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

[cafiorello.livejournal.com]

Sheesh. Just raising the question that something seems odd, and doing statistical analyses (which, BTW, if you don't have the statistics training to figure out yourself, you don't have the statistics training to classify as half-assed), is not libel, sleazy, or swiftboating. Did you read the original articles? Generally everyone, solarbird included, is saying "we don't know what this means." Hell, the one voter fraud claim I've seen is the speculation that the Repubs did it on purpose to make Clinton look bad--nobody I have seen has claimed that Clinton did it. Yeah, there might well be another confounding variable, but knowledgeable people keep pointing out possible ones, they redo the analyses, and the results continue to be anomalous. NOT evidence of fraud, but anomalous.

Cathy

[llachglin.livejournal.com]

I'm classifying them as half-assed because the person doing them admits to not being a statistician, because statisticians have pointed out that you can't jump to conclusions in cases like this because you can't identify all of the relevant factors, and because there's literally ZERO corroborating evidence for the outlandish claims of the electoral fraud theorists.

For the record (and as I've already stated), I support an audit of the discrepancy. What I dismiss is the tone of people, typically Obama supporters or Hillary haters or both, who assume that a discrepancy is evidence of fraud and perpetuate a slander against the Clinton campaign just because they don't like her. I am an Edwards supporter who agrees more with Kucinich on matters of policy than with any other Democrat. I like Obama's style and politics, but the messianic fervor of many of his supporters and their willingness to engage in slurs against Clinton over stuff like this is leading me to consider supporting her over him if it comes down to that choice. (Right now, in part because of the tone of his campaigning in the last couple of days, Obama still has the edge over Clinton for me.) And as a Democrat who genuinely likes all candidates running and wants to defeat the Republicans, I have a real problem with slander of any of them. There's lots about Clinton that's worthy of withering criticism, so it's a shame that something like this is getting so much attention.

Most of the slander is coming from Clinton's political opponents, but I detected a whiff of it in solarbird's original post at http://solarbird.livejournal.com/594810.html.