Variance estimation using refitted cross-validation in ultrahigh dimensional regression
From MaRDI portal
Abstract: Variance estimation is a fundamental problem in statistical modeling. In ultrahigh dimensional linear regressions where the dimensionality is much larger than sample size, traditional variance estimation techniques are not applicable. Recent advances on variable selection in ultrahigh dimensional linear regressions make this problem accessible. One of the major problems in ultrahigh dimensional regression is the high spurious correlation between the unobserved realized noise and some of the predictors. As a result, the realized noises are actually predicted when extra irrelevant variables are selected, leading to serious underestimate of the noise level. In this paper, we propose a two-stage refitted procedure via a data splitting technique, called refitted cross-validation (RCV), to attenuate the influence of irrelevant variables with high spurious correlations. Our asymptotic results show that the resulting procedure performs as well as the oracle estimator, which knows in advance the mean regression function. The simulation studies lend further support to our theoretical claims. The naive two-stage estimator which fits the selected variables in the first stage and the plug-in one stage estimators using LASSO and SCAD are also studied and compared. Their performances can be improved by the proposed RCV method.
Recommendations
- Variance estimation based on blocked 3 2 cross-validation in high-dimensional linear regression
- Error variance estimation in ultrahigh-dimensional additive models
- Test for high-dimensional regression coefficients using refitted cross-validation variance estimation
- scientific article; zbMATH DE number 1471718
- Variance estimation in high-dimensional linear models
Cited in
(only showing first 100 items - show all)- Variance estimation for semiparametric regression models by local averaging
- Test for high-dimensional regression coefficients using refitted cross-validation variance estimation
- Are discoveries spurious? Distributions of maximum spurious correlations and their applications
- Distributed testing and estimation under sparse high dimensional models
- Asymptotically optimal differenced estimators of error variance in nonparametric regression
- Extended differential geometric LARS for high-dimensional GLMs with general dispersion parameter
- Adaptive estimation of high-dimensional signal-to-noise ratios
- Greedy variance estimation for the LASSO
- Inference without compatibility: using exponential weighting for inference on a parameter of a linear model
- In defense of the indefensible: a very naïve approach to high-dimensional inference
- Reproducible learning in large-scale graphical models
- Two-sample testing of high-dimensional linear regression coefficients via complementary sketching
- Sparse spatio-temporal autoregressions by profiling and bagging
- Improved estimators for semi-supervised high-dimensional regression model
- RCV-based error density estimation in the ultrahigh dimensional additive model
- Robust error density estimation in ultrahigh dimensional sparse linear model
- Feature selection for generalized varying coefficient mixed-effect models with application to obesity GWAS
- Testing regression coefficients in high-dimensional and sparse settings
- Testing for high-dimensional network parameters in auto-regressive models
- Ultrahigh dimensional precision matrix estimation via refitted cross validation
- Error density estimation in high-dimensional sparse linear model
- Linear hypothesis testing for high dimensional generalized linear models
- Tests for high-dimensional single-index models
- Most powerful test against a sequence of high dimensional local alternatives
- The use of vector bootstrapping to improve variable selection precision in Lasso models
- RANK: Large-Scale Inference With Graphical Nonlinear Knockoffs
- Debiased Inference on Treatment Effect in a High-Dimensional Model
- Model selection criteria for a linear model to solve discrete ill-posed problems on the basis of singular decomposition and random projection
- Error variance estimation in ultrahigh-dimensional additive models
- Penalized weighted composite quantile regression in the linear regression model with heavy-tailed autocorrelated errors
- A study on tuning parameter selection for the high-dimensional lasso
- Nonsparse learning with latent variables
- Learning a high-dimensional linear structural equation model via _1-regularized regression
- Partitioned Approach for High-dimensional Confidence Intervals with Large Split Sizes
- Testing the Linear Mean and Constant Variance Conditions in Sufficient Dimension Reduction
- Regularized projection score estimation of treatment effects in high-dimensional quantile regression
- Variance-estimation-free test of significant covariates in high-dimensional regression
- L0-Regularized Learning for High-Dimensional Additive Hazards Regression
- Model Selection With Lasso-Zero: Adding Straw to the Haystack to Better Find Needles
