Welcome to the ‘Get started’ page of thejfapackage.jfa is an R package that provides Bayesian andclassical statistical methods for audit sampling, data auditing, andalgorithm auditing. This page points you to the vignettes accompanyingeach of these three subjects.
Firstly,jfa facilitates statistical audit sampling.That is, the package provides functions for planning, performing, andevaluating an audit sample compliant with international standards onauditing.
Secondly,jfa facilitates statistical data auditing.That is, the package includes functions for auditing data, such astesting the distribution of first digits of a data set against Benford’slaw, or assessing whether a data set includes an unusual amount ofrepeated values.
Finally,jfa facilitates statistical algorithmauditing. That is, the package implements functions for auditingalgorithms, such as computing fairness metrics and testing the equalityof parity metrics across protected groups.