Number Theory


Properties of Data Sets that Conform to Benford's Law

Authors: Robert C. Hall

The concept and application of Benford's Law have been examined a lot in the last 10 years or so, especially with regard to accounting forensics. There have been many papers written as to why Benford's Law is so prevalent and the concomitant reasons why(proofs). There are, unfortunately, many misconceptions such as the newly coined phrase "the Summation theorem", which states that if a data set conforms to Benford's Law then the sum of all numbers that begin with a particular digit (1,2,3,4,5,6,7,8,9) should be equal. Such is usually not the case. For exponential functions (y=aexp(x) it is but not for most other functions. I will show as to why this is the case. The distribution tends to be a Benford instead of a Uniform distribution. Also, I will show that if the probability density function (pdf) of the logarithm of a data set begins and ends on the x axis and if the the values of the pdf between all integral powers of ten can be approximated with a straight line then the data set will tend to conform to Benford's Law.

Comments: 46 Pages.

Download: PDF

Submission history

[v1] 2019-06-08 13:38:48

Unique-IP document downloads: 19 times is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus