A Kriging procedure for processes indexed by graphs
Statistics Theory
2014-06-26 v1 Statistics Theory
Abstract
We provide a new kriging procedure of processes on graphs. Based on the construction of Gaussian random processes indexed by graphs, we extend to this framework the usual linear prediction method for spatial random fields, known as kriging. We provide the expression of the estimator of such a random field at unobserved locations as well as a control for the prediction error.
Cite
@article{arxiv.1406.6592,
title = {A Kriging procedure for processes indexed by graphs},
author = {Thibault Espinasse and Jean-Michel Loubes},
journal= {arXiv preprint arXiv:1406.6592},
year = {2014}
}