Skip to content
Preprint

GFCM: A Tail-Sensitive Mixed-Type Conditional Independence Test for Causal Discovery

Aug 2026 · 0 citations · 50 references
Mathematics

TL;DR

The Generalised Feature Covariance Measure is valid, sensitive beyond covariance, robust inside PC, and applicable to mixed-type data.

Abstract

Constraint-based causal discovery like PC and FCI depends on its conditional independence test. Partial correlation and the Generalised Covariance Measure (GCM) detect only the conditional covariance of residuals, so they miss dependence in the mean's nonlinear part, the scale, and the tails. Tests that detect more are biased inside PC, not scalable, only continuous, or not aimed at the tails. Our Generalised Feature Covariance Measure (GFCM) is valid, sensitive beyond covariance, robust inside PC, and applicable to mixed-type data. It runs the GCM template on a configurable set of residual features with conditional mean zero (centered moments and conditional quantile indicators), pooled in blocks and combined by the Cauchy rule, with a growing-knot spline nuisance at regression cost. We contribute (i) a centering result making the scale feature Neyman orthogonal, where the uncentered version is biased; (ii) the orientation asymmetry the mean-quantile construction creates inside PC, and its fix; (iii) a Phi-faithfulness theory under which PC with GFCM recovers the CPDAG of the set's detection class; and (iv) a benchmark of CI tests sensitive beyond covariance on synthetic data, semi-synthetic tail injections, and PC discovery on random DAGs. Under size-corrected power, GFCM recovers the scale and tail edges the covariance family misses and alone keeps power at the deep conditioning sets PC issues. It stays calibrated as n grows, whereas FFCI, the boosted GCM, and the partial copula test do not, and it handles mixed-type data directly. Inside PC at scale it attains the lowest skeleton SHD among tests that stay calibrated, while the others inflate false edges. Validity rests on an additive nuisance, and the tail advantage is shown on simulated and semi-synthetic data, as no fully real benchmark with both heavy tails and known structure exists.

View source

Similar papers

Preprint Aug 2026

A Multiscale Ball Test for Conditional Mean Independence

Tests of conditional mean independence can lose power when departures are confined to a bounded part of a multivariate predictor space and the relevant spatial scale is unknown. We propose a Multiscale Ball Conditional Mean Independence (MBCMI) test that aggregates support-weighted local mean contrasts in an outcome va...

S. Rudkin, W. Rudkin · 0 citations
Preprint Sep 2026

Functional Causal Discovery via Conditional Covariance Ordering

We study causal discovery where each node is a random function. Previous studies on this topic rely on structural assumptions, e.g., linearity or non-linearity, and distributional assumptions, e.g., Gaussianity or non-Gaussianity. In contrast, we make use of covariance operators to avoid these assumptions. Under functi...

Ke-Yu Li, Ruo-Xu Tan · 0 citations
Preprint Sep 2026

RKHS-Based Inference for Nonlinear Granger Causality via Conditional Centering

This work proposes a reproducing kernel Hilbert space (RKHS)-based test for nonlinear Granger non-causality in conditional mean for nonlinear autoregressive processes and establishes a weighted chi-square null limit and consistency against fixed alternatives for the population-centered statistic.

Yu-Han Tian, Adam Waterbury, Marie-Christine Düker · 0 citations
#natural language process... Preprint Aug 2026

When Is a General Factor Distinguishable? Non-Proportionality, Stable Structure, and the Bifactor Decision

Whether an added general dimension is necessary beyond correlated first-order factors is a property of population covariance, not an estimator. A bifactor structure is covariance-equivalent to correlated factors when general and group loadings are proportional within every cluster. When every cluster violates proportio...

Jinsong Chen · 0 citations
Open access Sep 2026

Generalized Cook’s Distance and DFFITs for the New Biased-Based Estimator in the Presence of Multicollinearity and Outliers

Regression analysis is a powerful tool for modeling relationships between variables, but its reliability hinges on meeting key assumptions of the classical linear regression model. When multicollinearity and outliers are simultaneously present, traditional estimation techniques such as Ordinary Least Squares (OLS) beco...

Olanrewaju O. Oladiran, T. Olatayo, A. Taiwo · 0 citations
Preprint Aug 2026

Joint Conditional Maximum Likelihood Estimation of Beta Regression for Panel Data with Higher-Order Autoregressive Errors

Existing panel beta regression estimators do not accommodate higher-order autoregressive dependence within a joint likelihood framework. We develop such an estimator: a joint conditional maximum-likelihood beta-AR(k) model extended from a single time series to panel data, and extend it to panel inference through two ne...

Ariel Linden · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.