Confidence balls in Gaussian regression
Baraud, Yannick
Ann. Statist., Tome 32 (2004) no. 1, p. 528-551 / Harvested from Project Euclid
Starting from the observation of an ℝn-Gaussian vector of mean f and covariance matrix σ2In (In is the identity matrix), we propose a method for building a Euclidean confidence ball around f, with prescribed probability of coverage. For each n, we describe its nonasymptotic property and show its optimality with respect to some criteria.
Publié le : 2004-04-14
Classification:  Confidence ball,  nonparametric regression,  hypothesis testing,  estimation,  62G15,  62G05,  62G10
@article{1083178937,
     author = {Baraud, Yannick},
     title = {Confidence balls in Gaussian regression},
     journal = {Ann. Statist.},
     volume = {32},
     number = {1},
     year = {2004},
     pages = { 528-551},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1083178937}
}
Baraud, Yannick. Confidence balls in Gaussian regression. Ann. Statist., Tome 32 (2004) no. 1, pp.  528-551. http://gdmltest.u-ga.fr/item/1083178937/