What question did this study set out to answer?

The goal is to propose a nonparametric test for Granger causality in distributions using entropic optimal transport methods.

Testing Distributional Granger Causality With Entropic Optimal Transport

View Full Paper

Ask AI

Bookmark

Authors

This method tests for causal relationships in data, indicating new patterns in financial volatility forecasting.

The goal is to propose a nonparametric test for Granger causality in distributions using entropic optimal transport methods.
Develop nonparametric test for Granger causality using entropic optimal transport
Construct test statistic based on Wasserstein distances between kernel-smoothed distributions
Establish theoretical underpinnings including uniform consistency and central limit theorem
Propose stationary bootstrap for valid inference while preserving temporal dependence
Test achieves minimax optimal detection boundary over Hölder classes
Demonstrated reliable size control and high power in simulations
Empirical application uncovers causal patterns in financial volatility not detected by classical tests

Tao Wang (2026) studied this question.

View Full Paper

Ask AI

Bookmark