Honest Confidence Regions for Nonparametric Regression
Li, Ker-Chau
Ann. Statist., Tome 17 (1989) no. 1, p. 1001-1008 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
The problem of constructing honest confidence regions for nonparametric regression is considered. A lower rate of convergence, $n^{-1/4}$, for the size of the confidence region is established. The achievability of this rate is demonstrated using Stein's estimates and the associated unbiased risk estimates. Practical implications are discussed.
Publié le : 1989-09-14
Classification:  Adaptiveness,  confidence region,  convergence rate,  nonparametric regression,  Stein estimates,  Stein's unbiased risk estimates,  62G99,  62J99 
@article{1176347253,
     author = {Li, Ker-Chau},
     title = {Honest Confidence Regions for Nonparametric Regression},
     journal = {Ann. Statist.},
     volume = {17},
     number = {1},
     year = {1989},
     pages = { 1001-1008},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176347253}
}

Li, Ker-Chau. Honest Confidence Regions for Nonparametric Regression. Ann. Statist., Tome 17 (1989) no. 1, pp.  1001-1008. http://gdmltest.u-ga.fr/item/1176347253/