- Quantification of model bias underlying the phenomenon of Einstein from Noise
- Test for high dimensional regression coefficients of partially linear models
- Variance estimation for sparse ultra-high dimensional varying coefficient models
- Conditional Test for Ultrahigh Dimensional Linear Regression Coefficients
- A new nonparametric test for high-dimensional regression coefficients
- A tuning-free robust and efficient approach to high-dimensional regression
- Variance estimation of a general u-statistic with appllication to cross-validation
- Robust \(U\)-type test for high dimensional regression coefficients using refitted cross-validation variance estimation
- Block-regularized \(m\times 2\) cross-validated estimator of the generalization error
- Variance estimation based on blocked 3 2 cross-validation in high-dimensional linear regression
- Markov Neighborhood Regression for High-Dimensional Inference
- New Tests for High-Dimensional Linear Regression Based on Random Projection
- Statistical Inference for High-Dimensional Models via Recursive Online-Score Estimation
- Variance estimation in high-dimensional linear regression via adaptive elastic-net
- A new approach for ultrahigh-dimensional covariance matrix estimation
- A Critical Review of LASSO and Its Derivatives for Variable Selection Under Dependence Among Covariates
- Threshold Selection in Feature Screening for Error Rate Control
- Feature Screening with Latent Responses
- Moderate-Dimensional Inferences on Quadratic Functionals in Ordinary Least Squares
- Integrative Factor Regression and Its Inference for Multimodal Data Analysis
- Densely connected sub-Gaussian linear structural equation model learning via \(\ell_1\)- and \(\ell_2\)-regularized regressions
- Robust variable selection and estimation via adaptive elastic net S-estimators for linear regression
- A generalized knockoff procedure for FDR control in structural change detection
- A post-screening diagnostic study for ultrahigh dimensional data
- Reprint: Hypothesis testing on high dimensional quantile regression
- Hypothesis testing on high dimensional quantile regression
- Cross-Fitted Residual Regression for High-Dimensional Heteroscedasticity Pursuit
- Neighborhood-based cross fitting approach to treatment effects with high-dimensional data
- Estimations and Tests for Generalized Mediation Models with High-Dimensional Potential Mediators
- A simple method to improve principal components regression
- Sparse covariance matrix estimation for ultrahigh dimensional data
- Quantile generalized measures of correlation
- Asymptotic bias of the _2-regularized error variance estimator
- A new approach for ultrahigh dimensional precision matrix estimation
- Noise covariance estimation in multi-task high-dimensional linear models
- A Random Projection Approach to Hypothesis Tests in High-Dimensional Single-Index Models
- Are Latent Factor Regression and Sparse Regression Adequate?
- Ultrahigh dimensional single index model estimation via refitted cross-validation
- Activation discovery with FDR control: application to fMRI data
- A zero-estimator approach for estimating the signal level in a high-dimensional model-free setting
- Nonparametric Quantile Regression Estimation With Mixed Discrete and Continuous Data
- Using History Matching for Prior Choice
- Robust semiparametric gene-environment interaction analysis using sparse boosting
- Semi-supervised inference for the high-dimensional quantile regression
- Inference in models with omitted covariates: Cramér-type moderate deviations and applications to high-dimensional regression
- Distributed learning for high-dimensional factor augmented regression models
- Robust weighted transfer learning with linear constraints under linear regressive model
- High-Dimensional Expected Shortfall Regression
- Higher Order Accurate Symmetric Bootstrap Confidence Intervals in High Dimensional Penalized Regression
- Statistical inference for matrix-vector linear regression without debiasing under Kronecker covariance structure
- Fiducial selector: fast and efficient inference for high-dimensional regression
- Conditional dependence learning with high-dimensional conditioning variables
- Semiparametric inference based on adaptively collected data
- Cox reduction and confidence sets of models: a theoretical elucidation
- High dimensional regression with many nuisance parameters: both cases of specified and unspecified parameters of interest
- Bayesian L 1/2 Regression
- Test and Measure for Partial Mean Dependence Based on Machine Learning Methods
- Tests for high-dimensional partially linear regression models
- Inference for possibly misspecified generalized linear models with nonpolynomial-dimensional nuisance parameters
- Feature screening and error variance estimation for ultrahigh-dimensional linear model with measurement errors
- A Goodness-of-Fit Assessment for General Learning Procedures in High Dimensions
This page was built for publication: Variance estimation using refitted cross-validation in ultrahigh dimensional regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4632664)
