Data-driven neighborhood selection of a Gaussian field

Details Data-driven neighborhood selection of a Gaussian field Data-driven neighborhood selection of a Gaussian field

2009-01-15

arxiv.org/abs/0901.2213v2

Mathematics

Statistics Theory

Scientific paper

We study the nonparametric covariance estimation of a stationary Gaussian field X observed on a lattice. To tackle this issue, a neighborhood selection procedure has been recently introduced. This procedure amounts to selecting a neighborhood m by a penalization method and estimating the covariance of X in the space of Gaussian Markov random fields (GMRFs) with neighborhood m. Such a strategy is shown to satisfy oracle inequalities as well as minimax adaptive properties. However, it suffers several drawbacks which make the method difficult to apply in practice. On the one hand, the penalty depends on some unknown quantities. On the other hand, the procedure is only defined for toroidal lattices. The present contribution is threefold. A data-driven algorithm is proposed for tuning the penalty function. Moreover, the procedure is extended to non-toroidal lattices. Finally, numerical study illustrate the performances of the method on simulated examples. These simulations suggest that Gaussian Markov random field selection is often a good alternative to variogram estimation.

Affiliated with

Also associated with

No associations

Rating

Data-driven neighborhood selection of a Gaussian field does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Data-driven neighborhood selection of a Gaussian field, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Data-driven neighborhood selection of a Gaussian field will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-589738