Metraipolis › archive › dc_52ec0c35e4ab

The Limits of Experimental Design: Covariate Balance Beyond Low Dimension — arXiv:2608.18057

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18057
License (as archived)
CC0-1.0
Archived
2026-10-18T14:59:25.628Z
SHA-256 of the archived text
cd4eceb4348527c7238d2fe731092fe0e7aa357bc8f322fa27df8b686c1d4441
Stable URL of this page
https://metraipolis.com/documento/dc_52ec0c35e4ab

How to cite

The Limits of Experimental Design: Covariate Balance Beyond Low Dimension — arXiv:2608.18057 — arXiv (en), https://arxiv.org/abs/2608.18057 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_52ec0c35e4ab (Metraipolis archive dc_52ec0c35e4ab, sha256 cd4eceb4348527c7238d2fe731092fe0e7aa357bc8f322fa27df8b686c1d4441)
BibTeX
@misc{dc52ec0c35e4ab,
  title = {The Limits of Experimental Design: Covariate Balance Beyond Low Dimension — arXiv:2608.18057},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18057},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_52ec0c35e4ab; sha256 cd4eceb4348527c7238d2fe731092fe0e7aa357bc8f322fa27df8b686c1d4441},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18057. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study how fast experimental designs can approach the semiparametric efficiency bound in finite samples, as measured by the excess variance of unadjusted treatment effect estimation. We prove an impossibility theorem: under weak conditions, no design can approach the variance bound uniformly over smooth outcome models unless covariate dimension $d \ll \log n$. Even in experiments with thousands of units, this permits only a handful of covariates. Motivated by this, we propose new designs based on discrepancy minimization that instead attempt to control imbalances over restricted-complexity nonparametric function classes. Such designs achieve fast rates to their corresponding restricted efficiency targets, permitting $d \ll n$ covariates in an additive nonparametric specification. They can also be combined with matching to protect against unmodeled outcome variation. In simulations calibrated to 12 published experiments, our designs reduce variance relative to matched pairs randomization in every empirical setting.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-19 in math.ST).
Categorie arXiv: Econometrics (econ.EM) ; Statistics Theory (math.ST); Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2608.18057 — 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 2026-10-18T14:58:56.468Z dalla pagina https://arxiv.org/catchup/math.ST/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).