Power-Boosted Granger-Causal Discovery for Large Heterogeneous Panel Data

Yiheng Gu, Xiufan Yu
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:37326-37359, 2026.

Abstract

This paper proposes a power-enhanced panel Granger causality test (PE-PGCT) for assessing the Granger non-causality in heterogeneous and potentially high-dimensional panel data. Building on any existing panel Granger non-causality test, we show, both theoretically and empirically, that the proposed PE-PGCT boosts its power substantially. The power gains are particularly significant in situations of high-dimensional panels when the cross-sectional dimension exceeds the time dimension, as well as under sparse alternatives when the signals are sparsely distributed across panel units. We establish rigorous theoretical guarantees on the asymptotic behavior of the proposed power enhancement component, demonstrating attractive power enhancement properties that it induces negligible size distortion under the null hypothesis while delivering significant power gain under the alternatives. The empirical performances are illustrated via extensive simulation studies, as well as a real-world application.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-gu26p, title = {Power-Boosted {G}ranger-Causal Discovery for Large Heterogeneous Panel Data}, author = {Gu, Yiheng and Yu, Xiufan}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {37326--37359}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/gu26p/gu26p.pdf}, url = {https://proceedings.mlr.press/v306/gu26p.html}, abstract = {This paper proposes a power-enhanced panel Granger causality test (PE-PGCT) for assessing the Granger non-causality in heterogeneous and potentially high-dimensional panel data. Building on any existing panel Granger non-causality test, we show, both theoretically and empirically, that the proposed PE-PGCT boosts its power substantially. The power gains are particularly significant in situations of high-dimensional panels when the cross-sectional dimension exceeds the time dimension, as well as under sparse alternatives when the signals are sparsely distributed across panel units. We establish rigorous theoretical guarantees on the asymptotic behavior of the proposed power enhancement component, demonstrating attractive power enhancement properties that it induces negligible size distortion under the null hypothesis while delivering significant power gain under the alternatives. The empirical performances are illustrated via extensive simulation studies, as well as a real-world application.} }
Endnote
%0 Conference Paper %T Power-Boosted Granger-Causal Discovery for Large Heterogeneous Panel Data %A Yiheng Gu %A Xiufan Yu %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-gu26p %I PMLR %P 37326--37359 %U https://proceedings.mlr.press/v306/gu26p.html %V 306 %X This paper proposes a power-enhanced panel Granger causality test (PE-PGCT) for assessing the Granger non-causality in heterogeneous and potentially high-dimensional panel data. Building on any existing panel Granger non-causality test, we show, both theoretically and empirically, that the proposed PE-PGCT boosts its power substantially. The power gains are particularly significant in situations of high-dimensional panels when the cross-sectional dimension exceeds the time dimension, as well as under sparse alternatives when the signals are sparsely distributed across panel units. We establish rigorous theoretical guarantees on the asymptotic behavior of the proposed power enhancement component, demonstrating attractive power enhancement properties that it induces negligible size distortion under the null hypothesis while delivering significant power gain under the alternatives. The empirical performances are illustrated via extensive simulation studies, as well as a real-world application.
APA
Gu, Y. & Yu, X.. (2026). Power-Boosted Granger-Causal Discovery for Large Heterogeneous Panel Data. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:37326-37359 Available from https://proceedings.mlr.press/v306/gu26p.html.

Related Material