Post selection shrinkage estimation for high-dimensional data analysis

DOI10.1002/ASMB.2193MaRDI QIDQ4620187zbMATHOpenAlexFDO

Authors Xiaoli Gao, Yang Feng, S. Ejaz Ahmed

Publication date 8 February 2019

Published in Applied Stochastic Models in Business and Industry (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1603.07277

zbMATH Keywords

Lassoridge regressionasymptotic risksparse modelpost selection(positive) shrinkage estimation

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Ridge regression; shrinkage estimators (Lasso) (62J07)

Abstract: In high-dimensional data settings where $pggn$, many penalized regularization approaches were studied for simultaneous variable selection and estimation. However, with the existence of covariates with weak effect, many existing variable selection methods, including Lasso and its generations, cannot distinguish covariates with weak and no contribution. Thus, prediction based on a subset model of selected covariates only can be inefficient. In this paper, we propose a post selection shrinkage estimation strategy to improve the prediction performance of a selected subset model. Such a post selection shrinkage estimator (PSE) is data-adaptive and constructed by shrinking a post selection weighted ridge estimator in the direction of a selected candidate subset. Under an asymptotic distributional quadratic risk criterion, its prediction performance is explored analytically. We show that the proposed post selection PSE performs better than the post selection weighted ridge estimator. More importantly, it improves the prediction performance of any candidate subset model selected from most existing Lasso-type variable selection methods significantly. The relative performance of the post selection PSE is demonstrated by both simulation studies and real data analysis.

Recommendations

• Rejoinder to ``Post-selection shrinkage estimation for high-dimensional data analysis
• Efficient adaptive estimation strategies in high-dimensional partially linear regression models
• Prediction weighted maximum frequency selection
• scientific article; zbMATH DE number 7108807
• High dimensional thresholded regression and shrinkage effect

Cited in

(15)

• Penalised, post‐pretest, and post‐shrinkage strategies in nonlinear growth models
• Likelihood adaptively modified penalties
• A bootstrap Lasso+partial ridge method to construct confidence intervals for parameters in high-dimensional sparse linear models
• A sufficient condition for the MSE dominance of the positive-part shrinkage estimator when each individual regression coefficient is estimated in a misspecified linear regression model
• Shrinkage Estimation Strategies in Generalised Ridge Regression Models: Low/High‐Dimension Regime
• High-dimensional causal mediation analysis based on partial linear structural equation models
• A weak‐signal‐assisted procedure for variable selection and statistical inference with an informative subsample
• Weak signals in high-dimensional regression: detection, estimation and prediction
• Rejoinder to ``Post-selection shrinkage estimation for high-dimensional data analysis
• Robust gene–environment interaction analysis using penalized trimmed regression
• Estimation of semiparametric regression model with right-censored high-dimensional data
• Shrinkage estimation in linear mixed models for longitudinal data
• Shrinkage estimation of semi-parametric spatial autoregressive panel data model with fixed effects
• A two-stage bridge estimator for regression models with endogeneity based on control function method
• Pretest and shrinkage estimation of the regression parameter vector of the marginal model with multinomial responses

This page was built for publication: Post selection shrinkage estimation for high-dimensional data analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4620187)