - Article

VL - 142

SP - 3242

EP - 3253

JO - Journal of Statistical Planning and Inference

JF - Journal of Statistical Planning and Inference

SN - 0378-3758

IS - 12

ER -