eo

Statistics vs. Iran election

From the Washington Post article "The Devil Is in the Digits" about a statistical analysis of the Iran election results:

The numbers look suspicious. We find too many 7s and not enough 5s in the last digit. We expect each digit (0, 1, 2, and so on) to appear at the end of 10 percent of the vote counts. But in Iran's provincial results, the digit 7 appears 17 percent of the time, and only 4 percent of the results end in the number 5. Two such departures from the average – a spike of 17 percent or more in one digit and a drop to 4 percent or less in another – are extremely unlikely. Fewer than four in a hundred non-fraudulent elections would produce such numbers.

Apart from that, there seem to be too many adjacent digits (like 23 or 34, but not 61) in the data so that, as the article concludes, it becomes very likely that the figures have been tampered with if both observations are taken together.

I have no idea whether the interpretation of the data is correct, but it always amazes me what seems to be possible using statistics.