Error-dependent smoothing rules in local linear regression

dc.contributor.authorCheng, M-Y
dc.contributor.authorHall, Peter
dc.date.accessioned2015-12-13T22:23:18Z
dc.date.available2015-12-13T22:23:18Z
dc.date.issued2002
dc.date.updated2015-12-11T08:04:35Z
dc.description.abstractWe suggest an adaptive, error-dependent smoothing method for reducing the variance of local-linear curve estimators. It involves weighting the bandwidth used at the ith datum in proportion to a power of the absolute value of the ith residual. We show that the optimal power is 2/3. Arguing in this way, we prove that asymptotic variance can be reduced by 24% in the case of Normal errors, and by 35% for double-exponential errors. These results might appear to violate Jianqing Fan's bounds on performance of local-linear methods, but note that our approach to smoothing produces nonlinear estimators. In the case of Normal errors, our estimator has slightly better mean squared error performance than that suggested by Fan's minimax bound, calculated by him over all estimators, not just linear ones. However, these improvements are available only for single functions, not uniformly over Fan's function class. Even greater improvements in performance are achievable for error distributions with heavier tails. For symmetric error distributions the method has no first-order effect on bias, and existing bias-reduction techniques may be used in conjunction with error-dependent smoothing. In the case of asymmetric error distributions an overall reduction in mean squared error is achievable, involving a trade-off between bias and variance contributions. However, in this setting, the technique is relatively complex and probably not practically feasible.
dc.identifier.issn1017-0405
dc.identifier.urihttp://hdl.handle.net/1885/72709
dc.publisherAcademia Sinica
dc.sourceStatistica Sinica
dc.subjectKeywords: Bandwidth; Kernel method; Nonparametric regression; Tail weight; Variance reduction
dc.titleError-dependent smoothing rules in local linear regression
dc.typeJournal article
local.bibliographicCitation.lastpage447
local.bibliographicCitation.startpage429
local.contributor.affiliationCheng, M-Y, College of Physical and Mathematical Sciences, ANU
local.contributor.affiliationHall, Peter, College of Physical and Mathematical Sciences, ANU
local.contributor.authoremailrepository.admin@anu.edu.au
local.contributor.authoruidCheng, M-Y, u951234
local.contributor.authoruidHall, Peter, u7801145
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.absfor010405 - Statistical Theory
local.identifier.ariespublicationMigratedxPub3390
local.identifier.citationvolume12
local.identifier.scopusID2-s2.0-0036556654
local.identifier.uidSubmittedByMigrated
local.type.statusPublished Version

Downloads

Back to topicon-arrow-up-solid
 
APRU
IARU
 
edX
Group of Eight Member

Acknowledgement of Country

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.


Contact ANUCopyrightDisclaimerPrivacyFreedom of Information

+61 2 6125 5111 The Australian National University, Canberra

TEQSA Provider ID: PRV12002 (Australian University) CRICOS Provider Code: 00120C ABN: 52 234 063 906