Bayesian adaptive bandit-based designs using the Gittins index for multi-armed trials with normally distributed endpoints

DOI10.1080/02664763.2017.1342780OpenAlexW2598454364WikidataQ55001321 ScholiaQ55001321MaRDI QIDQ5035752

Adam L. Smith, Sofía S. Villar

Publication date: 22 February 2022

Published in: Journal of Applied Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1703.05172

zbMATH Keywords

Gittins indexsequential samplingmulti-armed banditpatient allocationresponse adaptive proceduresnormally distributed endpoint

Mathematics Subject Classification ID

Applications of statistics (62Pxx)

Related Items (4)

Generalisations of a Bayesian decision-theoretic randomisation procedure and the impact of delayed responses ⋮ Nonmyopic and pseudo-nonmyopic approaches to optimal sequential design in the presence of covariates ⋮ A novel statistical test for treatment differences in clinical trials using a response‐adaptive forward‐looking Gittins Index Rule ⋮ Rejoinder: response-adaptive randomization in clinical trials

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
• Batched bandit problems
• The multi-armed bandit problem with covariates
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• One-armed bandit problems with covariates
• The learning component of dynamic allocation indices
• Response‐adaptive randomization for multi‐arm clinical trials using the forward looking Gittins index rule
• A generalized Dunnett test for multi-arm multi-stage clinical studies with treatment selection
• Multi‐Armed Bandit Allocation Indices
• Probability, Random Processes, and Statistical Analysis
• Randomised allocation of treatments in sequential trials
• A One-Armed Bandit Problem with a Concomitant Variable
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Bayesian adaptive bandit-based designs using the Gittins index for multi-armed trials with normally distributed endpoints