Iranian Election – no statistical smoking gun, but a possibly a crime scene
FiveThirtyEight provides a considered post showing that the graph alleging that a strong linear relationship in voting patterns is evidence of electoral fraud is not a smoking gun.
To be clear, these results certainly do not prove that Iran’s election was clean. I have no particular reason to believe the results reported by the Interior Ministry. But I also don’t have any particular reason to disbelieve them, at least based on the statistical evidence. If Moosavi truly did have the support of a majority of Iran’s citizenry, the best evidence we will have of that is what happens in the streets of Tehran over the next days and weeks.
He also provides a link to Juan Cole’s blog which gives top reasons for thinking the election was stolen.
this post-election situation looks to me like a crime scene. And here is how I would reconstruct the crime.
As the real numbers started coming into the Interior Ministry late on Friday, it became clear that Mousavi was winning. Mousavi’s spokesman abroad, filmmaker Mohsen Makhbalbaf, alleges that the ministry even contacted Mousavi’s camp and said it would begin preparing the population for this victory.
The ministry must have informed Supreme Leader Ali Khamenei, who has had a feud with Mousavi for over 30 years, who found this outcome unsupportable. And, apparently, he and other top leaders had been so confident of an Ahmadinejad win that they had made no contingency plans for what to do if he looked as though he would lose.
They therefore sent blanket instructions to the Electoral Commission to falsify the vote counts.
This clumsy cover-up then produced the incredible result of an Ahmadinejad landlside in Tabriz and Isfahan and Tehran.
The reason for which Rezaie and Karoubi had to be assigned such implausibly low totals was to make sure Ahmadinejad got over 51% of the vote and thus avoid a run-off between him and Mousavi next Friday, which would have given the Mousavi camp a chance to attempt to rally the public and forestall further tampering with the election.
This scenario accounts for all known anomalies and is consistent with what we know of the major players.
Comments
| 13 June 2009, 11:20 pm |
This hypothetical reconstruction certainly seems to make a lot of sense. Bearing in mind, on the one hand, that the mullahs always had it in their power to rig the election in their boy’s favour, and, on the other, that if they’d done it more discreetly they might well have got away with it without triggering such a wave of outrage, it looks as though some serious setback (from the ayatollahs’ point of view) must have occurred to prompt them to hit the panic button the way they did. A massive vote for Mousavi, giving him a first-round victory, would presumably have amounted to an unexpected setback on that scale.
| 14 June 2009, 12:02 am |
Well, the US says we aren’t accepting this outcome:
http://news.yahoo.com/s/ap/20090613/ap_on_go_ca_st_pe/us_us_iran
I don’t know whether to laugh or cry.
PS, where is Roger Cohen?
| 14 June 2009, 12:06 am |
Caught a report on Radio 4. The reporter said that when he visited a polling station people were having to mark their ballots on a table in front of officials. No secret ballot and plenty of opportunity for intimidation was his observation.
| 14 June 2009, 12:20 am |
PS, where is Roger Cohen?
Har. He can hardly fail to disappoint, having cut this gem:
One way to look at Iran’s scurrilous anti-Israel tirades is as a provocation to focus people on Israel’s bomb, its 41-year occupation of the West Bank, its Hamas denial, its repetitive use of overwhelming force. Iranian language can be vile, but any Middle East peace — and engagement with Tehran — will have to take account of these points.
http://www.nytimes.com/2009/02/23/opinion/23cohen.html
God bless The New York Times.
| 14 June 2009, 12:39 am |
Hamas denial? What a prick.
| 14 June 2009, 12:40 am |
p.s. My statistical intuitions about that graph were correct mesquito. ;)
| 14 June 2009, 12:42 am |
It may well be the case that some fraud occurred but it wasn’t enough to change the result – indeed I suspected this is what most likely happened. What annoys me, as ever, is you get all these people on the “left” who use the opportunity to reflexively propagandise in favour of Ahmadinejad and against the west. God they are irriating. What about the defeat for the progressive cause in Iran and the fact this will make military action more likely? They don’t don’t give a shit. They just want another pointy finger guy in the middle east who bashes Israel and the US.
