Controlled for demographics, the voting anomaly continues to be present

[solarbird]

People at ScienceBlog and a variety of other statistics-literate sources have been doing demographic analysis on the unpredicted/unpolled Clinton/Obama vote swings in machine-counted vs. hand-counted balloting in Vermont. Controlling for a large number of demographic variables - including such outliers as geography - the variation against polling and against hand-counted ballot remains pretty constant. The calculated statistical probability of this being a random effect is p<.001, which is to say, around 1000:1 against. Further analysis is ongoing.

I would like to see similar analysis applied to the Romney surge, which appears to be comparable at the top level.

ETA: I was in a hurry before and forgot to credit cafiorello for the link. Thanks!

Comments

[llachglin.livejournal.com]

I don't want to turn away from anomaly. The vote should be audited.

What I have a problem with is excitable language like "horrified," " desperately stupid," "sloppy," "rage," and "disaster" used to describe a statistical anomaly that without corroborating evidence of fraud is nothing more than a mathematical curiosity (these were all in solarbird's original post about this on 1/9, and are mild compared to what people were saying in other places where this story was being propagated). I also think it's irresponsible to pass on information from Andrew Sullivan without pointing out that he has a well-known grudge against the Clintons.

[solarbird]

I stand by horrified. If the electoral system is fucked up, and there's any whiff of it, that should be horrifying. A rigged election would be a disaster, and rage is the right tag for something like that, as far as I'm concerned. Why do you think I was posting asking for another explanation? Because these numbers are statistically meaningful (and btw, the original exit polling put the "undecided" vote as split between Obama and Clinton, not going almost entirely to Senator Clinton as you propose) and looking at what the numbers say has historically been really, really illuminating in my historical experience.

On the other hand, slapping me with the use of "desperately stupid" and "sloppy" when I was using those as words to describe why it's UNLIKELY Senator Clinton did something crooked is Not Fair Play as evidence for accusations of slander at me.

[llachglin.livejournal.com]

FYI, the recount was completely on Monday and there was no fraud: http://www.dailykos.com/storyonly/2008/1/21/83051/3514/129/440226 (which has links to the official NH recount results). I'm posting here because it missed my attention until now (in a story about Kucinich dropping out today) and I haven't seen anything from you on this, so I figured you missed it too.

By the way, in regard to quoting some of your language, I wasn't intending to make a personal attack but just trying to point out why to me your post read as accusing, even if that's not what you intended. There seemed to be an implicit bias toward the possibility of fraud being real, despite a complete lack of evidence, and even though your language was conditional it still ended up characterizing the Clinton campaign for something there was no evidence had happened, and which we now know did not happen, at all. There's enough actually wrong with Clinton's substantial positions and campaign that there's no need to raise the alarm about things that didn't happen. The general tone of the campaign has really devolved over the last month, and I really wish we could stay focused on substance rather than rumor, mudslinging, accusations, and counter-accusations.

[solarbird]

Yeah, I'd been following it on the Secretary of State page (tho' hadn't seen a final tally yet, I've been busy), and also, this paper provided a rational possibility for why there would be a non-demographically-visible difference. (Picosummary: Boston exurbs were more likely to vote for Clinton than Obama. They're also (for unknown reasons) more likely to have machine-counted ballots.) So that's good.

What's new since I lived there is the rest of the state having demographics comparable to the Boston-exurb areas. (Which, apparently, it does.) Either I was wrong about that at the time, or that's a significant shift.