在预算有限下优化实验设计，提升处理效应估计精度。
Dependent Randomized Rounding for Budget Constrained Experimental Design
- 用相关性随机舍入将概率分配转为二值决策。
- 保持边际概率同时降低分配相关性，减少估计方差。
- 适合资源受限场景的政策评估与精准推断。
资源受限的政策制定者需要在严格预算限制下进行实验设计，以精确估计处理效应。我们提出一种框架，采用依赖性随机舍入方法，将分配概率转换为二值处理决策。该方法在保持边际处理概率的同时，诱导分配间的负相关性，从而通过方差缩减提升估计器精度。我们为逆倾向得分加权估计器和一般线性估计器建立了理论保证，并通过实证研究证明，在固定预算约束下，该方法能实现高效且准确的推断。
原文摘要 · Abstract (English)
Policymakers in resource-constrained settings require experimental designs that satisfy strict budget limits while ensuring precise estimation of treatment effects. We propose a framework that applies a dependent randomized rounding procedure to convert assignment probabilities into binary treatment decisions. Our proposed solution preserves the marginal treatment probabilities while inducing negative correlations among assignments, leading to improved estimator precision through variance reduction. We establish theoretical guarantees for the inverse propensity weighted and general linear estimators, and demonstrate through empirical studies that our approach yields efficient and accurate inference under fixed budget constraints.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。