The restricted consistency property of leave-n_v-out cross-validation for high-dimensional variable selection

DOI10.5705/SS.202015.0394MaRDI QIDQ5226652zbMATH OpenOpenAlexFDO

Authors Yang Feng, Yi Yu

Publication date 1 August 2019

Published in STATISTICA SINICA (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1308.5390

zbMATH Keywords

variable selectiongeneralized linear modelsrestricted maximum likelihood estimatorsleave-\(n_v\)-out cross-validationrestricted model-selection consistency

Mathematics Subject Classification ID

Applications of statistics to biology and medical sciences; meta analysis (62P10) Statistical ranking and selection procedures (62F07) Generalized linear models (logistic models) (62J12)

Abstract: Cross-validation (CV) methods are popular for selecting the tuning parameter in the high-dimensional variable selection problem. We show the mis-alignment of the CV is one possible reason of its over-selection behavior. To fix this issue, we propose a version of leave-$n_v$-out cross-validation (CV($n_v$)), for selecting the optimal model among the restricted candidate model set for high-dimensional generalized linear models. By using the same candidate model sequence and a proper order of construction sample size $n_c$ in each CV split, CV($n_v$) avoids the potential hurdles in developing theoretical properties. CV($n_v$) is shown to enjoy the restricted model selection consistency property under mild conditions. Extensive simulations and real data analysis support the theoretical results and demonstrate the performances of CV($n_v$) in terms of both model selection and prediction.

Recommendations

• Linear Model Selection by Cross-Validation
• Leave-one-out cross-validation is risk consistent for Lasso
• Multiple predicting \(K\)-fold cross-validation for model selection
• Cross-validation with confidence
• Cross-validation for selecting a model selection procedure

Cited in

(11)

• Multiple predicting \(K\)-fold cross-validation for model selection
• High-dimensional variable selection via low-dimensional adaptive learning
• High-dimensional regression with potential prior information on variable importance
• Network Estimation by Mixing: Adaptivity and More
• A tuning-free robust and efficient approach to high-dimensional regression
• Cross-validation with confidence
• Targeted cross-validation
• Nested model averaging on solution path for high-dimensional linear regression
• A Note on Cross-Validation for Lasso Under Measurement Errors
• Asymptotic optimality and efficient computation of the leave-subject-out cross-validation
• Variance estimation based on blocked \(3\times 2\) cross-validation in high-dimensional linear regression

This page was built for publication: The restricted consistency property of leave-\(n_v\)-out cross-validation for high-dimensional variable selection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5226652)