34 Pages
English
Gain access to the library to view online
Learn more

Chapitre Hierarchical modelling for univariate data

-

Gain access to the library to view online
Learn more
34 Pages
English

Description

Chapitre 5.3 Hierarchical modelling for univariate data : nonstationary spatial process model S. Banerjee, B. Carlin, A. Gelfand 19 octobre 2006

  • r2 processus spatial

  • stationnaire isotrope

  • process model

  • hierarchical modelling

  • covariance cov

  • processus

  • processus stationnaire


Subjects

Informations

Published by
Published 01 October 2006
Reads 6
Language English
Document size 3 MB

Exrait

Chapitre 5.3 Hierarchical modelling for univariate data nonstationary spatial process model
S. Banerjee, B. Carlin, A. Gelfand
19 octobre 2006
:
Processus stationnaires
Z(s),sDR2processus spatial
faiblement stationnaire:
E(Z(s)) =µR Cov(Z(s+h),Z(s)) =C(h),hR2
Plus fort,faiblement stationnaire isotrope:
E(Z(s)) =µR Cov(Z(s+h),Z(s)) =C(khk),hR2
ns fort,sertntseuemnniataoiins`eqtrin:
Un peu moins fort,
E(Z(s)Z(s+h)) = 0 Var(Z(s+h),Z(s)) =γC(h),hR2
e.cnairtion)staZ(s(Cevoaicnvora),s(s=C))sZ(),uaessere´tnisnOs)βetZ(semplexT(s(,)vace=)(µ)sη+nunee(llemηdenoyeuqetnemrtni`sniednreicrsa.
Danslaplupartdesapplications(environnement,´ecologie, climatologie,...),lestroishypoth`esessontirr´ealistes:
Processus non stationnaires
iseeaitrienmie,brtpoinosas)=parexZ(s))=µ(dnnaec(E.,..)etzoe,lenaetm´qurieipooe´gina(rtos