High-dimensional empirical likelihood inference

DOI10.1093/BIOMET/ASAA051zbMATH Open1462.62760arXiv1805.10742OpenAlexW2984280748MaRDI QIDQ5857982FDOQ5857982

Authors: Jinyuan Chang, Cheng Yong Tang, Tong Tong Wu, Song Xi Chen 

Publication date: 8 April 2021

Published in: Biometrika (Search for Journal in Brave)

Abstract: High-dimensional statistical inference with general estimating equations are challenging and remain less explored. In this paper, we study two problems in the area: confidence set estimation for multiple components of the model parameters, and model specifications test. For the first one, we propose to construct a new set of estimating equations such that the impact from estimating the high-dimensional nuisance parameters becomes asymptotically negligible. The new construction enables us to estimate a valid confidence region by empirical likelihood ratio. For the second one, we propose a test statistic as the maximum of the marginal empirical likelihood ratios to quantify data evidence against the model specification. Our theory establishes the validity of the proposed empirical likelihood approaches, accommodating over-identification and exponentially growing data dimensionality. The numerical studies demonstrate promising performance and potential practical benefits of the new methods.

Full work available at URL: https://arxiv.org/abs/1805.10742

Recommendations

• Empirical likelihood for higher dimensional linear models
• Empirical likelihood for high-dimensional linear regression models
• A unified theory of confidence regions and testing for high-dimensional estimating equations
• Two-sample high-dimensional empirical likelihood
• Large dimensional empirical likelihood

zbMATH Keywords

empirical likelihoodnuisance parameterhigh-dimensional statistical inferenceover-identificationgeneral estimating equation

Mathematics Subject Classification ID

Statistical aspects of big data and data science (62R07) Estimation in multivariate analysis (62H12)

Cited In (24)

• Simultaneous selection and incorporation of consistent external aggregate information
• A unified theory of confidence regions and testing for high-dimensional estimating equations
• Markov Neighborhood Regression for High-Dimensional Inference
• High dimensional exponential family estimation via empirical Bayes
• High-dimensional inference using the extremal skew-\(t\) process
• Projection-based Inference for High-dimensional Linear Models
• Statistical Inference for High-Dimensional Models via Recursive Online-Score Estimation
• Penalized Jackknife Empirical Likelihood in High Dimensions
• Modified Likelihood root in High Dimensions
• Testing the martingale difference hypothesis in high dimension
• Statistical inference in massive datasets by empirical likelihood
• Asymptotic inference for high-dimensional data
• Culling the Herd of Moments with Penalized Empirical Likelihood
• Regularized parameter estimation of high dimensional distribution
• Inference in High-Dimensional Multivariate Response Regression with Hidden Variables
• Empirical likelihood ratio tests for non-nested model selection based on predictive losses
• In defense of the indefensible: a very naïve approach to high-dimensional inference
• High dimensional generalized empirical likelihood for moment restrictions with dependent data
• Effects of data dimension on empirical likelihood
• A likelihood ratio framework for high-dimensional semiparametric regression
• Wilks' theorem for semiparametric regressions with weakly dependent data
• Jackknife empirical likelihood: small bandwidth, sparse network and high-dimensional asymptotics
• A review of recent advances in empirical likelihood
• Penalized empirical likelihood for high-dimensional generalized linear models with longitudinal data

This page was built for publication: High-dimensional empirical likelihood inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5857982)