On Global Properties of Variable Bandwidth Density Estimators
Hall, Peter
Ann. Statist., Tome 20 (1992) no. 1, p. 762-778 / Harvested from Project Euclid
It is argued that mean integrated squared error is not a useful measure of the performance of a variable bandwidth density estimator based on Abramson's square root law. The reason is that when the unknown density $f$ has even moderately light tails, properties of those tails drive the formula for optimal bandwidth, to the virtual exclusion of other properties of $f$. We suggest that weighted integrated squared error be employed as the performance criterion, using a weight function with compact support. It is shown that this criterion is driven by pointwise properties of $f$. Furthermore, weighted squared-error cross-validation selects a bandwidth which gives first-order asymptotic optimality of an adaptive, feasible version of Abramson's variable bandwidth estimator.
Publié le : 1992-06-14
Classification:  Cross-validation,  density estimation,  integrated squared error,  square root law,  variable bandwidth,  62G05,  62H12
@article{1176348655,
     author = {Hall, Peter},
     title = {On Global Properties of Variable Bandwidth Density Estimators},
     journal = {Ann. Statist.},
     volume = {20},
     number = {1},
     year = {1992},
     pages = { 762-778},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176348655}
}
Hall, Peter. On Global Properties of Variable Bandwidth Density Estimators. Ann. Statist., Tome 20 (1992) no. 1, pp.  762-778. http://gdmltest.u-ga.fr/item/1176348655/