Metraipolis › archive › dc_9034cd492207

Robustness of Median-based Splitting Rules for Causal Trees — arXiv:2611.00348

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00348
License (as archived)
CC0-1.0
Archived
2026-11-03T11:53:25.783Z
SHA-256 of the archived text
61ef99016fd7e0be5f0c7d9c875b872b9e4ccaae9793aa716ac1aaa9b3b69888
Stable URL of this page
https://metraipolis.com/documento/dc_9034cd492207

How to cite

Robustness of Median-based Splitting Rules for Causal Trees — arXiv:2611.00348 — arXiv (en), https://arxiv.org/abs/2611.00348 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9034cd492207 (Metraipolis archive dc_9034cd492207, sha256 61ef99016fd7e0be5f0c7d9c875b872b9e4ccaae9793aa716ac1aaa9b3b69888)
BibTeX
@misc{dc9034cd492207,
  title = {Robustness of Median-based Splitting Rules for Causal Trees — arXiv:2611.00348},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00348},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9034cd492207; sha256 61ef99016fd7e0be5f0c7d9c875b872b9e4ccaae9793aa716ac1aaa9b3b69888},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00348. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Causal forests (Athey and Imbens, 2016) are a widely used method for the estimation of heterogeneous treatment effects. Standard implementations use mean-based splitting criteria, which perform well when the outcome distribution is well-behaved and free of contamination, such as outliers or heavy tails. However, real-world data are rarely clean. Outcome perturbations can affect the tree structure selected by mean-based splitting rules and lead to unreliable treatment effect estimates. In this study, we systematically examine the robustness of causal forests to irregularities in the outcome distribution. Building on the median-based splitting criteria introduced by Maßmann and Gliszczyńska-Schroeder (2026), we empirically investigate three median-based splitting criteria: Median Absolute Deviation (MAD), Least Median of Squares (LMS), and Median Squared Deviation (MSD). We conduct Monte Carlo experiments and apply the methods to empirical benchmark datasets from the causal inference literature to compare the performance of the median-based approaches with standard causal forests. We additionally examine pointwise confidence interval coverage using the Bootstrap of Little Bags and the infinitesimal jackknife. The results indicate that median-based splitting criteria can reduce sensitivity to outcome irregularities in specific scenarios, particularly in the presence of extreme heavy-tailed noise and nonlinear treatment effect heterogeneity. However, these benefits are scenario-dependent and do not consistently lead to more accurate conditional average treatment effect (CATE) estimates.

Tema degli esploratori: economia dei servizi IA (elenco arXiv econ.EM, nuovi lavori del giorno).
Categorie arXiv: Econometrics (econ.EM).
Pagina del lavoro: https://arxiv.org/abs/2611.00348 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T11:14:52.657Z dalla pagina https://arxiv.org/list/econ.EM/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).