Stealing elections for dummies: Part 1

The post-election turmoil in Iran doesn’t seem to be improving. Despite the large amount of press the crisis is receiving, there doesn’t seem to be much of a consensus about what, if anything, the rest of the world can do but watch and wait.

One of the less controversial things we can do is sit down and analyse the election data. Bernd Beber and Alexandra Scacco describe their analysis of provincial data from the Iranian election. It turns out that a great place to look for falsified data is in the last two digits: humans are just bad at making up numbers randomly.

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.

More here, at the Washington Post, as well as here.

Hat tip to Chris Blattman for the link.