EconBase
← All papers

Treatment recommendation with distributional targets

Anders Bredahl Kock, David Preinerstorfer, Bezirgen Veliyev

arXiv 19 May 2020 · Econometrics · publishedJournal of Econometrics (2022) · 3 citations (OpenAlex)

arXiv:2005.09717 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We study the problem of a decision maker who must provide the best possible treatment recommendation based on an experiment. The desirability of the outcome distribution resulting from the policy recommendation is measured through a functional capturing the distributional characteristic that the decision maker is interested in optimizing. This could be, e.g., its inherent inequality, welfare, level of poverty or its distance to a desired outcome distribution. If the functional of interest is not quasi-convex or if there are constraints, the optimal recommendation may be a mixture of treatments. This vastly expands the set of recommendations that must be considered. We characterize the difficulty of the problem by obtaining maximal expected regret lower bounds. Furthermore, we propose two (near) regret-optimal policies. The first policy is static and thus applicable irrespectively of subjects arriving sequentially or not in the course of the experimentation phase. The second policy can utilize that subjects arrive sequentially by successively eliminating inferior treatments and thus spends the sampling effort where it is most needed.

Citation extraction

49
references
71
in-text mentions
49
distinct cited
3
self-citations
30,426
main-text words

appendix boundary found by none_found · 100% 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
1Kock, A. B., D. Preinerstorfer, and B. Veliyev (2020) Functional sequential treatment allocation self1.00073100%
2Bubeck, S., R. Munos, and G. Stoltz (2009) Pure exploration in multi-armed bandits problems1.00053100%
3Kock, A. B., D. Preinerstorfer, and B. Veliyev (2020) Functional sequential treatment allocation with covariates self0.84333100%
4Manski, C. F. and A. Tetenov (2016) Sufficient trial size to inform clinical practice0.73732100%
5Audibert, J.-Y., S. Bubeck, and R. Munos (2010) Best arm identification in multi-armed bandits0.64422100%
6Bélisle, C. and V. Melfi (2008) Independence after adaptive allocation0.64422100%
7Karnin, Z., T. Koren, and O. Somekh (2013) Almost optimal exploration in multi-armed bandits0.64422100%
8Manski, C. F (2004) Statistical treatment rules for heterogeneous populations0.64422100%
9Tran-Thanh, L. and J. Y. Yu (2014) Functional bandits0.64422100%
10Cassel, A., S. Mannor, and A. Zeevi (2018) A general approach to multi-armed bandits under risk criteria0.51121100%

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
1Regularizing Fairness in Optimal Policy Learning with Distributional Targets0.69395
2Efficient Adaptive Experimental Design for Average Treatment Effect Estimation0.40511
3Treatment Choice with Nonlinear Regret0.40511
4Stochastic treatment choice with empirical welfare updating0.40511
5Policy Learning with Distributional Welfare0.40511
6A Primer on the Analysis of Randomized Experiments and a Survey of some Recent Advances0.40511
7Locally Robust Policy Learning: Inequality, Inequality of Opportunity and Intergenerational Mobility0.40511
8Leave No One Undermined: Policy Targeting with Regret Aversion0.40511
9Adaptive Experimental Design for Policy Learning0.00021
10Functional Sequential Treatment Allocation0.00011