Fourier methods for smooth distribution function estimation

DOI10.1016/J.SPL.2013.10.010zbMATH Open1288.62055arXiv1305.2476OpenAlexW2017029359MaRDI QIDQ2444403FDOQ2444403

Authors: José E. Chacón, Pablo Monfort, Carlos Tenreiro 

Publication date: 9 April 2014

Published in: Statistics \& Probability Letters (Search for Journal in Brave)

Abstract: In this paper we show how to use Fourier transform methods to analyze the asymptotic behavior of kernel distribution function estimators. Exact expressions for the mean integrated squared error in terms of the characteristic function of the distribution and the Fourier transform of the kernel are employed to obtain the limit value of the optimal bandwidth sequence in its greatest generality. The assumptions in our results are mild enough so that they are applicable when the kernel used in the estimator is a superkernel, or even the sinc kernel, and this allows to extract some interesting consequences, as the existence of a class of distributions for which the kernel estimator achieves a first-order improvement in efficiency over the empirical distribution function.

Full work available at URL: https://arxiv.org/abs/1305.2476

Recommendations

• Fourier methods for estimating mixing densities and distributions
• Smooth estimators of distribution and density functions
• Improved estimates of statistical regularization parameters in Fourier differentiation and smoothing
• On wavelet methods for estimating smooth functions
• Choosing the smoothing parameter in a fourier approach to nonparametric deconvolution of a density estimate
• scientific article; zbMATH DE number 589703

zbMATH Keywords

Fourier analysisoptimal bandwidthsinc kernelmean integrated squared errorkernel distribution estimation

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Fourier and Fourier-Stieltjes transforms and other transforms of Fourier type (42A38)

Cites Work

• Introduction to nonparametric estimation
• Bandwith selection for the smoothing of distribution functions
• An exponential inequality for the distribution function of the kernel density estimator, with applications to adaptive estimation
• Bandwidth selection for kernel distribution function estimation
• Smoothing parameter selection for smooth distribution functions
• Multistage plug—in bandwidth selection for kernel distribution function estimates
• A note on kernel density estimation at a parametric rate†
• A New Kernel Distribution Function Estimator Based on a Non‐parametric Transformation of the Data
• A note on the universal consistency of the kernel distribution function estimator
• Title not available (Why is that?)
• Some New Estimates for Distribution Functions
• CDF and survival function estimation with infinite-order kernels
• Correction of Density Estimators that are not Densities
• Title not available (Why is that?)
• Title not available (Why is that?)
• Modifying the kernel distribution function estimator towards reduced bias
• On the existence and limit behavior of the optimal bandwidth for kernel density estimation
• An automatic bandwidth selector for kernel density estimation
• Inversion Formulae for the Distribution of Ratios
• Admissible kernel estimators of a multivariate density
• Mean integrated square error properties of density estimates
• The performance of kernel density functions in kernel distribution function estimation
• Some Errors Associated with the Non-parametric Estimation of Density Functions
• Asymptotic behaviour of multistage plug-in bandwidth selections for kernel distribution function estimators
• Title not available (Why is that?)
• Mean intergrated squared error properties and optimal kernels when estimating a diatribution function
• Some extensions of the asymptotics of a kernel estimator of a distribution function
• Note on the minimum mean integrated squared error of kernel estimates of a distribution function and its derivatives
• Distribution function estimation: a review
• Facts about the gaussian probability density function
• Uniform in bandwidth limit laws for kernel distribution function estimators
• On the asymptotic behaviour of the ISE for automatic kernel distribution estimators

Cited In (6)

• Efficiency behaviour of kernel-smoothed kernel distribution function estimators
• A new class of boundary kernels for distribution function estimation
• Unbiasedness of fourier integral estimator under weaker assumptions
• Exact mean integrated squared error and bandwidth selection for kernel distribution function estimators
• A fortran implementation of univariate fourier series density estimation
• On a new higher order kernel for density estimation

This page was built for publication: Fourier methods for smooth distribution function estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2444403)