EconBase
← All papers

Optimal Experimental Design for Staggered Rollouts

Ruoxuan Xiong, Susan Athey, Mohsen Bayati, Guido Imbens

arXiv 9 Nov 2019 · Econometrics · publishedManagement Science (2023) · 22 citations (OpenAlex)

arXiv:1911.03764 · PDF · DOI · OpenAlex · Extracted main text

Abstract

In this paper, we study the design and analysis of experiments conducted on a set of units over multiple time periods where the starting time of the treatment may vary by unit. The design problem involves selecting an initial treatment time for each unit in order to most precisely estimate both the instantaneous and cumulative effects of the treatment. We first consider non-adaptive experiments, where all treatment assignment decisions are made prior to the start of the experiment. For this case, we show that the optimization problem is generally NP-hard, and we propose a near-optimal solution. Under this solution, the fraction entering treatment each period is initially low, then high, and finally low again. Next, we study an adaptive experimental design problem, where both the decision to continue the experiment and treatment assignment decisions are updated after each period's data is collected. For the adaptive case, we propose a new algorithm, the Precision-Guided Adaptive Experiment (PGAE) algorithm, that addresses the challenges at both the design stage and at the stage of estimating treatment effects, ensuring valid post-experiment inference accounting for the adaptive nature of the design. Using realistic settings, we demonstrate that our proposed solutions can reduce the opportunity cost of the experiments by over 50%, compared to static design benchmarks.

Citation extraction

74
references
99
in-text mentions
74
distinct cited
0
self-citations
18,676
main-text words

appendix boundary found by appendix_titled_section at “Supplementary Material for Generalized Least Squares” · 37% 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
1Hemming K, Haines TP, Chilton PJ, Girling AJ, Lilford RJ (2015) The stepped wedge cluster randomised trial: rationale, design, analysis, and reporting0.92843100%
2Bhat N, Farias VF, Moallemi CC, Sinha D (2019) Near optimal ab testing0.84333100%
3Li F, Turner EL, Preisser JS (2018) Optimal allocation of clusters in cohort stepped wedge designs0.84333100%
4Card D, Krueger AB (1994) Minimum wages and employment: A case study of the fast-food industry in new jersey and pennsylvania0.73732100%
5Abadie A, Diamond A, Hainmueller J (2010) Synthetic control methods for comparative case studies: Estimating the effect of california’s tobacco control program0.64422100%
6Abaluck J, Kwong LH, Styczynski A, Haque A, Kabir MA, Bates-Jefferys… (2021) Impact of community masking on covid-19: A cluster-randomized trial in bangladesh0.64422100%
7Bertsekas D (2012) Dynamic programming and optimal control: Volume I0.64422100%
8Glynn PW, Whitt W (1992) a) The asymptotic efficiency of simulation estimators0.64422100%
9Johari R, Koomen P, Pekelis L, Walsh D (2017) Peeking at a/b tests: Why it matters, and what to do about it0.64422100%
10Singham DI, Schruben LW (2012) Finite-sample performance of absolute precision stopping rules0.64422100%

Showing the top 10 of 74 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Estimating Effects of Long-Term Treatments0.84333
2Data-Driven Switchback Experiments: Theoretical Tradeoffs and Empirical Bayes Designs0.84333
3Multiple Randomization Designs: Estimation and Inference with Interference0.64422
4Can We Validate Counterfactual Estimations in the Presence of General Network Interference?0.64422
5Efficient Estimation for Staggered Rollout Designs0.51121
6Tackling Interference Induced by Data Training Loops in A/B Tests: A Weighted Training Approach0.40511
7Large-Sample Properties of the Synthetic Control Method under Selection on Unobservables0.40511
8Causal Models for Longitudinal and Panel Data: A Survey0.40511
9Heterogeneous Treatment Effects in Panel Data0.40511
10Higher-Order Causal Message Passing for Experimentation with Complex Interference0.40511