Robust inference with knockoffs

DOI10.1214/19-AOS1852zbMATH Open1452.62193arXiv1801.03896OpenAlexW3043129934MaRDI QIDQ2196226FDOQ2196226

Authors: Rina Foygel Barber, Emmanuel J. Candès, Richard Samworth 

Publication date: 28 August 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Abstract: We consider the variable selection problem, which seeks to identify important variables influencing a response $Y$ out of many candidate features $X_1,ldots,X_p$. We wish to do so while offering finite-sample guarantees about the fraction of false positives - selected variables $X_j$ that in fact have no effect on $Y$ after the other features are known. When the number of features $p$ is large (perhaps even larger than the sample size $n$), and we have no prior knowledge regarding the type of dependence between $Y$ and $X$, the model-X knockoffs framework nonetheless allows us to select a model with a guaranteed bound on the false discovery rate, as long as the distribution of the feature vector $X=(X_1,dots,X_p)$ is exactly known. This model selection procedure operates by constructing "knockoff copies'" of each of the $p$ features, which are then used as a control group to ensure that the model selection algorithm is not choosing too many irrelevant features. In this work, we study the practical setting where the distribution of $X$ could only be estimated, rather than known exactly, and the knockoff copies of the $X_j$'s are therefore constructed somewhat incorrectly. Our results, which are free of any modeling assumption whatsoever, show that the resulting model selection procedure incurs an inflation of the false discovery rate that is proportional to our errors in estimating the distribution of each feature $X_j$ conditional on the remaining features $X_k:keqj$. The model-X knockoff framework is therefore robust to errors in the underlying assumptions on the distribution of $X$, making it an effective method for many practical applications, such as genome-wide association studies, where the underlying distribution on the features $X_1,dots,X_p$ is estimated accurately but not known exactly.

Full work available at URL: https://arxiv.org/abs/1801.03896

Recommendations

• Relaxing the assumptions of knockoffs by conditioning
• Panning for Gold: ‘Model-X’ Knockoffs for High Dimensional Controlled Variable Selection
• Controlling the false discovery rate via knockoffs
• Derandomizing Knockoffs
• Powerful knockoffs via minimizing reconstructability
• A pseudo knockoff filter for correlated features
• Adjusting the Benjamini–Hochberg method for controlling the false discovery rate in knockoff-assisted variable selection
• Metropolized Knockoff Sampling
• Gene hunting with hidden Markov model knockoffs
• A high-dimensional power analysis of the conditional randomization test and knockoffs

zbMATH Keywords

variable selectionfalse discovery ratehigh-dimensional regressionrobustnessknockoffs

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Nonparametric hypothesis testing (62G10) Nonparametric robustness (62G35) Robustness and adaptive procedures (parametric inference) (62F35)

Cites Work

• Title not available (Why is that?)
• Sparse inverse covariance estimation with the graphical lasso
• The control of the false discovery rate in multiple testing under dependency.
• A knockoff filter for high-dimensional selective inference
• Model selection and estimation in the Gaussian graphical model
• Strong Control, Conservative Point Estimation and Simultaneous Conservative Consistency of False Discovery Rates: A Unified Approach
• High-dimensional covariance estimation by minimizing \(\ell _{1}\)-penalized log-determinant divergence
• RANK: Large-Scale Inference With Graphical Nonlinear Knockoffs
• On the Benjamini-Hochberg method
• Panning for Gold: ‘Model-X’ Knockoffs for High Dimensional Controlled Variable Selection
• Gene hunting with hidden Markov model knockoffs
• Controlling the false discovery rate via knockoffs
• A dynamic programming algorithm for haplotype block partitioning

Cited In (42)

• Identifying important predictors in large data bases -- multiple testing and model selection
• Robust AIC with high breakdown scale estimate
• False Discovery Rate Control via Data Splitting
• A Scale-Free Approach for False Discovery Rate Control in Generalized Linear Models
• Local false discovery rate estimation with competition-based procedures for variable selection
• Relaxing the assumptions of knockoffs by conditioning
• Controlling the false discovery rate by a latent Gaussian copula knockoff procedure
• Sequential knockoffs for continuous and categorical predictors: with application to a large psoriatic arthritis clinical trial pool
• FANOK: knockoffs in linear time
• Familywise error rate control via knockoffs
• A generalized knockoff procedure for FDR control in structural change detection
• Adaptive novelty detection with false discovery rate guarantee
• Powerful knockoffs via minimizing reconstructability
• Deep knockoffs
• IPAD: stable interpretable forecasting with knockoffs inference
• A knockoff filter for high-dimensional selective inference
• FDR control and power analysis for high-dimensional logistic regression via Stabkoff
• On the power of conditional independence testing under model-X
• A pseudo knockoff filter for correlated features
• Null-free false discovery rate control using decoy permutations
• Multilayer knockoff filter: controlled variable selection at multiple resolutions
• False discovery rate-controlled multiple testing for union null hypotheses: a knockoff-based approach
• Support recovery of Gaussian graphical model with false discovery rate control
• Reconciling model-X and doubly robust approaches to conditional independence testing
• Feature screening and FDR control with knockoff features for ultrahigh-dimensional right-censored data
• A recipe for robust estimation using pseudo data
• Overview of research advance for knockoff methods
• Controlling False Discovery Rate Using Gaussian Mirrors
• Generating knockoffs via conditional independence
• A prototype knockoff filter for group selection with FDR control
• Stab-GKnock: controlled variable selection for partially linear models using generalized knockoffs
• Reproducible feature selection in high-dimensional accelerated failure time models
• Kernel Knockoffs Selection for Nonparametric Additive Models
• Gene hunting with hidden Markov model knockoffs
• Threshold Selection in Feature Screening for Error Rate Control
• False Discovery Rate Control Under General Dependence By Symmetrized Data Aggregation
• Reproducible learning in large-scale graphical models
• Deep latent variable models for generating knockoffs
• CoxKnockoff: controlled feature selection for the Cox model using knockoffs
• Statistical inference for structured high-dimensional models. Abstracts from the workshop held March 11--17, 2018
• Controlling the false discovery rate via knockoffs
• New perspectives on knockoffs construction

Uses Software

• glasso

This page was built for publication: Robust inference with knockoffs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2196226)