Asymptotics for Least Squares Cross-Validation Bandwidths in Nonsmooth Cases
van Es, Bert
Ann. Statist., Tome 20 (1992) no. 1, p. 1647-1657 / Harvested from Project Euclid
We consider the problem of bandwidth selection for kernel density estimators. Let $H_n$ denote the bandwidth computed by the least squares cross-validation method. Furthermore, let $H^\ast_n$ and $h^\ast_n$ denote the minimizers of the integrated squared error and the mean integrated squared error, respectively. The main theorem establishes asymptotic normality of $H_n - H^\ast_n$ and $H_n - h^\ast_n$, for three classes of densities with comparable smoothness properties. Apart from densities satisfying the standard smoothness conditions, we also consider densities with a finite number of jumps or kinks. We confirm the $n^{-1/10}$ rate of convergence to 0 of the relative distances $(H_n - H^\ast_n)/H^\ast_n$ and $(H_n - h^\ast_n)/h^\ast_n$ derived by Hall and Marron in the smooth case. Unexpectedly, in turns out that these relative rates of convergence are faster in the nonsmooth cases.
Publié le : 1992-09-14
Classification:  Density estimation,  kernel estimators,  bandwidth selection,  cross-validation,  rates of convergence,  62G05,  62E20
@article{1176348790,
     author = {van Es, Bert},
     title = {Asymptotics for Least Squares Cross-Validation Bandwidths in Nonsmooth Cases},
     journal = {Ann. Statist.},
     volume = {20},
     number = {1},
     year = {1992},
     pages = { 1647-1657},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176348790}
}
van Es, Bert. Asymptotics for Least Squares Cross-Validation Bandwidths in Nonsmooth Cases. Ann. Statist., Tome 20 (1992) no. 1, pp.  1647-1657. http://gdmltest.u-ga.fr/item/1176348790/