EconBase
← All papers

Where to Experiment? Site Selection Under Distribution Shift via Optimal Transport and Wasserstein DRO

Adam Bouyamourn

arXiv 6 Nov 2025 · Statistics — Methodology

arXiv:2511.04658 · PDF · DOI · OpenAlex · Extracted main text

Abstract

How should researchers select experimental sites when the deployment population differs from observed data? I formulate the problem of experimental site selection as an optimal transport problem, developing methods to minimize downstream estimation error by choosing sites that minimize the Wasserstein distance between population and sample covariate distributions. I develop new theoretical upper bounds on PATE and CATE estimation errors, and show that these different objectives lead to different site selection strategies. I extend this approach by using Wasserstein Distributionally Robust Optimization to develop a site selection procedure robust to adversarial perturbations of covariate information: a specific model of distribution shift. I also propose a novel data-driven procedure for selecting the uncertainty radius the Wasserstein DRO problem, which allows the user to benchmark robustness levels against observed variation in their data. Simulation evidence, and a reanalysis of a randomized microcredit experiment in Morocco (Crépon et al.), show that these methods outperform random and stratified sampling of sites when covariates have prognostic R-squared > .5, and alternative optimization methods i) for moderate-to-large size problem instances ii) when covariates are moderately informative about treatment effects, and iii) under induced distribution shift.

Citation extraction

129
references
175
in-text mentions
130
distinct cited
1
self-citations
14,388
main-text words

appendix boundary found by appendix_command · 65% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Naoki Egami and Diana Da In Lee (2024) Designing multi-site studies for external validity: Site selection via synthetic purposive sampling, 20240.9285380%
2Clara Bicalho, Adam Bouyamourn, and Thad Dunning (2022) Conditional balance tests: Increasing sensitivity and specificity with prognostic covariates, 2022 self0.84333100%
3Elizabeth Tipton (2013) Improving generalizations from experiments using propensity score subclassification: Assumptions, properties, and contexts0.73732100%
4T Dunning, G Grossman, M Humphreys, S D Hyde, C McIntosh, and G Nell… (2019) Information, Accountability, and Cumulative Learning: Lessons from Metaketa I0.6443267%
5Jacques E Rossouw, Garnet L Anderson, Ross L Prentice, Andrea Z LaCr… (2002) Risks and benefits of estrogen plus progestin in healthy postmenopausal women: Principal results from the women's health initiat…0.6443267%
6Jose Blanchet and Karthyek Murthy (2018) Quantifying distributional model risk via optimal transport0.64422100%
7Jennifer L. Hill (2010) Bayesian nonparametric modeling for causal inference0.64422100%
8Frank H. Knight (1921) Risk, Uncertainty and Profit0.64422100%
9Cass R. Sunstein (2023) Knightian uncertainty0.64422100%
10Marco Cuturi (2013) Sinkhorn distances: Lightspeed computation of optimal transportation distances, 20130.64422100%

Showing the top 10 of 130 scored citations.