Earning While Learning: How to Run Batched Bandit Experiments

Jan Kemper and Davud Rostam-Afschar

No 1717, GLO Discussion Paper Series from Global Labor Organization (GLO)

Abstract: Researchers typically collect experimental data sequentially, allowing early outcome observations and adaptive treatment assignment to reduce exposure to inferior treatments. This article reviews multi-armed-bandit adaptive experimental designs that balance exploration and exploitation. Because adaptively collected experimental data through bandit algorithms violate standard asymptotics, inference is challenging. We implement an estimator that yields valid heteroskedasticity-robust confidence intervals in batched bandit designs and compare coverage in Monte Carlo simulations. We introduce bbandits for Stata, a tool for designing experiments via simulation, running interactive bandit experiments, and implementing and analyzing adaptively collected data. bbandits includes three common assignment algorithms-e-first, e-greedy, and Thompson sampling-and supports estimation, inference, and visualization.

Keywords: Randomized controlled trial; causal inference; multi-armed bandits; experimental design; machine learning (search for similar items in EconPapers)
JEL-codes: C1 C11 C12 C13 C15 C18 C8 C87 C88 C9 D83 (search for similar items in EconPapers)
Date: 2026
New Economics Papers: this item is included in nep-exp
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/337369/1/GLO-DP-1717.pdf (application/pdf)

Related works:
Working Paper: Earning While Learning: How to Run Batched Bandit Experiments (2026)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zbw:glodps:1717

Access Statistics for this paper

More papers in GLO Discussion Paper Series from Global Labor Organization (GLO) Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().