adjustr: Stan Model Adjustments and Sensitivity Analyses using Importance Sampling

Assess the sensitivity of a Bayesian model (fitted using 'Stan' via 'rstan', 'brms', or 'cmdstanr') to the specification of its likelihood and priors. Users provide a series of alternate sampling specifications, and the package uses Pareto-smoothed importance sampling (PSIS) to estimate posterior quantities of interest under each specification, without needing to refit the model. Methods are based on Vehtari, Simpson, Gelman, Yao, and Gabry (2024) <doi:10.48550/arXiv.1507.02646>.

Version:	0.2.0
Depends:	R (≥ 3.6.0), dplyr (≥ 1.0.0)
Imports:	rlang, tidyselect, rstan, loo
Suggests:	ggplot2, extraDistr, tidyr, testthat, covr, knitr, rmarkdown
Published:	2026-05-29
DOI:	10.32614/CRAN.package.adjustr
Author:	Cory McCartan [aut, cre, cph]
Maintainer:	Cory McCartan <mccartan at psu.edu>
BugReports:	https://github.com/CoryMcCartan/adjustr/issues
License:	MIT + file LICENSE
URL:	https://corymccartan.com/adjustr/
NeedsCompilation:	no
Materials:	README, NEWS
CRAN checks:	adjustr results

Documentation:

Reference manual:	adjustr.html , adjustr.pdf
Vignettes:	Sensitivity Analysis of a Simple Hierarchical Model (source, R code)

Downloads:

Package source:	adjustr_0.2.0.tar.gz
Windows binaries:	r-devel: adjustr_0.2.0.zip, r-release: adjustr_0.2.0.zip, r-oldrel: adjustr_0.2.0.zip
macOS binaries:	r-release (arm64): adjustr_0.2.0.tgz, r-oldrel (arm64): adjustr_0.2.0.tgz, r-release (x86_64): adjustr_0.2.0.tgz, r-oldrel (x86_64): adjustr_0.2.0.tgz

Linking:

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