Causal Discovery via Conditional Independence Testing with Proxy Variables (2023-05-09T00:00:00.000000Z)

TL;DR

This paper designs a proxy-based hypothesis test for identifying causal relationships when unobserved variables are present that has ideal power when large samples are available and demonstrates the effectiveness of the method using synthetic and real-world data.

Abstract

Distinguishing causal connections from correlations is important in many scenarios. However, the presence of unobserved variables, such as the latent confounder, can introduce bias in conditional independence testing commonly employed in constraint-based causal discovery for identifying causal relations. To address this issue, existing methods introduced proxy variables to adjust for the bias caused by unobserveness. However, these methods were either limited to categorical variables or relied on strong parametric assumptions for identification. In this paper, we propose a novel hypothesis-testing procedure that can effectively examine the existence of the causal relationship over continuous variables, without any parametric constraint. Our procedure is based on discretization, which under completeness conditions, is able to asymptotically establish a linear equation whose coefficient vector is identifiable under the causal null hypothesis. Based on this, we introduce our test statistic and demonstrate its asymptotic level and power. We validate the effectiveness of our procedure using both synthetic and real-world data.

Authors

Y. Qiao

16 papers

Mingzhou Liu

2 papers

Xinwei Sun

2 papers

TL;DR

Abstract

Authors

References62 items

Causal Discovery from Subsampled Time Series with Proxy Variables

Partial Identification of Causal Effects Using Proxy Variables

Testing unconditional and conditional independence via mutual information

Nonparametric conditional local independence testing

Optimal transport for causal discovery

Many Proxy Controls

Proximal mediation analysis

Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows

Wasserstein Conditional Independence Testing

Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction

Minimax Kernel Machine Learning for a Class of Doubly Robust Functionals

Identifying Effects of Multiple Treatments in the Presence of Unmeasured Confounding

An Introduction to Proximal Causal Learning

Minimax optimal conditional independence testing

CCMI : Classifier based Conditional Mutual Information Estimation

Review of Causal Discovery Methods Based on Graphical Models

Causality

Causal Inference and Mechanism Clustering of a Mixture of Additive Noise Models

Causal Inference via Kernel Deviance Measures

Cause-Effect Inference by Comparing Regression Errors

Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal Discovery

Prescription opioids are associated with higher mortality in patients diagnosed with sepsis: A retrospective cohort study using electronic health records

Conditional independence testing based on a nearest-neighbor estimator of conditional mutual information

Conditioning using conditional expectations: the Borel–Kolmogorov Paradox

Causal Discovery Using Proxy Variables

Approximate Kernel-Based Conditional Independence Tests for Fast Non-Parametric Causal Discovery

Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder.

MIMIC-III, a freely accessible critical care database

Kernel‐based tests for joint independence

Inference of Cause and Effect with Unsupervised Inverse Regression

A Randomized Trial of Loading Vancomycin in the Emergency Department

A Permutation-Based Kernel Conditional Independence Test

Probability in High Dimension

On the Decreasing Power of Kernel and Distance Based Nonparametric Hypothesis Tests in High Dimensions

Linear Algebra and Matrix Analysis for Statistics

Measurement bias and effect restoration in causal inference

Causal Mediation Analysis

Kernel-based Conditional Independence Test and Application in Causal Discovery

Testing conditional independence using maximal nonlinear conditional correlation

On the Identifiability of the Post-Nonlinear Causal Model

Nonlinear causal discovery with additive noise models

Causal Inference Using the Algorithmic Markov Condition

A Linear Non-Gaussian Acyclic Model for Causal Discovery

Distribution-Free Learning of Bayesian Network Structure in Continuous Domains

Effects of morphine analgesia in ventilated preterm neonates: primary outcomes from the NEOPAIN randomised trial

Causation, Prediction, and Search

Definition of sepsis

Opioids in pain management

Conditioning as disintegration

Supervised and Unsupervised Discretization of Continuous Features

Proximal Causal Learning of Heterogeneous Treatment Effects

Bivariate Causal Discovery via Conditional Divergence

Proximal Causal Inference with Hidden Mediators: Front-Door and Related Mediation Problems

Probability: theory and examples , volume 49

Statistical Inference

Sepsis

Con-founding: what it is and how to deal with it

Mathematical Statistics

Procalcitonin, C-reactive protein, white blood cells and SOFA score in ICU: diagnosis and monitoring of sepsis.

Vancomycin: a 50-year reassessment.

Probability with Martingales

Some integrals involving the QM function (Corresp.)

Field of Study

Venue Information

Name

Type

URL

Alternate Names