Learning to increase the power of conditional randomization tests

DOI10.1007/S10994-023-06302-3MaRDI QIDQ6134320zbMATH OpenOpenAlexFDO

Authors Shalev Shaer, Yaniv Romano

Publication date 22 August 2023

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2207.01022

zbMATH Keywords

false discovery rateconditional independence testingconditional randomization testmodel-X knockoffscontrolled feature selection

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Abstract: The model-X conditional randomization test is a generic framework for conditional independence testing, unlocking new possibilities to discover features that are conditionally associated with a response of interest while controlling type-I error rates. An appealing advantage of this test is that it can work with any machine learning model to design powerful test statistics. In turn, the common practice in the model-X literature is to form a test statistic using machine learning models, trained to maximize predictive accuracy with the hope to attain a test with good power. However, the ideal goal here is to drive the model (during training) to maximize the power of the test, not merely the predictive accuracy. In this paper, we bridge this gap by introducing, for the first time, novel model-fitting schemes that are designed to explicitly improve the power of model-X tests. This is done by introducing a new cost function that aims at maximizing the test statistic used to measure violations of conditional independence. Using synthetic and real data sets, we demonstrate that the combination of our proposed loss function with various base predictive models (lasso, elastic net, and deep neural networks) consistently increases the number of correct discoveries obtained, while maintaining type-I error rates under control.

Recommendations

• How to gain on power: novel conditional independence tests based on short expansion of conditional mutual information
• Hypothesis testing in adaptively sampled data: ART to maximize power beyond \textit{iid }sampling
• The conditional permutation test for independence while controlling for confounders
• Testing conditional independence via integrating-up transform
• The Hardness of Conditional Independence Testing and the Generalised Covariance Measure

Cites work

• scientific article; zbMATH DE number 6378127 (Why is no real title available?)
• scientific article; zbMATH DE number 720689 (Why is no real title available?)
• scientific article; zbMATH DE number 7370644 (Why is no real title available?)
• Causal inference by using invariant prediction: identification and confidence intervals. With discussion and authors' reply
• Causal inference in genetic trio studies
• Controlling the false discovery rate via knockoffs
• Deep knockoffs
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• Fast and powerful conditional randomization testing via distillation
• Gene hunting with hidden Markov model knockoffs
• On the power of conditional independence testing under model-X
• Panning for Gold: ‘Model-X’ Knockoffs for High Dimensional Controlled Variable Selection
• Regularization and Variable Selection Via the Elastic Net
• The Hardness of Conditional Independence Testing and the Generalised Covariance Measure
• The Holdout Randomization Test for Feature Selection in Black Box Models
• The control of the false discovery rate in multiple testing under dependency.
• Variable selection for sparse Dirichlet-multinomial regression with an application to microbiome data analysis

Cited in

(1)

• Hypothesis testing in adaptively sampled data: ART to maximize power beyond \textit{iid }sampling

This page was built for publication: Learning to increase the power of conditional randomization tests

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6134320)