Data-driven neighborhood selection of a Gaussian field Verzelen, Nicolas

User activity

Share to:
View the summary of this work
Author
Verzelen, Nicolas
Appears In
Computational Statistics and Data Analysis
Subjects
[MATH:MATH_ST] Mathematics/Statistics; research report; Algorithms -- Analysis
Audience
Academic
Summary
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.
Bookmark
http://trove.nla.gov.au/work/278434
Work ID
278434

User activity


e.g. test cricket, Perth (WA), "Parkes, Henry"

Separate different tags with a comma. To include a comma in your tag, surround the tag with double quotes.

Be the first to add a tag for this work

Be the first to add this to a list

Comments and reviews

What are comments? Add a comment

No user comments or reviews for this work

Add a comment


Show comments and reviews from Amazon users