Empirical Bayes Selection for Value Maximization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Coey, Dominic, Hung, Kenneth
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918132195524608
author Coey, Dominic
Hung, Kenneth
author_facet Coey, Dominic
Hung, Kenneth
contents We study the problem of selecting the best $m$ units from a set of $n$ as $m / n \to α\in (0, 1)$, where noisy, heteroskedastic measurements of the units' true values are available and the decision-maker wishes to maximize the aggregate true value of the units selected. Given a parametric prior distribution, the empirical Bayes decision rule incurs $O_p(n^{-1})$ regret relative to the Bayesian oracle that knows the true prior. More generally, if the error in the estimated prior is of order $O_p(r_n)$, regret is $O_p(r_n^2)$. In this sense \emph{selection} of the best units is fundamentally easier than \emph{estimation} of their values. We show this regret bound is sharp in the parametric case, by giving an example in which it is attained. Using priors calibrated from a dataset of over four thousand internet experiments, we confirm that empirical Bayes methods perform well in detecting the best treatments with only a modest number of experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2210_03905
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Empirical Bayes Selection for Value Maximization
Coey, Dominic
Hung, Kenneth
Methodology
Econometrics
62C12, 62C25 (Primary) 62P20 (Secondary)
We study the problem of selecting the best $m$ units from a set of $n$ as $m / n \to α\in (0, 1)$, where noisy, heteroskedastic measurements of the units' true values are available and the decision-maker wishes to maximize the aggregate true value of the units selected. Given a parametric prior distribution, the empirical Bayes decision rule incurs $O_p(n^{-1})$ regret relative to the Bayesian oracle that knows the true prior. More generally, if the error in the estimated prior is of order $O_p(r_n)$, regret is $O_p(r_n^2)$. In this sense \emph{selection} of the best units is fundamentally easier than \emph{estimation} of their values. We show this regret bound is sharp in the parametric case, by giving an example in which it is attained. Using priors calibrated from a dataset of over four thousand internet experiments, we confirm that empirical Bayes methods perform well in detecting the best treatments with only a modest number of experiments.
title Empirical Bayes Selection for Value Maximization
topic Methodology
Econometrics
62C12, 62C25 (Primary) 62P20 (Secondary)
url https://arxiv.org/abs/2210.03905