Uniformly valid post-regularization confidence regions for many functional parameters in z-estimation framework

DOI10.1214/17-AOS1671zbMATH Open1407.62268arXiv1512.07619OpenAlexW2963629082WikidataQ92909056 ScholiaQ92909056MaRDI QIDQ1990597FDOQ1990597

Authors: Victor Chernozhukov, Denis Chetverikov, Ying Wei, A. Belloni 

Publication date: 25 October 2018

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

Abstract: In this paper we develop procedures to construct simultaneous confidence bands for $ildep$ potentially infinite-dimensional parameters after model selection for general moment condition models where $ildep$ is potentially much larger than the sample size of available data, $n$. This allows us to cover settings with functional response data where each of the $ildep$ parameters is a function. The procedure is based on the construction of score functions that satisfy certain orthogonality condition. The proposed simultaneous confidence bands rely on uniform central limit theorems for high-dimensional vectors (and not on Donsker arguments as we allow for $ildepggn$). To construct the bands, we employ a multiplier bootstrap procedure which is computationally efficient as it only involves resampling the estimated score functions (and does not require resolving the high-dimensional optimization problems). We formally apply the general theory to inference on regression coefficient process in the distribution regression model with a logistic link, where two implementations are analyzed in detail. Simulations and an application to real data are provided to help illustrate the applicability of the results.

Full work available at URL: https://arxiv.org/abs/1512.07619

Recommendations

• Uniform post-selection inference for least absolute deviation regression and other Z-estimation problems
• Uniform consistency of a class of regression function estimators
• Non-asymptotic confidence regions for regularized linear regression estimates
• Strong uniform consistency of nonparametric regression function estimates
• A unified theory of confidence regions and testing for high-dimensional estimating equations
• Uniform consistency of \(k\mathrm{NN}\) regressors for functional variables
• Universal confidence sets for the mode of a regression function
• Nonparametric regression, confidence regions and regularization
• Uniform confidence bands for nonparametric errors-in-variables regression

zbMATH Keywords

inference after model selectionLasso and post-Lasso with functional response datamoment condition models with a continuum of target parameters

Mathematics Subject Classification ID

Nonparametric tolerance and confidence regions (62G15) Estimation in multivariate analysis (62H12) Ridge regression; shrinkage estimators (Lasso) (62J07)

Cites Work

• Weak convergence and empirical processes. With applications to statistics
• Introduction to empirical processes and semiparametric inference
• Asymptotic Statistics
• Central limit theorems and bootstrap in high dimensions
• Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• Asymptotics for Semiparametric Econometric Models Via Stochastic Equicontinuity
• Double/debiased machine learning for treatment and structural parameters
• Confidence Intervals for Low Dimensional Parameters in High Dimensional Linear Models
• On asymptotically optimal confidence regions and tests for high-dimensional models
• Least squares after model selection in high-dimensional sparse models
• Comparison and anti-concentration bounds for maxima of Gaussian random vectors
• Bootstrap and wild bootstrap for high dimensional linear models
• \(\ell_1\)-penalized quantile regression in high-dimensional sparse models
• Gaussian approximations and multiplier bootstrap for maxima of sums of high-dimensional random vectors
• Sparse models and methods for optimal instruments with an application to eminent domain
• Sparse estimators and the oracle property, or the return of Hodges' estimator
• Hypothesis Testing in High-Dimensional Regression Under the Gaussian Random Design Model: Asymptotic Theory
• Semiparametric efficiency bounds
• Efficiency Bounds for Semiparametric Regression
• The Asymptotic Variance of Semiparametric Estimators
• Inference on treatment effects after selection among high-dimensional controls
• Inference on counterfactual distributions
• Conditional Transformation Models
• On the distribution of penalized maximum likelihood estimators: the LASSO, SCAD, and thresholding
• Title not available (Why is that?)
• Uniformly valid post-regularization confidence regions for many functional parameters in z-estimation framework
• Title not available (Why is that?)
• Empirical and multiplier bootstraps for suprema of empirical processes of increasing complexity, and related Gaussian couplings
• Uniform Central Limit Theorems
• Gaussian approximation of suprema of empirical processes
• Anti-concentration and honest, adaptive confidence bands
• CAN ONE ESTIMATE THE UNCONDITIONAL DISTRIBUTION OF POST-MODEL-SELECTION ESTIMATORS?
• Semiparametric Efficiency in Multivariate Regression Models with Missing Data
• Uniform post-selection inference for least absolute deviation regression and other Z-estimation problems
• Pivotal estimation via square-root lasso in nonparametric regression
• Title not available (Why is that?)
• GUEST EDITORS' EDITORIAL: RECENT DEVELOPMENTS IN MODEL SELECTION AND RELATED AREAS

Cited In (22)

• Statistical inference in sparse high-dimensional additive models
• Uniform post-selection inference for least absolute deviation regression and other Z-estimation problems
• Uniformly valid post-regularization confidence regions for many functional parameters in z-estimation framework
• Debiased machine learning of set-identified linear models
• Non-separable models with high-dimensional data
• Estimation and inference for policy relevant treatment effects
• Inference on heterogeneous treatment effects in high‐dimensional dynamic panels under weak dependence
• Unconditional quantile regression with high‐dimensional data
• On LASSO for predictive regression
• Multiway Cluster Robust Double/Debiased Machine Learning
• Transformation Models in High Dimensions
• Nonsparse learning with latent variables
• Model-assisted inference for treatment effects using regularized calibrated estimation with high-dimensional data
• Nonparametric Tests of the Causal Null With Nondiscrete Exposures
• On rank estimators in increasing dimensions
• POST-SELECTION INFERENCE IN THREE-DIMENSIONAL PANEL DATA
• Functional delta residuals and applications to simultaneous confidence bands of moment based statistics
• Simultaneous confidence bands for functional data using the Gaussian kinematic formula
• High-dimensional simultaneous inference with the bootstrap
• ArCo: an artificial counterfactual approach for high-dimensional panel time-series data
• Generalized M-estimators for high-dimensional Tobit I models
• Improved central limit theorem and bootstrap approximations in high dimensions

This page was built for publication: Uniformly valid post-regularization confidence regions for many functional parameters in z-estimation framework

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1990597)