Quasi-universal bandwidth selection for kernel density estimators

DOI10.2307/3315649zbMath1066.62521OpenAlexW2005928911MaRDI QIDQ4267419

Marten H. Wegkamp

Publication date: 19 December 1999

Published in: Canadian Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2307/3315649

zbMATH Keywords

kernel density estimatorsAsymptotic optimalitydata splittingprojection estimators, empirical processesuniversal bandwidth selection

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Nonparametric estimation (62G05) Sums of independent random variables; random walks (60G50)

Related Items

Bandwidth selection for kernel density estimation: a review of fully automatic selectors, Adaptive density estimation using the blockwise Stein method, Model selection in nonparametric regression, Oracle inequalities for probability density estimations, SPADES and mixture models, Linear and convex aggregation of density estimators, Copula Density Estimation Using Multiwavelets Based on the Multiresolution Analysis, A note on penalized minimum distance estimation in nonparametric regression

Cites Work

• Unnamed Item
• Distribution-free lower bounds in density estimation
• The equivalence of weak, strong, and complete convergence in \(L_ 1\) for kernel density estimates
• An asymptotically optimal window selection rule for kernel density estimates
• A universally acceptable smoothing factor for kernel density estimates
• Nonasymptotic universal smoothing factors, kernel complexity and Yatracos classes
• Weak convergence and empirical processes. With applications to statistics