Jump estimation in inverse regression

DOI10.1214/08-EJS204MaRDI QIDQ1952028zbMATH OpenFDO

Authors Leif Boysen, Sophie Bruns, Axel Munk

Publication date 27 May 2013

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/0803.2119, https://projecteuclid.org/euclid.ejs/1260801226

zbMATH Keywords

asymptotic normalitychange-point estimationdeconvolutionentropy boundsjump estimationnative Hilbert spacespositive definite functionsreproducing kernel Hilbert spacessingular kernelstotal positivity

Mathematics Subject Classification ID

Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Nonparametric estimation (62G05) Asymptotic properties of nonparametric inference (62G20)

Abstract: We consider estimation of a step function $f$ from noisy observations of a deconvolution $phi\ast f$, where $phi$ is some bounded $L_1$-function. We use a penalized least squares estimator to reconstruct the signal $f$ from the observations, with penalty equal to the number of jumps of the reconstruction. Asymptotically, it is possible to correctly estimate the number of jumps with probability one. Given that the number of jumps is correctly estimated, we show that the corresponding parameter estimates of the jump locations and jump heights are $n^{-1/2}$ consistent and converge to a joint normal distribution with covariance structure depending on $phi$, and that this rate is minimax for bounded continuous kernels $phi$. As special case we obtain the asymptotic distribution of the least squares estimator in multiphase regression and generalisations thereof. In contrast to the results obtained for bounded $phi$, we show that for kernels with a singularity of order $O(|x{|}^{-alpha}),1/2<alpha<1$, a jump location can be estimated at a rate of $n^{-1/(3-2alpha)}$, which is again the minimax rate. We find that these rate do not depend on the spectral information of the operator rather on its localization properties in the time domain. Finally, it turns out that adaptive sampling does not improve the rate of convergence, in strict contrast to the case of direct regression.

Recommendations

• scientific article; zbMATH DE number 4169866
• Consistencies and rates of convergence of jump-penalized least squares estimators
• Estimation of the number of jumps of the jump regression functions
• Kernel-type estimators of jump points and values of a regression function
• scientific article; zbMATH DE number 10785

Cites work

• Asymptotic Statistics
• Asymptotics of M-estimators in two-phase linear regression models.
• Can one estimate the conditional distribution of post-model-selection estimators?
• Change-point estimation from indirect observations. 1. Minimax complexity
• Change-point estimation from indirect observations. 2. Adaptation
• Change-points in nonparametric regression analysis
• Designs for Regression Problems with Correlated Errors III
• Detecting a change in regression: First-order optimality
• Discontinuous versus smooth regression
• scientific article; zbMATH DE number 3120956 (Why is no real title available?)
• scientific article; zbMATH DE number 4169866 (Why is no real title available?)
• scientific article; zbMATH DE number 4071579 (Why is no real title available?)
• scientific article; zbMATH DE number 192936 (Why is no real title available?)
• scientific article; zbMATH DE number 1487502 (Why is no real title available?)
• scientific article; zbMATH DE number 1361580 (Why is no real title available?)
• scientific article; zbMATH DE number 1420699 (Why is no real title available?)
• scientific article; zbMATH DE number 3246461 (Why is no real title available?)
• scientific article; zbMATH DE number 3348831 (Why is no real title available?)
• Minimal penalties for Gaussian model selection
• Minimax theory of image reconstruction
• New Estimation and Model Selection Procedures for Semiparametric Modeling in Longitudinal Data Analysis
• On asymptotic distribution theory in segmented regression problems - identified case
• On Minimax Estimation of a Discontinuous Signal
• On the optimal rates of convergence for nonparametric deconvolution problems
• On the ratio of two correlated normal random variables
• Optimal change-point estimation from indirect observations
• Optimal Change‐point Estimation in Inverse Problems
• Scattered Data Approximation
• Sharp adaptation for inverse problems with random noise
• Sharp Optimality in Density Deconvolution with Dominating Bias. I
• Sharp Optimality in Density Deconvolution with Dominating Bias. II
• Some Hypotheses Concerning Two Phase Regression Lines
• Sparse estimators and the oracle property, or the return of Hodges' estimator
• Tests of the Hypothesis that a Linear Regression System Obeys Two Separate Regimes
• The Estimation of the Parameters of a Linear Regression System Obeying Two Separate Regimes

Cited in

(8)

• Consistencies and rates of convergence of jump-penalized least squares estimators
• Iterative Potts minimization for the recovery of signals with discontinuities from indirect measurements: the multivariate case
• Consistency of a range of penalised cost approaches for detecting multiple changepoints
• scientific article; zbMATH DE number 4169866 (Why is no real title available?)
• Jump Regressions
• The L^1-Potts functional for robust jump-sparse reconstruction
• Asymptotic laws for change point estimation in inverse regression
• Sparsity for dynamic inverse problems on Wasserstein curves with bounded variation

This page was built for publication: Jump estimation in inverse regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1952028)