Mellin-Meijer kernel density estimation on R^+

DOI10.1007/S10463-020-00772-1zbMATH Open1473.62120arXiv1707.04301OpenAlexW3107410504MaRDI QIDQ2230876FDOQ2230876

Authors: Gery Geenens 

Publication date: 28 September 2021

Published in: Annals of the Institute of Statistical Mathematics (Search for Journal in Brave)

Abstract: Nonparametric kernel density estimation is a very natural procedure which simply makes use of the smoothing power of the convolution operation. Yet, it performs poorly when the density of a positive variable is to be estimated (boundary issues, spurious bumps in the tail). So various extensions of the basic kernel estimator allegedly suitable for $mathbb{R}^{+}$-supported densities, such as those using Gamma or other asymmetric kernels, abound in the literature. Those, however, are not based on any valid smoothing operation analogous to the convolution, which typically leads to inconsistencies. By contrast, in this paper a kernel estimator for $mathbb{R}^{+}$-supported densities is defined by making use of the Mellin convolution, the natural analogue of the usual convolution on $mathbb{R}^{+}$. From there, a very transparent theory flows and leads to new type of asymmetric kernels strongly related to Meijer's $G$-functions. The numerous pleasant properties of this `Mellin-Meijer-kernel density estimator' are demonstrated in the paper. Its pointwise and $L_2$-consistency (with optimal rate of convergence) is established for a large class of densities, including densities unbounded at 0 and showing power-law decay in their right tail. Its practical behaviour is investigated further through simulations and some real data analyses.

Full work available at URL: https://arxiv.org/abs/1707.04301

Recommendations

• Varying kernel density estimation on \(\mathbb R_+\)
• Nonparametric density estimation for classes of positive random variables
• Convolution power kernels for density estimation
• Asymptotic results for continuous associated kernel estimators of density functions
• Probability density function estimation using gamma kernels

zbMATH Keywords

Mellin transformkernel density estimatorasymmetric kernelsMeijer \(G\)-functionsboundary issues

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20)

Cites Work

• Title not available (Why is that?)
• Miscellanea Kernel-Type Density Estimation on the Unit Interval
• Title not available (Why is that?)
• Title not available (Why is that?)
• Variable kernel density estimation
• Simple and effective boundary correction for kernel densities and regression with an application to the world income and Engel curve estimation
• Nonparametric and semiparametric models.
• On automatic boundary corrections
• Smooth optimum kernel estimators near endpoints
• Incorporating support constraints into nonparametric estimators of densities
• Title not available (Why is that?)
• Asymptotics and Mellin-Barnes integrals
• An Improved Estimator of the Density Function at the Boundary
• Some Applications of the Mellin Transform in Statistics
• Title not available (Why is that?)
• CONSISTENCY OF ASYMMETRIC KERNEL DENSITY ESTIMATORS AND SMOOTHED HISTOGRAMS WITH APPLICATION TO INCOME DATA
• Density estimation using inverse and reciprocal inverse Gaussian kernels
• Probability density function estimation using gamma kernels
• Nonparametric kernel density estimation near the boundary
• Nonnegative bias reduction methods for density estimation using asymmetric kernels
• Statistical inference for time-changed Lévy processes via Mellin transform approach
• Meijer G-Functions: A Gentle Introduction
• Re-formulation of inverse Gaussian, reciprocal inverse Gaussian, and Birnbaum-Saunders kernel estimators
• A generalized reflection method of boundary correction in kernel density estimation
• Title not available (Why is that?)
• Title not available (Why is that?)
• Convolution power kernels for density estimation
• Improved variable window kernel estimates of probability densities
• Weighted log-normal kernel density estimation
• Moment density estimation for positive random variables
• Varying kernel density estimation on \(\mathbb R_+\)
• Title not available (Why is that?)
• Family of the generalised gamma kernels: a generator of asymmetric kernels for nonnegative data
• A note on the performance of the gamma kernel estimators at the boundary
• On Some Applications of Mellin Transforms to Statistics: Dependent Random Variables
• Generalized Birnbaum-Saunders kernel density estimators and an analysis of financial data
• Nonparametric density estimation for nonnegative data, using symmetrical-based inverse and reciprocal inverse Gaussian kernels through dual transformation
• A gamma kernel density estimation for insurance loss data
• Generalised gamma kernel density estimation for nonnegative data and its bias reduction
• On the use of bivariate Mellin transform in bivariate random scaling and some applications
• Some applications of Meijer-G functions to distribution problems in statistics
• Local-Likelihood Transformation Kernel Density Estimation for Positive Random Variables

Cited In (3)

• Asymptotic evaluations for multivariate Mellin convolution operators
• Varying kernel density estimation on \(\mathbb R_+\)
• The complete asymptotic evaluation for Mellin convolution operators

Uses Software

• KernSmooth

This page was built for publication: Mellin-Meijer kernel density estimation on \(\mathbb{R}^+\)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2230876)