Approximation by log-concave distributions, with applications to regression

DOI10.1214/10-AOS853zbMATH Open1216.62023arXiv1002.3448OpenAlexW3100270455MaRDI QIDQ548533FDOQ548533

Authors: Lutz Dümbgen, Richard Samworth, Dominic Schuhmacher 

Publication date: 29 June 2011

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

Abstract: We study the approximation of arbitrary distributions $P$ on $d$-dimensional space by distributions with log-concave density. Approximation means minimizing a Kullback--Leibler-type functional. We show that such an approximation exists if and only if $P$ has finite first moments and is not supported by some hyperplane. Furthermore we show that this approximation depends continuously on $P$ with respect to Mallows distance $D_1(cdot,cdot)$. This result implies consistency of the maximum likelihood estimator of a log-concave density under fairly general conditions. It also allows us to prove existence and consistency of estimators in regression models with a response $Y=mu(X)+epsilon$, where $X$ and $epsilon$ are independent, $mu(cdot)$ belongs to a certain class of regression functions while $epsilon$ is a random error with log-concave density and mean zero.

Full work available at URL: https://arxiv.org/abs/1002.3448

Recommendations

• Theoretical properties of the log-concave maximum likelihood estimator of a multidimensional density
• Maximum likelihood estimation of a log-concave density and its distribution function: basic properties and uniform consistency
• Multivariate log-concave distributions as a nearly parametric model
• Adaptation in log-concave density estimation
• Estimating a discrete log-concave distribution in higher dimensions

zbMATH Keywords

isotonic regressionprojectionconvex supportMallows distanceweak semicontinuity

Mathematics Subject Classification ID

Density estimation (62G07) Nonparametric regression and quantile regression (62G08) Linear regression; mixed models (62J05) Estimation in multivariate analysis (62H12) Approximations to statistical distributions (nonasymptotic) (62E17)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Limit distribution theory for maximum likelihood estimation of a log-concave density
• Multivariate log-concave distributions as a nearly parametric model
• Approximation by log-concave distributions, with applications to regression
• Maximum likelihood estimation of a log-concave density and its distribution function: basic properties and uniform consistency
• Inference and modeling with log-concave distributions
• Breakdown properties of location estimates based on halfspace depth and projected outlyingness
• Title not available (Why is that?)
• Some asymptotic theory for the bootstrap
• The Integral of a Symmetric Unimodal Function over a Symmetric Convex Set and Some Probability Inequalities
• Title not available (Why is that?)
• Large deviation probabilities for certain nonparametric maximum likelihood estimators
• Title not available (Why is that?)
• Log-concave probability and its applications
• Title not available (Why is that?)
• Differential evolution. A practical approach to global optimization. With CD-ROM.
• Theoretical properties of the log-concave maximum likelihood estimator of a multidimensional density
• Quasi-concave density estimation
• Nonparametric estimation of multivariate convex-transformed densities
• Title not available (Why is that?)
• A Note on Asymptotic Joint Normality
• Convex models, MLE and misspecification
• Consistency of multivariate log-concave density estimators
• Thinking outside the box: Statistical inference based on Kullback-Leibler empirical projections

Cited In (45)

• Local continuity of log-concave projection, with applications to estimation under model misspecification
• High-dimensional nonparametric density estimation via symmetry and shape constraints
• Exact solutions in log-concave maximum likelihood estimation
• Improved inference for vaccine-induced immune responses via shape-constrained methods
• Convergence of linear functionals of the Grenander estimator under misspecification
• Inference for the mode of a log-concave density
• Semiparametric time series models with log-concave innovations: maximum likelihood estimation and its consistency
• Editorial: Special issue on ``Nonparametric inference under shape constraints
• On the Bartlett correction of empirical likelihood for Gaussian long-memory time series
• Adaptation in log-concave density estimation
• Some approximations of the logistic distribution with application to the covariance matrix of logistic regression
• A Unifying Tutorial on Approximate Message Passing
• Independent component analysis via nonparametric maximum likelihood estimation
• An EM algorithm for fitting a mixture model with symmetric log-concave densities
• Adaptation in multivariate log-concave density estimation
• Inference for empirical Wasserstein distances on finite spaces
• The robust EM-type algorithms for log-concave mixtures of regression models
• Maximum likelihood estimation of the mixture of log-concave densities
• A new computational framework for log-concave density estimation
• A Bayesian nonparametric approach to log-concave density estimation
• Recent progress in log-concave density estimation
• Modal linear regression using log-concave distributions
• Global rates of convergence of the MLEs of log-concave and \(s\)-concave densities
• Univariate log-concave density estimation with symmetry or modal constraints
• Multivariate log-concave distributions as a nearly parametric model
• Learning Theory
• Global convergence of the log-concave MLE when the true distribution is geometric
• Variational analysis of constrained M-estimators
• Fusion of hard and soft information in nonparametric density estimation
• Adaptive estimation in symmetric location model under log-concavity constraint
• Approximation and estimation of \(s\)-concave densities via Rényi divergences
• Maximum-likelihood estimation of a log-concave density based on censored data
• On convex least squares estimation when the truth is linear
• Concave Likelihood-Based Regression with Finite-Support Response Variables
• Confidence intervals for multiple isotonic regression and other monotone models
• Log-concavity and strong log-concavity: a review
• On convergence rates of convex regression in multiple dimensions
• Approximation by log-concave distributions, with applications to regression
• R-estimation in semiparametric dynamic location-scale models
• Inference for Local Parameters in Convexity Constrained Models
• The limiting behavior of isotonic and convex regression estimators when the model is misspecified
• Bi-log-concave distribution functions
• Optimal combination of linear and spectral estimators for generalized linear models
• Monotony of Lloyd's method II for log-concave density and convex error weighting function (Corresp.)
• On computation of semiparametric maximum likelihood estimators with shape constraints

Uses Software

• LogConcDEAD
• logcondens

This page was built for publication: Approximation by log-concave distributions, with applications to regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q548533)