Movatterモバイル変換

jfa: Statistical Methodsfor Auditing

jfa is an R package that provides statisticalmethods for auditing. The package includes functions for planning,performing, and evaluating audit samples compliant with internationalauditing standards, as well as functions for auditing data, such astesting the distribution of leading digits against Benford’s law, andfunctions for auditing algorithms with respect to fairness. In additionto offering classical (frequentist) methods,jfa alsoprovides a straightforward implementation of their Bayesiancounterparts.

• Auditsampling: Get started
• Dataauditing: Get started
• Algorithmauditing: Get started

The functionality of thejfa package and itsintended workflow are implemented with a graphical user interface in theAudit module ofJASP, a free and open-source softwareprogram for statistical analyses.

Resources

• Package website(online documentation, vignettes)
• Textbook (detailedinformation, code examples)
• Ask aquestion (discussion forum)
• Open an issue(bug reports, feature requests)

Installation

Latest Release

The most recentjfa release can be installed fromCRAN via:

install.packages("jfa")

Development Version

To install the development version from GitHub, first make sure thatyou can install therstan package and C++ toolchain byfollowing theseinstructions.Oncerstan is successfully installed, you can installjfa from GitHub using theremotespackage by executing the following command in R:

# install.packages("remotes")remotes::install_github("koenderks/jfa",INSTALL_opts ="--no-multiarch")