On asymptotically optimal confidence regions and tests for high-dimensional models

Abstract

We propose a general method for constructing confidence intervals and statistical tests for single or low-dimensional components of a large parameter vector in a high-dimensional model. It can be easily adjusted for multiplicity taking dependence among tests into account. For linear models, our method is essentially the same as in Zhang and Zhang [J. R. Stat. Soc. Ser. B Stat. Methodol. 76 (2014) 217-242]: we analyze its asymptotic properties and establish its asymptotic optimality in terms of semiparametric efficiency. Our method naturally extends to generalized linear models with convex loss functions. We develop the corresponding theory which includes a careful analysis for Gaussian, sub-Gaussian and bounded correlated designs.

Published in at http://dx.doi.org/10.1214/14-AOS1221 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (11)

• Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
• Valid post-selection inference
• The sparsity and bias of the Lasso selection in high-dimensional linear regression
• Lasso-type recovery of sparse representations for high-dimensional data
• High-dimensional generalized linear models and the lasso
• High-dimensional variable selection
• Sparsity oracle inequalities for the Lasso
• Confidence sets in sparse regression
• Rates of convergence of the Adaptive LASSO estimators to the Oracle distribution and higher order refinements by the bootstrap
• Quasi-Likelihood and/or Robust Estimation in High Dimensions
• On the Distribution of Penalized Maximum Likelihood Estimators: The LASSO, SCAD, and Thresholding

Cited by in corpus (77)

• Controlling the false discovery rate via knockoffs
• Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations
• Deep Neural Networks for Estimation and Inference
• SLOPE - Adaptive variable selection via convex optimization
• A modern maximum-likelihood theory for high-dimensional logistic regression
• Asymptotic normality and optimalities in estimation of large Gaussian graphical models
• High-Dimensional Inference: Confidence Intervals, $p$-Values and R-Software hdi
• Valid Post-Selection and Post-Regularization Inference: An Elementary, General Approach
• Gene Hunting with Knockoffs for Hidden Markov Models
• Inference and Uncertainty Quantification for Noisy Matrix Completion
• Confidence intervals for high-dimensional inverse covariance estimation
• High-dimensional regression adjustments in randomized experiments
• Improving Metrology with Quantum Scrambling
• Contributed Discussion to Uncertainty Quantification for the Horseshoe by Stéphanie van der Pas, Botond Szabó and Aad van der Vaart
• Global and Simultaneous Hypothesis Testing for High-Dimensional Logistic Regression Models
• High-Dimensional Survival Analysis: Methods and Applications
• High-dimensional inference in misspecified linear models
• Network classification with applications to brain connectomics
• Linear Hypothesis Testing in Dense High-Dimensional Linear Models
• Goodness of fit tests for high-dimensional linear models
• Statistical Inference, Learning and Models in Big Data
• Spike-and-Slab Group Lassos for Grouped Regression and Sparse Generalized Additive Models
• Distributed Simultaneous Inference in Generalized Linear Models via Confidence Distribution
• Confidence regions for entries of a large precision matrix
• Significance testing in non-sparse high-dimensional linear models
• Modern approaches for evaluating treatment effect heterogeneity from clinical trials and observational data
• The Asymptotic Distribution of the MLE in High-dimensional Logistic Models: Arbitrary Covariance
• Estimating the error variance in a high-dimensional linear model
• Geometric Inference for General High-Dimensional Linear Inverse Problems
• Recursive Sparse Point Process Regression with Application to Spectrotemporal Receptive Field Plasticity Analysis
• Testability of high-dimensional linear models with non-sparse structures
• An Overview of Healthcare Data Analytics With Applications to the COVID-19 Pandemic
• Uncertainty Quantification for Matrix Compressed Sensing and Quantum Tomography Problems
• Estimation of Large Covariance and Precision Matrices from Temporally Dependent Observations
• High-dimensional empirical likelihood inference
• Hierarchical inference for genome-wide association studies: a view on methodology with software
• Lagrangian Inference for Ranking Problems
• On the Post Selection Inference constant under Restricted Isometry Properties
• Asymptotic Confidence Regions for High-dimensional Structured Sparsity
• A statistical mechanics approach to de-biasing and uncertainty estimation in LASSO for random measurements
• Bayesian Sparse Linear Regression with Unknown Symmetric Error
• Estimating Treatment Effect under Additive Hazards Models with High-dimensional Covariates
• Uniformly Valid Confidence Sets Based on the Lasso
• Greedy algorithms for prediction
• High-Dimensional Estimation, Basis Assets, and the Adaptive Multi-Factor Model
• High-dimensional variable selection via low-dimensional adaptive learning
• Non-Asymptotic Guarantees for Reliable Identification of Granger Causality via the LASSO
• The costs and benefits of uniformly valid causal inference with high-dimensional nuisance parameters
• Discussion of Big Bayes Stories and BayesBag
• Compressed sensing radar detectors under the row-orthogonal design model: a statistical mechanics perspective
• High-Dimensional Confidence Regions in Sparse MRI
• High-dimensional semi-supervised learning: in search for optimal inference of the mean
• Higher-order least squares: assessing partial goodness of fit of linear causal models
• Proximal MCMC for Bayesian Inference of Constrained and Regularized Estimation
• Feature-specific inference for penalized regression using local false discovery rates
• Regression Discontinuity Design with Potentially Many Covariates
• Local Projection Inference in High Dimensions
• The EAS approach to variable selection for multivariate response data in high-dimensional settings
• Design-based theory for Lasso adjustment in randomized block experiments and rerandomized experiments
• ${\ell }_1$-penalized Multinomial Regression: Estimation, inference, and prediction, with an application to risk factor identification for different dementia subtypes
• Detection and inference of changes in high-dimensional linear regression with non-sparse structures
• Detangling robustness in high dimensions: composite versus model-averaged estimation
• Uncertainty Quantification for High Dimensional Sparse Nonparametric Additive Models
• Uniformly Valid Inference Based on the Lasso in Linear Mixed Models
• High-Dimensional Expected Shortfall Regression
• Estimator Augmentation with Applications in High-Dimensional Group Inference
• AutoGFI: Streamlined Generalized Fiducial Inference for Modern Inference Problems in Models with Additive Errors
• Non-asymptotic error controlled sparse high dimensional precision matrix estimation
• Residual permutation test for regression coefficient testing
• Scalable Data-Driven Basis Selection for Linear Machine Learning Interatomic Potentials
• Honest confidence sets for high-dimensional regression by projection and shrinkage
• Robust High-Dimensional Time-Varying Coefficient Estimation
• Sparsified Simultaneous Confidence Intervals for High-Dimensional Linear Models
• Replica Analysis for Ensemble Techniques in Variable Selection
• Group Spike and Slab Variational Bayes
• Inference for Large Panel Data with Many Covariates
• Understanding the population structure correction regression