Unbiased risk estimation method for covariance estimation. (25th July 2014)

• Record Type: Journal Article
• Authors: Lescornel, Hélène; Loubes, Jean-Michel; Chabriac, Claudie
• Is Part Of: ESAIM. Volume 18(2014)
• Page Start: 251
• Page End: 264
• Publication Date: 2014-07-25
• Subjects: Covariance estimation, -- model selection, -- U.R.E. method; Probabilities -- Periodicals; Mathematical statistics -- Periodicals; 519.2
• DOI: 10.1051/ps/2013034
• Languages: English
• ISSNs: 1292-8100

Abstract

Abstract : We consider a model selection estimator of the covariance of a random process. Using the Unbiased Risk Estimation (U.R.E.) method, we build an estimator of the risk which allows to select an estimator in a collection of models. Then, we present an oracle inequality which ensures that the risk of the selected estimator is close to the risk of the oracle. Simulations show the efficiency of this methodology.