This is a great use of statistics by a couple of PhD candidates at New York University, identifying and quantifying some strong irregularities released by the Iranian Government.
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.
Even more than that, this demonstrates the power of cheap, easy access to information over the internet. Two students can pinpoint problems with election results half a world away, publish them, and have them copied, shared, bookmarked, re-tweeted all over the world in a couple of hours. Using publicly available data, and free software. We haven’t even begun to figure out all the ways in which the internet, social media, open source and open access is changing the way the world works.
This is another nail in the coffin for traditional academic publishing. If and when Scacco and Beber write this up as a journal article, the results won’t be publicly available until it goes through the rigorous academic review cycle, which could be anywhere from a few months to several years. But the events in Iran are happening now. Protestors are dying now. Publishing these results in a respected newspaper gets the results out much more quickly.
Furthermore, the authors made the data and statistical analysis code available for anyone in the world to download and run (remember, its all free software, and free data). This means that instead of a couple journal editors validating their work, they’ve effectively crowdsourced the review process. Brilliant. I don’t know how traditional academic journals can continue to pretend to be socially relevant in a world where anyone can make their work public, that work can be independently verified in minutes instead of years.