Archive for the Data Validation Category

Release 1.52 of the XL Audit Commander is available

Support is now provided for both comma separated value format files (CSV), as well as “print” files through the use of file specifications. Further information is available. Also, there are now a variety of tutorials available in shockwave format to demonstrate the system in action. Information about system limitations is now available.

Establishment of “Auditor’s Corner”

I have established a web page devoted to sharing articles and ideas on IT auditing. Part of it consists of tutorial modules as shown below. Some are VBA classes for use within Excel, others pertain to use of the XL Audit Commander.

General Audit Topics
Module Description Approx Length With Quiz? Last Update
Module-1 Obtaining Basic Population Statistics 15 minutes Yes 06-22-2007
Module-2 Audit uses for Benford’s Law 15 minutes Yes 06-22-2007
Module-3 Use of histograms in audits 15 minutes Yes 06-23-2007
Module-4 SQLite as an Audit Tool 30 min No 06-29-07
Module Description Approx Length With Quiz? Last Update
Module-5 Beyond the COUNTIF and SUMIF functions 20 min No 06-25-07
Module-6 A work-around for very large files 20 min No 06-29-07
Module-7 Identifying duplicates and gaps in large files 20 min No 06-29-07
Module-8 Sizing up the population - Going to Extremes 20 min No 06-29-07

Fairly simple procedure to create Benford’s Law charts

I have received a number of requests for the ability to create charts which show the results of tests of Benford’s law and can be downloaded and included in other documents, such as Word® or Powerpoint®. I have added such capability in the server routines (Main|Benford’s Law). As an option, an output file name can be specified for the chart desired. The resulting chart will then be available for view or download from the URL http://ezrstats.org/chart/FILENAME.PNG where FILENAME.PNG was the name specified for the output. An example of the charts is available for view. Use of the server and routines is available at no charge. I have had quite a number of visitors from both educational institutions as well as government agencies.

A simple, yet effective, way to test Benford’s law

This example explains how to perform a simple, yet effective, test to determine if a data range in Excel conforms with that expected under Benford’s law. The example data used is that provided in the Excel data sheet provided in the 26th annual report to Congress. This is an audit test that should take no more than a few minutes, yet provides a good test of fit for the numbers in the range, and potentially an easy test for possible fraud or made-up data. The step-by-step procedure is detailed. The example provided is the test of the first digit. Further tests of Benford’s law, such as the first 2 or 3 digits, the last 1 or 2 digits or the second digit, can be performed using EZ-R Stats for Windows (no cost). For the curious, there is an Excel workbook with all the formulae…

Auditors Guide to SQLite

Documentation showing how to use the open source SQLite database to perform common audit functions.  View.

Auditors Guide to Duplicate Payments

Documentation showing techniques used to identify duplicate payments. View document.

Auditors Guide to Tests Using Benford’s Law

Documentation showing audit techniques for the application of Benford’s Law.

Commonly used Internal Audit Software Functions

Documentation showing audit techniques for the commonly used Internal Audit software functions. View document.

Converting data to tab separated value format (TSV)

Techniques to convert data from a variety of sources (e.g. Excel, MS-Access, database ODBC, text files, etc. into the industry standard tab separated value format. Once data has been converted into this format, it may then be loaded into databases such as SQLite, MySQL, and is also in the proper format for data analysis using software packages such as EZ-R Stats for Windows and other software packages. View PDF

Testing the Application of Benford’s Law

Proc BENFORD is a command language procedure (and GUI) to test the conformity of a distribution with Benford’s law. The results of this audit test are assessed using Kolmogorov-Smirnov in order to provide a measure of the degree of fit between observed data and expected data.  View examples.