slides and spread sheet powered by Google.doc....
New Statistical Audit Manual
Over the past decade many state revenue departments have retired the traditional block sample in conducting an audit in favor of the properly drawn random sample in the context of precise statistical mathematical guidelines. This is part of a trend of using statistics to enhance the effectiveness of all types of audits. Our free course provides background on this growing movement.
The manual is in the works for accountants to design and implement statistical audit samples. It will outline the process in a step by step fashion. Included will be an Excel workbook with exercises that helps the student to learn statistical auditing by example.
The Ubiquitous Statistical Audit
What do sales and use tax statistical audits have in common
with medical insurance claims audits?
Statistically they are identical. The purpose
of both is to review transactions either for
credits and/or dollar amounts in error requiring inurance company reimbursement for
overpayments or additional sales and use taxes owed by
the taxpayer. You can save a Demo to your hard
drive to explore the dynamics of proper
Free Demo Spread Sheet
Statistical Audit Course
The Demo is an example of varable sampling which, with our course, is an excellent gateway to using modern statistical tools that can unlock a wide range of other statistical services including:
data mining, internal audits; income estimation using IRS specifications; fraud detection; sampling for valuation; market analysis; statistical evidence in litigation; sampling for Medicare and other claims; meta files etc.
It is best to first get experience and a comfort level in working with your clients using the variable sampling statistcal audit. Use it as a building block to the more advanced topics listed above.PowerPoint Statistical Audit Course
Current Lesson Topic
BENFORD'S LAW PROVIDES A DATA analysis method that can help alert CPAs to
possible errors, potential fraud, manipulative biases,
costly processing inefficiencies or other irregularities. It is
a relativly simple formula:
p(d) = Log10(1/(1+d))
Benford's Law gives the expected patterns of the digits in the numbers in tabulated data such as town and city populations or Madoff's fictitious portfolio returns. Those digits, in unaltered data, will not occur in equal proportions; there is a large bias towards the lower digits, so much so that nearly one-half of all numbers are expected to start with the digits 1 or 2. The widespread applicability of Benford's Law and its practical uses is to detect fraud, errors and other anomalies. There are many examples on the internet of authentic and accurate data that conforms to Benford’s Law – and the fraudulent and invented numbers that do not. One famous case of fraud is when the World Bank, by using Benford's Law, found that a country had consistently provided false GDP data . That country's dishonesty only delayed the changes needed to correct years of economic mismanagement. You could also argue the World Bank should have also taken action sooner once the fraud was detected.