EconBase
← All papers

Efficient Online Estimation of Causal Effects by Deciding What to Observe

Shantanu Gupta, Zachary C. Lipton, David Childers

arXiv 20 Aug 2021 · Machine Learning · 1 citations (OpenAlex)

arXiv:2108.09265 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Researchers often face data fusion problems, where multiple data sources are available, each capturing a distinct subset of variables. While problem formulations typically take the data as given, in practice, data acquisition can be an ongoing process. In this paper, we aim to estimate any functional of a probabilistic model (e.g., a causal effect) as efficiently as possible, by deciding, at each time, which data source to query. We propose online moment selection (OMS), a framework in which structural assumptions are encoded as moment conditions. The optimal action at each step depends, in part, on the very moments that identify the functional of interest. Our algorithms balance exploration with choosing the best action as suggested by current estimates of the moments. We propose two selection strategies: (1) explore-then-commit (OMS-ETC) and (2) explore-then-greedy (OMS-ETG), proving that both achieve zero asymptotic regret as assessed by MSE. We instantiate our setup for average treatment effect estimation, where structural assumptions are given by a causal graph and data sources may include subsets of mediators, confounders, and instrumental variables.

Citation extraction

49
references
63
in-text mentions
49
distinct cited
1
self-citations
8,772
main-text words

appendix boundary found by appendix_command · 38% 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
1J. D. Angrist (1990) Lifetime earnings and the vietnam era draft lottery: evidence from social security administrative records0.7374275%
2J. L. Hill (2011) Bayesian nonparametric modeling for causal inference0.73732100%
3L. P. Hansen (1982) Large sample properties of generalized method of moments estimators0.64422100%
4W. K. Newey and D. McFadden (1994) Large sample estimation and hypothesis testing0.5115220%
5R. Zhan, Z. Ren, S. Athey, and Z. Zhou (2021) Policy learning with adaptively collected data0.5112250%
6T. Lattimore and C. Szepesvári (2020) Bandit algorithms0.51121100%
7V. Dorie (2016) Non-parametrics for causal inference0.40511100%
8D. W. Andrews (1999) Consistent moment selection procedures for generalized method of moments estimation0.40511100%
9J. D. Angrist (2009) Replication data for: Lifetime Earnings and the Vietnam Era Draft Lottery: Evidence from Social Security Administrative Records,…0.40511100%
10E. Bareinboim and J. Pearl (2016) Causal inference and the data-fusion problem0.40511100%

Showing the top 10 of 49 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
1Efficient Adaptive Experimental Design for Average Treatment Effect Estimation0.40511
2Best Arm Identification with Contextual Information under a Small Gap0.40511
3Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choice0.40511
4Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap0.00011
5Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds0.00011
6Worst-Case Optimal Multi-Armed Gaussian Best Arm Identification with a Fixed Budget0.00011
7Adaptive Experimental Design for Policy Learning0.00011