Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/337369 
Erscheinungsjahr: 
2026
Schriftenreihe/Nr.: 
GLO Discussion Paper No. 1717
Verlag: 
Global Labor Organization (GLO), Essen
Zusammenfassung: 
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.
Schlagwörter: 
Randomized controlled trial
causal inference
multi-armed bandits
experimental design
machine learning
JEL: 
C1
C11
C12
C13
C15
C18
C8
C87
C88
C9
D83
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe
892.76 kB





Publikationen in EconStor sind urheberrechtlich geschützt.