R package jfa
jfa is a multi-functional R package for statistical auditing. The package provides the user with four generic functions for planning, performing, and evaluating an audit and its results. Specifically, it contains functions for calculating sample sizes for substantive testing, sampling from data according to standard auditing techniques, and calculating various confidence bounds for the maximum error from data or summary statistics. The package also allows the user to create a Bayesian prior distribution for use in these functions. The
jfa package can be used to set up the entire audit sampling workflow.
For complete documentation, see the package manual.
- Koen Derks - Initial work - Website
See also the list of contributors who participated in this project.
This project is licensed under the GPL-3 License.
These instructions will get you a copy of the
jfa package up and running on your
local machine for use in R and RStudio.
- R - The programming language used for deploying the package.
jfa is simple to download and set-up. The live version from CRAN can be downloaded by running the following command in R:
jfa package can then be loaded in RStudio by typing:
Examples can be found in the package vignette.
Below is a list of the available functions in the current development version of
jfa, sorted by their occurrence in the standard audit sampling workflow.
auditPrior: Creating a prior distribution for substantive testing
This function creates a prior distribution according to the audit risk model and assessments of the inherent and control risk. The returned object is of class
jfaPrior and can be used with associated
jfaPrior results can also be used as input argument for the
prior argument in other functions.
auditPrior(materiality, confidence = 0.95, method = "arm", ir = 1, cr = 1, expectedError = 0, likelihood = "binomial", N = NULL)
Planning: Calculating an audit sample size
This function calculates the required sample size for an audit, based on the poisson, binomial, or hypergeometric likelihood. A prior can be specified to combine with the specified likelihood in order to perform Bayesian planning. The returned
jfaPlanning object has a
print() and a
planning(materiality = NULL, confidence = 0.95, expectedError = 0, distribution = "poisson" N = NULL, maxSize = 5000, prior = FALSE, kPrior = 0, nPrior = 0)
Sampling: Selecting transactions from a population
This function takes a data frame and performs sampling according to one of three algorithms: random sampling, cell sampling, or fixed interval sampling in combination with either record sampling or monetary unit sampling. The returned
jfaSampling object has a
print() and a
plot() method. The
sampleSize argument can also be an object of class
sampling(population, sampleSize, bookValues = NULL, algorithm = "random", units = "record", intervalStartingPoint = 1, ordered = TRUE, ascending = TRUE, withReplacement = FALSE, seed = 1)
Evaluation: Calculating confidence bounds for audit samples
This function takes a sample data frame or summary statistics about an evaluated audit sample and calculates a confidence bound according to a specified method. The returned
jfaEvalution object has a
evaluation(sample = NULL, bookValues = NULL, auditValues = NULL, confidence = 0.95, dataType = "sample", sampleSize = NULL, sumErrors = NULL, method = "binomial", materiality = NULL, N = NULL, rohrbachDelta = 2.7)