Iran 2009, Meet Ohio 2004

Statistical progression suggests the Ahmadinejad landslide was unlikely, although his win was predictable. In other words, while the election may have been rigged, it wasn't stolen.
Author:
Publish date:

With violence and mass protests dominating media coverage in the aftermath of elections in Iran, relatively little ink addresses whether scientific evidence supports the idea that the election was in fact stolen.

In several ways, Iran 2009 looks a lot like Ohio 2004: errors in the voting rolls, votes counted by partisans and strange anomalies in the results. Who knew we had so much in common?

As for Iran, opinion polls leading up to the election were sketchy, though widely cited as the most convincing evidence of fraud just as exit polling in Ohio raised eyebrows.

But not so fast. The Washington Post published an op-ed by two expert U.S. opinion surveyors, sponsored by Terror Free Tomorrow and the New America Foundation, who say based on pre-election telephone interviews two weeks before the election, President Mahmoud Ahmadinejad had a 2-to-1 lead over the favorite of Western media reports, former Prime Minister Mir Hossein Mousavi. That suggests the decision is accurate.

The only problem, as The Washington Post reports on its blog, is that more than half of respondents refused to answer the poll, expressed no opinion or said they would vote for neither of the two men.

A dozen or more public opinion surveys leading up to the election were also dodgy. They showed Mousavi's share creeping up, and by no means a landslide for President Ahmadinejad. But public opinion polls are tough in any country, let alone Iran. And we're supposed to believe the one poll conducted by Americans as irrefutable?

We turned to masters of probability and dissecting poll numbers, the Web site FiveThirtyEight.com. Armed with the "official" election results coming out of the Interior Ministry of Iran, the Web site charts a map of Iran by province in iconic shades of red and green.

FiveThirtyEight.com founder Nate Silver, who made a name for himself in the lead up to U.S. presidential elections in 2008 for his spot-on analysis of polling data, took to the provincial returns with some help from others familiar with Iranian politics. (Who can forget Mehdi Karroubi in 2005?) He used linear progression based on past elections going back to 1985 to graph the likelihood that the election results are fraudulent.

The conclusion is "maybe," with an emphasis on more likely than not.

"A regression using just first round data projects that in 2009, the first round winner would pick up just 31.5% of the vote, quite a low figure — but with two nationally competitive candidates, and two regionally competitive candidates, certainly not impossible," writes FiveThirtyEight.com blogger Renard Sexton. "Using just the overall victor's winning percentage, a 2009 projected figure of 58.7% comes out — higher than any polling would have suggested, but certainly within a range of normal. We would have expected Ahmadinejad's result from Friday, informed by the polling, historical trends and a bit of bet-hedging, to be between 40% and 55%."

Ahmadinejad instead captured 69 percent of the national vote, and Mousavi 28 percent.

Several items beyond mathematics support the case for a rigged election: super fast election results, which usually take three days to hand count paper ballots instead came in one day; reported voter harassment and intimidation; disruption of communications through cell phone and text message services; and most importantly, the outcomes in certain provinces relative to results in past elections.

"Given the absolutely bizarre figures that have been given for several provinces, given qualitative knowledge — for example, that Mehdi Karroubi earned almost negligible vote totals in his native Lorestan and neighboring Khuzestan, which he won in 2005 with 55.5% and 36.7% respectively — there is room for a much closer look," Sexton wrote.

Silver gave the pre-election polls their due considering inherent difficulties and flaws.

"While the numbers have been extremely variable between polls, and making a decision about what polls to include or exclude from aggregating in a case like Iran is nearly impossible, we can see a basic cycle that can be corroborated by anecdotal news evidence over the last two months. The incumbent has been largely held below a majority."

In response to widespread civil demonstrations, Iran's supreme leader Ayatollah Ali Khamenei has offered to recount certain ballots.

So now Iran can have its own Florida 2000, or Minnesota 2008, too.

Sign up for our free e-newsletter.

Are you on Facebook? Become our fan.

Follow us on Twitter.

Add our news to your site.

Related