Exploring spatial nonlinearity using additive approximation

We propose to approximate the conditional expectation of a spatial random variable given its nearest neighbour observations by an additive function. The setting is meaningful in practice and requires no unilateral ordering. It is capable of catching nonlinear features in spatial data and exploring l...

Full description

Bibliographic Details
Main Authors: Lu, Zudi, Lundervold, A., Tjostheim, D., YAO, Qiwei
Format: Journal Article
Published: International Statistical Institute/Bernoulli Society 2007
Online Access:http://isi.cbs.nl/bernoulli/index.htm
http://hdl.handle.net/20.500.11937/20467
_version_ 1848750312802746368
author Lu, Zudi
Lundervold, A.
Tjostheim, D.
YAO, Qiwei
author_facet Lu, Zudi
Lundervold, A.
Tjostheim, D.
YAO, Qiwei
author_sort Lu, Zudi
building Curtin Institutional Repository
collection Online Access
description We propose to approximate the conditional expectation of a spatial random variable given its nearest neighbour observations by an additive function. The setting is meaningful in practice and requires no unilateral ordering. It is capable of catching nonlinear features in spatial data and exploring local dependence structures. Our approach is different from both Markov field methods and disjunctive kriging. The asymptotic properties of the additive estimators have been established for α-mixing spatial processes by extending the theory of the backfitting procedure to the spatial case. This facilitates the confidence intervals for the component functions, although the asymptotic biases have to be estimated via (wild) bootstrap. Simulation results are reported. Applications to real data illustrate that the improvement in describing the data over the auto-normal scheme is significant when nonlinearity or non-Gaussianity is pronounced.
first_indexed 2025-11-14T07:34:50Z
format Journal Article
id curtin-20.500.11937-20467
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:34:50Z
publishDate 2007
publisher International Statistical Institute/Bernoulli Society
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-204672017-01-30T12:19:27Z Exploring spatial nonlinearity using additive approximation Lu, Zudi Lundervold, A. Tjostheim, D. YAO, Qiwei We propose to approximate the conditional expectation of a spatial random variable given its nearest neighbour observations by an additive function. The setting is meaningful in practice and requires no unilateral ordering. It is capable of catching nonlinear features in spatial data and exploring local dependence structures. Our approach is different from both Markov field methods and disjunctive kriging. The asymptotic properties of the additive estimators have been established for α-mixing spatial processes by extending the theory of the backfitting procedure to the spatial case. This facilitates the confidence intervals for the component functions, although the asymptotic biases have to be estimated via (wild) bootstrap. Simulation results are reported. Applications to real data illustrate that the improvement in describing the data over the auto-normal scheme is significant when nonlinearity or non-Gaussianity is pronounced. 2007 Journal Article http://hdl.handle.net/20.500.11937/20467 http://isi.cbs.nl/bernoulli/index.htm International Statistical Institute/Bernoulli Society restricted
spellingShingle Lu, Zudi
Lundervold, A.
Tjostheim, D.
YAO, Qiwei
Exploring spatial nonlinearity using additive approximation
title Exploring spatial nonlinearity using additive approximation
title_full Exploring spatial nonlinearity using additive approximation
title_fullStr Exploring spatial nonlinearity using additive approximation
title_full_unstemmed Exploring spatial nonlinearity using additive approximation
title_short Exploring spatial nonlinearity using additive approximation
title_sort exploring spatial nonlinearity using additive approximation
url http://isi.cbs.nl/bernoulli/index.htm
http://hdl.handle.net/20.500.11937/20467