whatifbandit: Analyzing Randomized Experiments as Multi-Arm Bandits

Simulates the results of completed randomized controlled trials, as if they had been conducted as adaptive Multi-Arm Bandit (MAB) trials instead. Augmented inverse probability weighted estimation (AIPW), outlined by Hadad et al. (2021) <doi:10.1073/pnas.2014602118>, is used to robustly estimate the probability of success for each treatment arm under the adaptive design. Provides customization options to simulate perfect/imperfect information, stationary/non-stationary bandits, blocked treatment assignments, along with control augmentation, and other hybrid strategies for assigning treatment arms. The methods used in simulation were inspired by Offer-Westort et al. (2021) <doi:10.1111/ajps.12597>.

Version:	0.3.0
Depends:	R (≥ 4.1.0)
Imports:	bandit, data.table, dplyr, furrr, ggplot2, lubridate, purrr, randomizr, rlang, tibble, tidyr
Suggests:	future, knitr, rmarkdown, testthat (≥ 3.0.0)
Published:	2025-11-03
DOI:	10.32614/CRAN.package.whatifbandit (may not be active yet)
Author:	Noah Ochital [aut, cre, cph], Ryan T. Moore [ctb, cph]
Maintainer:	Noah Ochital <noahochital at icloud.com>
BugReports:	https://github.com/Noch05/whatifbandit/issues
License:	GPL (≥ 3)
URL:	https://github.com/Noch05/whatifbandit
NeedsCompilation:	no
Materials:	README, NEWS
CRAN checks:	whatifbandit results

Documentation:

Reference manual:	whatifbandit.html , whatifbandit.pdf
Vignettes:	Introduction to '{whatifbandit}' (source, R code)

Downloads:

Package source:	whatifbandit_0.3.0.tar.gz
Windows binaries:	r-devel: whatifbandit_0.3.0.zip, r-release: not available, r-oldrel: not available
macOS binaries:	r-release (arm64): whatifbandit_0.3.0.tgz, r-oldrel (arm64): whatifbandit_0.3.0.tgz, r-release (x86_64): whatifbandit_0.3.0.tgz, r-oldrel (x86_64): whatifbandit_0.3.0.tgz

Linking:

Please use the canonical form https://CRAN.R-project.org/package=whatifbandit to link to this page.