Model Selection for Estimating the Non Zero Components of a Gaussian Vector

@inproceedings{Huet2006ModelSF,
  title={Model Selection for Estimating the Non Zero Components of a Gaussian Vector},
  author={Sylvie Huet},
  year={2006}
}
We propose a method based on a penalised likelihood criterion, for estimating the number on non-zero components of the mean of a Gaussian vector. Following the work of Birgé and Massart in Gaussian model selection, we choose the penalty function such that the resulting estimator minimises the Kullback risk. Mathematics Subject Classification. 62G05, 62G09. Received January 13, 2004. Revised September 28, 2005. Introduction The following regression model is considered: X = m + τε, ε ∼ Nn(0, In… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 22 references

A bayesian analysis of the minimum aic procedure

H. Akaike
Ann. Inst. Statist. Math • 1978
View 11 Excerpts
Highly Influenced

Comparison of methods for estimating the non zero components of a gaussian vector

S. Huet
Technical report, • 2005
View 3 Excerpts
Highly Influenced

Adaptive variable selection competes with bayes expert

D. P. Foster, R. A. Stine
Technical report, The Wharton School of the University of Pennsylvania, Philadelphia • 2002
View 3 Excerpts
Highly Influenced

Maximum likelihood principle and model selection when the true model is unspecified

R. Nishii
J. Multivariate Anal • 1988
View 3 Excerpts
Highly Influenced

Universal coding, information, prediction, and estimation

IEEE Trans. Information Theory • 1984
View 3 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…