EconBase
← All papers

Stochastic Treatment Choice with Empirical Welfare Updating

Toru Kitagawa, Hugo Lopez, Jeff Rowley

arXiv 3 Nov 2022 · Econometrics

arXiv:2211.01537 · PDF · DOI · OpenAlex · Extracted main text

Abstract

This paper proposes a novel method to estimate individualised treatment assignment rules. The method is designed to find rules that are stochastic, reflecting uncertainty in estimation of an assignment rule and about its welfare performance. Our approach is to form a prior distribution over assignment rules, not over data generating processes, and to update this prior based upon an empirical welfare criterion, not likelihood. The social planner then assigns treatment by drawing a policy from the resulting posterior. We show analytically a welfare-optimal way of updating the prior using empirical welfare; this posterior is not feasible to compute, so we propose a variational Bayes approximation for the optimal posterior. We characterise the welfare regret convergence of the assignment rule based upon this variational Bayes approximation, showing that it converges to zero at a rate of ln(n)/sqrt(n). We apply our methods to experimental data from the Job Training Partnership Act Study to illustrate the implementation of our methods.

Citation extraction

78
references
161
in-text mentions
78
distinct cited
5
self-citations
10,665
main-text words

appendix boundary found by appendix_command · 46% 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
1Kitagawa, T. and A. Tetenov (2018) Who should be treated? empirical welfare maximization methods for treatment choice self0.95825688%
2Alquier, P., J. Ridgway, and N. Chopin (2016) On the properties of variational approximations of Gibbs posteriors0.9098375%
3Bégin, L., P. Germain, F. Laviolette, and J.-F. Roy (2016) PAC-Bayesian bounds based on the Rényi divergence, in0.9098375%
4Manski, C. F (2004) Statistical treatment rules for heterogeneous populations0.87452100%
5Germain, P., A. Lacasse, F. Laviolette, and M. Marchand (2009) PAC-Bayesian learning of linear classifiers, in0.84333100%
6McAllester, D. A (2003) PAC-Bayesian stochastic model selection0.81142100%
7Chamberlain, G (2011) Bayesian aspects of treatment choice0.73732100%
8Bloom, H. S., L. L. Orr, S. H. Bell, G. Cave, F. Doolittle, W. Lin,… (1997) The benefits and costs of JTPA Title II-A programs: Key findings from the National Job Training Partnership Act study0.73732100%
9Maurer, A (2004) A note on the PAC Bayesian theorem0.6936333%
10Bissiri, P. G., C. C. Holmes, and S. G. Walker (2016) A general framework for updating belief distributions0.64422100%

Showing the top 10 of 78 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
1The $f$-divergence of a von Mises-Fisher distribution from some reference distributions1.00053
2PAC-Bayesian Treatment Allocation Under Budget Constraints0.64422
3Nonparametric Bayesian Policy Learning0.64422
4Stable Probability Weighting Large-Sample and Finite-Sample Estimation and Inference Methods for Heterogeneous Causal Effects of Multivalued Treatments Under Limited Overlap0.40511
5Individualized Treatment Allocation in Sequential Network Games0.40511
6Bandit Algorithms for Policy Learning: Methods, Implementation, and Welfare-performance0.40511