Kernel estimators and
the Dvoretzky–Kiefer–Wolfowitz inequality
Applicationes Mathematicae, Tome 34 (2007) no. 4, pp. 401-404
It turns out that for standard kernel estimators no inequality like that of Dvoretzky–Kiefer–Wolfowitz can be constructed, and as a result it is impossible to answer the question of how many observations are needed to guarantee a prescribed level of accuracy of the estimator. A remedy is to adapt the bandwidth to the sample at hand.
Keywords:
turns out standard kernel estimators inequality dvoretzky kiefer wolfowitz constructed result impossible answer question many observations needed guarantee prescribed level accuracy estimator remedy adapt bandwidth sample
Affiliations des auteurs :
Ryszard Zieli/nski  1
@article{10_4064_am34_4_3,
author = {Ryszard Zieli/nski},
title = {Kernel estimators and
the {Dvoretzky{\textendash}Kiefer{\textendash}Wolfowitz} inequality},
journal = {Applicationes Mathematicae},
pages = {401--404},
year = {2007},
volume = {34},
number = {4},
doi = {10.4064/am34-4-3},
language = {en},
url = {http://geodesic.mathdoc.fr/articles/10.4064/am34-4-3/}
}
Ryszard Zieli/nski. Kernel estimators and the Dvoretzky–Kiefer–Wolfowitz inequality. Applicationes Mathematicae, Tome 34 (2007) no. 4, pp. 401-404. doi: 10.4064/am34-4-3
Cité par Sources :