arXiv 26 Sep 2023 · Statistics — Methodology · publishedJournal of Causal Inference (2024)
arXiv:2309.15297 · PDF · DOI · OpenAlex · Extracted main text
We consider an experiment with at least two stages or batches and $O(N)$ subjects per batch. First, we propose a semiparametric treatment effect estimator that efficiently pools information across the batches, and show it asymptotically dominates alternatives that aggregate single batch estimates. Then, we consider the design problem of learning propensity scores for assigning treatment in the later batches of the experiment to maximize the asymptotic precision of this estimator. For two common causal estimands, we estimate this precision using observations from previous batches, and then solve a finite-dimensional concave maximization problem to adaptively learn flexible propensity scores that converge to suitably defined optima in each batch at rate $O_p(N^{-1/4})$. By extending the framework of double machine learning, we show this rate suffices for our pooled estimator to attain the targeted precision after each batch, as long as nuisance function estimates converge at rate $o_p(N^{-1/4})$. These relatively weak rate requirements enable the investigator to avoid the common practice of discretizing the covariate space for design and estimation in batch adaptive experiments while maintaining the advantages of pooling. Our numerical study shows that such discretization often leads to substantial asymptotic and finite sample precision losses outweighing any gains from design.
appendix boundary found by appendix_command · 36% of the source is main text. Read the extracted text to check this.
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.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Hahn, J., Hirano, K., and Karlan, D (2011) Adaptive experimental design using the propensity score | 1.000 | 10 | 4 | 100% |
| 2 | Tabord-Meehan, M (2022) Stratification Trees for Adaptive Randomisation in Randomised Controlled Trials | 1.000 | 5 | 3 | 100% |
| 3 | Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C… (2018) Double/debiased machine learning for treatment and structural parameters | 0.961 | 9 | 4 | 89% |
| 4 | van der Vaart, A. W. and Wellner, J. A (1996) Weak Convergence and Empirical Processes | 0.843 | 5 | 3 | 60% |
| 5 | Blackwell, M., Pashley, N. E., and Valentino, D (2022) Batch adaptive designs to improve efficiency in social science experiments | 0.644 | 2 | 2 | 100% |
| 6 | Cytrynbaum, M (2021) Designing representative and balanced experiments by local randomization | 0.644 | 2 | 2 | 100% |
| 7 | Zhao, J (2023) Adaptive Neyman allocation | 0.644 | 2 | 2 | 100% |
| 8 | Atkinson, A., Donev, A., and Tobias, R (2007) Optimum experimental designs, with SAS, volume 34 | 0.405 | 1 | 1 | 100% |
| 9 | Chamberlain, G (1992) Efficiency bounds for semiparametric regression | 0.405 | 1 | 1 | 100% |
| 10 | Che, E. and Namkoong, H (2023) Adaptive experimentation at scale: Bayesian algorithms for flexible batches | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 46 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.