190992
20190316235751.0
1061-8600
10.1080/10618600.2012.729982
doi
000326315500005
ISI
ARTICLE
Nonstationary Positive Definite Tapering On The Plane
Alexandria
2013
American Statistical Association
2013
18
Journal Articles
A common problem in spatial statistics is to predict a random field f at some spatial location t(0) using observations f(t(1)),..., f(t(n)) at t(1),..., t(n) epsilon IRd. Recent work by Kaufman et al. and Furrer et al. studies the use of tapering for reducing the computational burden associated with likelihood-based estimation and prediction in large spatial datasets. Unfortunately, highly irregular observation locations can present problems for stationary tapers. In particular, there can exist local neighborhoods with too few observations for sufficient accuracy, while others have too many for computational tractability. In this article, we show how to generate nonstationaty covariance tapers T(s, t) such that the number of observations in {t : T(s, t) > 0} is approximately a constant function of s. This ensures that tapering neighborhoods do not have too many points to cause computational problems but simultaneously have enough local points for accurate prediction. We focus specifically on tapering in two dimensions where quasi-conformal theory can be used. Supplementary materials for the article are available online.
Covariance tapering
Kriging
Optimization
Random fields.
Anderes, Ethan
Univ Calif Davis, Dept Stat, Davis, CA 95616 USA
Huser, RaphaĆ«l
166379
243110
Nychka, Douglas
Natl Ctr Atmospher Res, CISLs Inst Math Appl Geosci IMAGe, Boulder, CO 80305 USA
Coram, Marc
848-865
4
Journal Of Computational And Graphical Statistics
22
Publisher's version
1508999
Publisher's version
http://infoscience.epfl.ch/record/190992/files/Untitled.pdf
STAT
252136
U10124
oai:infoscience.tind.io:190992
article
SB
GLOBAL_SET
111184
EPFL-ARTICLE-190992
EPFL
PUBLISHED
REVIEWED
ARTICLE