integrity: Assessing the Integrity and Trustworthiness of Clinical Trials Data

The integrity package implements the IPD Integrity Tool, a structured and transparent framework for evaluating the integrity of individual participant data (IPD) from randomised trials (see Hunter et al. (2024) <doi:10.1002/jrsm.1738> and <doi:10.32614/RJ-2017-008>). It supports users to identify potential issues, such as unusual data patterns, implausible values, lack of expected correlations, date violations, and inconsistencies. The package provides reproducible workflows for screening, documenting and summarising integrity concerns, and may be applied by evidence synthesists, editors, and others to determine whether a randomised trial may be considered sufficiently trustworthy to contribute to the evidence base that informs policy and practice.

Version: 1.0.1
Depends: R (≥ 4.1.0)
Imports: ggplot2, dplyr, janitor, gtsummary, ggpubr, lubridate, car, rlang
Suggests: knitr, pkgload, readxl, rmarkdown, testthat (≥ 3.0.0), yaml
Published: 2026-05-26
DOI: 10.32614/CRAN.package.integrity
Author: Sol Libesman [aut, cre], Kylie Hunter [aut], David Nguyen [aut], Dario Strbenac [aut], Anne Lene Seidler [aut], Jie Kang [aut]
Maintainer: Sol Libesman <sol.libesman at sydney.edu.au>
License: GPL-3
URL: https://github.sydney.edu.au/Charles-Perkins-Centre-Data-Science-Hub/CPCDASH0010
NeedsCompilation: no
Materials: README, NEWS
CRAN checks: integrity results

Documentation:

Reference manual: integrity.html , integrity.pdf
Vignettes: An Introduction to the integrity Package (source, R code)

Downloads:

Package source: integrity_1.0.1.tar.gz
Windows binaries: r-devel: integrity_1.0.zip, r-release: integrity_1.0.zip, r-oldrel: integrity_1.0.1.zip
macOS binaries: r-release (arm64): integrity_1.0.1.tgz, r-oldrel (arm64): integrity_1.0.1.tgz, r-release (x86_64): integrity_1.0.1.tgz, r-oldrel (x86_64): integrity_1.0.1.tgz
Old sources: integrity archive

Linking:

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