| 14 June 2009, 1:41 am |
Cole’s “argument” for a stolen election is a poorly written sketch for a whodunnit. The election may well have been stolen. Then again, the conservative majority in the small towns may have been overlooked by the analysts and wishful thinkers. I don’t know. But Cole’s screed is worthless as a source of information.
| 14 June 2009, 4:46 am |
Neither the proof nor the refutation of fraud are proper statistical analyses. The near-constant ratio between the candidate’s vote totals would make sense only if the votes in each partial result were approximately an representative sample of the total vote. Which would mean that either:
a) Iranian precincts or districts count and report votes at approximately the same rate.
or
b) For each partial result the tallied vote ratios just happen to coincide with those of the complete result, because reporting places which are more pro-opposition than average just happen to balance out pro-government places
or
c) There is a reporting bias, i.e., some kinds of precints/voting sites/districts count and report votes at different rates*, but voting patterns are approximately the same across the country and between cities and countryside.
Now, a) is conceivable in theory, but from what I read reporting was not uniform. b) requires a series of unlikely coincidences, and c) would mean voting patterns have changed significantly (and congruently) between past elections and the last one.
None of this proves fraud, but certainly seem to suggest it. A proper statistical analysis would take as the null hypothesis the non-existence of fraud, and try to quantify how unlikely that would be. It would be virtually impossible to disguise massive fraud from a full statistical analysis of voting patterns, if detailed results were available. For some reason, I suspect they won’t be. But even with coarser data, one could
- Prove or disprove a) by simple inspection of the places included in each partial tally
- Prove or disprove b) by inspecting subtotal in each tally
- Test c) by comparing reported voting patterns (as a function of region, urbanization and whatnot) in this election with those of past elections.
The catch is that, while we can in principle exclude a) and b), we can at most say about c) that ‘Either there was fraud, or voting patterns changes in such-and-such way’. One is then left with the somewhat subjective task of estimating the likelihood of such a change. This is what Iranian experts are for, and this is where the debate should occur. Of course, were we to be told that, for instance, the ratio between Obama and McCain votes wa the same in both Illinois and Arizona, we would be pretty sure there was something wrong with the results. From the fragmentary reports I’ve read, which seem to be based as of yet on very incomplete data, the reported voting patterns in Iran seem equally implausible. We should not rush to judgment, but my preliminary impression is that this election does indeed look fishy.
__________________
* E.g. smaller rural precincts count quicker than big urban ones, or eastern regions count earlier than western because most people vote before sunset
| 14 June 2009, 9:27 am |
What about the defeat for the progressive cause in Iran and the fact this will make military action more likely?
Mike, it is interesting that you say this will make military action “more likely”. Who will initiate military action and why?
Shouldn’t we seperate out the “progressive cause” which is something we all should be behind and “military action” which we should not.
| 14 June 2009, 12:10 pm |
” Cole is no Neocon which makes his position more interesting”.
Yet his analysis is clearly agenda-driven.
Obamas policy of engaging with the Iranian regime rather than
isolate it would lose credibility if the hardliners won a legitimate
landslide victory in an election.
And why is it so unlikely,that Ahmedinejad has won in Tehran?
He is the citys former mayor.
| 14 June 2009, 6:47 pm |
I had a look at the numbers this morning, and they clearly show that they are bogus. Ignore the R^2 value for a moment, you should concentrate on the intercepts.
The plot of totals vs Ahmedinejad and Mousavi is clearly fake; the two lines have the following algorithms:-
Ahmedinejad = ((total-488149)*0.6562)+488149
Where on a spreadsheet the user can change the total and the % support (65.62) for Ahmedinejad.
Mousavi = ((total-488149)*(1-0.6562)-488149
it is quite obvious that the pair of algorithms were designed to be able to provide Ahmedinejad with a 2*(488149) or 976298 vote greater than Mousavi. The planned % to be awarded to Ahmedinejad was probably in the order of 55%.
i.e. with a total of 39,270,000 and a 5% loss to the other two candidates+ spoilt ballots, an input of 55% for Ahmedinejad gives 20,570,000 and 16,830,000.
But they panicked, probably when he only got 30% of the ballots, and gave him 65% instead.
It’s a dictatorship. You can’t tell if elections are free in a dictatorship. You should adopt the principled position of assuming they are fixed unless proven otherwise. No proof has been offered that they were genuine results.