Consistency of data-driven histogram methods for density estimation and classification

DOI10.1214/AOS/1032894460zbMath0859.62040OpenAlexW2159075009MaRDI QIDQ1816593

Gábor Lugosi, Andrew B. Nobel

Publication date: 9 April 1997

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1032894460

zbMATH Keywords

L1-consistencystatistically equivalent blocksdata-dependent partitionsVapnik-Chervonenkis inequalitypartitioning estimatesalmost-sure risk consistencygeneral sufficient conditionshistogram classificationhistogram density estimatesmultivariate clusteringpartitioning rules

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Related Items (31)

Iterated Bernstein operators for distribution function and density estimation: balancing between the number of iterations and the polynomial degree ⋮ Estimation of Entropy and Mutual Information ⋮ Properties of Bagged Nearest Neighbour Classifiers ⋮ Bin width selection in multivariate histograms by the combinatorial method ⋮ Information dependency: strong consistency of Darbellay-Vajda partition estimators ⋮ Bayesian neural tree models for nonparametric regression ⋮ Nonlinear orthogonal series estimates for random design regression ⋮ On the convergence of Shannon differential entropy, and its connections with density and entropy estimation ⋮ Estimator selection with respect to Hellinger-type risks ⋮ Combining regular and irregular histograms by penalized likelihood ⋮ Hierarchical two-part MDL code for multinomial distributions ⋮ Density estimation via the random forest method ⋮ Multivariate Density Estimation by Bayesian Sequential Partitioning ⋮ Sample-Spacings-Based Density and Entropy Estimators for Spherically Invariant Multidimensional Data ⋮ Bandwidth choice for nonparametric classification ⋮ Classifier selection from a totally bounded class of functions ⋮ Information divergence estimation based on data-dependent partitions ⋮ An iterated classification rule based on auxiliary pseudo-predictors. ⋮ Tree-structured regression and the differentiation of integrals ⋮ Minimum distance histograms with universal performance guarantees ⋮ Consistency of data-driven histogram methods for density estimation and classification ⋮ Histogram regression estimation using data-dependent partitions ⋮ Universally consistent regression function estimation using hierarchical \(B\)-splines ⋮ A nonparametric ensemble binary classifier and its statistical properties ⋮ A kernel-based combined classification rule ⋮ Discrete minimax estimation with trees ⋮ Histogram selection in non Gaussian regression ⋮ Stochastic Tree Search for Estimating Optimal Dynamic Treatment Regimes ⋮ Universal consistency of delta estimators ⋮ Equal-bin-width histogram versus equal-bin-count histogram ⋮ An almost surely optimal combined classification rule

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Almost surely consistent nonparametric regression from recursive partitioning schemes
• Asymptotically efficient solutions to the classification problem
• Consistent nonparametric regression from recursive partitioning schemes
• Consistent nonparametric regression. Discussion
• Consistency of data-driven histogram methods for density estimation and classification
• Histogram regression estimation using data-dependent partitions
• Almost sure \(L_ 1\)-norm convergence for data-based histogram density estimates
• A Method of Fractile Graphical Analysis
• Automatic pattern recognition: a study of the probability of error
• Recursive partitioning to reduce distortion
• A histogram method of density estimation
• Rates of convergence in the source coding theorem, in empirical quantizer design, and in universal lossy source coding
• Enumeration of Seven-Argument Threshold Functions
• A Consistent Nonparametric Multivariate Density Estimator Based on Statistically Equivalent Blocks
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Almost Sure $L_r$-Norm Convergence for Data-Based Histogram Density Estimates
• Convergence of stochastic processes

This page was built for publication: Consistency of data-driven histogram methods for density estimation and classification