arXiv 5 Mar 2025 · Econometrics
arXiv:2503.03910 · PDF · DOI · OpenAlex · Extracted main text
Policymakers often make changes to policies whose benefits and costs are unknown and must be inferred from statistical estimates in empirical studies. In this paper I consider the problem of a planner who changes upfront spending on a set of policies to maximize social welfare but faces statistical uncertainty about the impact of those changes. I set up a local optimization problem that is tractable under statistical uncertainty and solve for the local change in spending that maximizes the posterior expected rate of increase in welfare. I propose an empirical Bayes approach to approximating the optimal local spending rule, which solves the planner's local problem with posterior mean estimates of benefits and net costs. I show theoretically that the empirical Bayes approach performs well by deriving rates of convergence for the rate of increase in welfare. These rates converge for a large class of decision problems, including those where rates from a sample plug-in approach do not.
appendix boundary found by appendix_command · 35% 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 | Hendren, Nathaniel and Sprung-Keyser, Ben (2020) A unified welfare analysis of government policies | 0.953 | 15 | 7 | 87% |
| 2 | Soloff, Jake A and Guntuboyina, Adityanand and Sen, Bodhisattva (2025) Multivariate, heteroscedastic empirical Bayes via nonparametric maximum likelihood | 0.709 | 28 | 6 | 36% |
| 3 | Chetty, Raj (2009) Sufficient statistics for welfare analysis: A bridge between structural and reduced-form methods | 0.644 | 2 | 2 | 100% |
| 4 | Efron, Bradley (2012) Large-scale inference: empirical Bayes methods for estimation, testing, and prediction | 0.644 | 2 | 2 | 100% |
| 5 | Finkelstein, Amy and Hendren, Nathaniel (2020) Welfare analysis meets causal inference | 0.644 | 2 | 2 | 100% |
| 6 | Kleven, Henrik J (2021) Sufficient statistics revisited | 0.644 | 2 | 2 | 100% |
| 7 | Koenker, Roger and Mizera, Ivan (2014) Convex optimization, shape constraints, compound decisions, and empirical Bayes rules | 0.644 | 2 | 2 | 100% |
| 8 | Robbins, H (1956) An empirical Bayes approach to statistics | 0.644 | 2 | 2 | 100% |
| 9 | Jiang, Wenhua (2020) On general maximum likelihood empirical Bayes estimation of heteroscedastic IID normal means | 0.585 | 3 | 3 | 33% |
| 10 | Chen, Jiafeng (2025) Empirical Bayes when estimation precision predicts parameters | 0.538 | 45 | 6 | 16% |
Showing the top 10 of 42 scored citations.
arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.
| Citing paper | Intensity | Mentions | Sections | |
|---|---|---|---|---|
| 1 | Nonparametric Bayesian Policy Learning | 0.737 | 3 | 2 |
| 2 | Policy Learning with Confidence$^$ | 0.511 | 2 | 1 |
| 3 | On the Lower Confidence Band for the Optimal Welfare in Policy Learning | 0.405 | 1 | 1 |
| 4 | Compound Selection Decisions: An Almost SURE Approach | 0.405 | 1 | 1 |
| 5 | Tweedie Calculus | 0.405 | 1 | 1 |