Asymptotics and optimal bandwidth selection for highest density region estimation
From MaRDI portal
Publication:973884
DOI10.1214/09-AOS766zbMATH Open1189.62061arXiv1010.0591MaRDI QIDQ973884FDOQ973884
Authors: Richard Samworth, M. P. Wand 
Publication date: 26 May 2010
Published in: The Annals of Statistics (Search for Journal in Brave)
Abstract: We study kernel estimation of highest-density regions (HDR). Our main contributions are two-fold. First, we derive a uniform-in-bandwidth asymptotic approximation to a risk that is appropriate for HDR estimation. This approximation is then used to derive a bandwidth selection rule for HDR estimation possessing attractive asymptotic properties. We also present the results of numerical studies that illustrate the benefits of our theory and methodology.
Full work available at URL: https://arxiv.org/abs/1010.0591
Recommendations
- Bandwidth selection for kernel density estimators of multivariate level sets and highest density regions
- Asymptotics and optimal bandwidth for nonparametric estimation of density level sets
- Asymptotically best bandwidth selectors in kernel density estimation
- On optimal data-based bandwidth selection in kernel density estimation
- An asymptotically efficient solution to the bandwidth problem of kernel density estimation
Cites Work
- Title not available (Why is that?)
- Exact mean integrated squared error
- Title not available (Why is that?)
- Title not available (Why is that?)
- Rates of strong uniform consistency for multivariate kernel density estimators. (Vitesse de convergence uniforme presque sûre pour des estimateurs à noyaux de densités multivariées)
- On nonparametric estimation of density level sets
- Total error in a plug-in estimator of level sets.
- Asymptotic normality of plug-in level set estimates
- Optimal rates for plug-in estimators of density level sets
- Kernel estimation of density level sets
- Measuring mass concentrations and estimating density contour clusters -- An excess mass approach
- Excess Mass Estimates and Tests for Multimodality
- Estimation of a Convex Density Contour in Two Dimensions
- Uniform Central Limit Theorems
- Convergence rates in nonparametric estimation of level sets
- Nonparametric density estimation and clustering in astronomical sky surveys
- Title not available (Why is that?)
- Accuracy of binned kernel functional approximations
Cited In (23)
- Inference for the mode of a log-concave density
- Hypothesis testing based on a vector of statistics
- Detecting relevant changes in the mean of nonstationary processes -- a mass excess approach
- A Review on Modal Clustering
- A comparative simulation study of data-driven methods for estimating density level sets
- Level Set Estimation
- Wavelet-based gradient boosting
- Nonparametric estimation of regression level sets using kernel plug-in estimator
- A data-adaptive method for estimating density level sets under shape conditions
- Optimal subgroup selection
- Asymptotics and optimal bandwidth for nonparametric estimation of density level sets
- Smallest covering regions and highest density regions for discrete distributions
- Continuous record Laplace-based inference about the break date in structural change models
- Bandwidth selection for kernel density estimators of multivariate level sets and highest density regions
- Bayesian adaptive bandwidth kernel density estimation of irregular multivariate distributions
- Asymptotic properties of plug-in level set estimators for right censored data
- Modal clustering asymptotics with applications to bandwidth selection
- Nonparametric estimation of directional highest density regions
- Distribution-Free Prediction Sets
- Kernel conditional density estimation when the regressor is valued in a semi-metric space
- Confidence regions for level sets
- GENERALIZED LAPLACE INFERENCE IN MULTIPLE CHANGE-POINTS MODELS
- Optimal weighted nearest neighbour classifiers
Uses Software
This page was built for publication: Asymptotics and optimal bandwidth selection for highest density region estimation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q973884)
