Nonparametric Conditional Local Independence Testing

Abstract

Conditional local independence is an asymmetric independence relation among continuous time stochastic processes. It describes whether the evolution of one process is directly influenced by another process given the histories of additional processes, and it is important for the description and learning of causal relations among processes. We develop a model-free framework for testing the hypothesis that a counting process is conditionally locally independent of another process. To this end, we introduce a new functional parameter called the Local Covariance Measure (LCM), which quantifies deviations from the hypothesis. Following the principles of double machine learning, we propose an estimator of the LCM and a test of the hypothesis using nonparametric estimators and sample splitting or cross-fitting. We call this test the (cross-fitted) Local Covariance Test ((X)-LCT), and we show that its level and power can be controlled uniformly, provided that the nonparametric estimators are consistent with modest rates. We illustrate the theory by an example based on a marginalized Cox model with time-dependent covariates, and we show in simulations that when double machine learning is used in combination with cross-fitting, then the test works well without restrictive parametric assumptions.

arXiv comment62 pages, 10 figures. Comments are welcome

References in corpus (11)

• The Hardness of Conditional Independence Testing and the Generalised Covariance Measure
• Graphical models for marked point processes based on local independence
• Learning Granger Causality for Hawkes Processes
• Uncovering Causality from Multivariate Hawkes Integrated Cumulants
• Statistical modeling of causal effects in continuous time
• Markov equivalence of marginalized local independence graphs
• Conditional Independence Testing in Hilbert Spaces with Applications to Functional Data Analysis
• Testing Conditional Independence via Quantile Regression Based Partial Copulas
• Graphical modeling of stochastic processes driven by correlated errors
• The Projected Covariance Measure for assumption-lean variable significance testing
• Graphical criteria for the identification of marginal causal effects in continuous-time survival and event-history analyses

Cited by in corpus (1)

• Algorithm-agnostic significance testing in supervised learning with multimodal data