Each of these two tests provides strong evidence that the numbers released by Iran's Ministry of the Interior were manipulated. But taken together, they leave very little room for reasonable doubt. The probability that a fair election would produce both too few non-adjacent digits and the suspicious deviations in last-digit frequencies described earlier is less than .005. In other words, a bet that the numbers are clean is a one in two-hundred long shot.As many fraud investigators know, digital analysis has been used to look for financial chicanery too. However, traditional digital analysis generally looks at the first two digits and compares them with Benford's Law to see if they are distributed randomly. The approach used to investigate election fraud is an interesting twist on digital analysis.
Thursday, June 25, 2009
Election fraud in Iran -- check the digits...
A former student of mine, Dan Leslie, pointed out an article in The Washington Post that analyzes the frequency of the last two digits in the votes reported for the recent Iranian election to see if the vote counts appear random. The authors conclude that: