I thought I had put this baby to bed, but Stefan has updated his intentionally muddled rebuttal on Sound Politics, and, well… I wasn’t raised in a family that easily tolerates letting somebody else get in the last word.
Amongst other things, Stefan writes:
Statistics is the science of drawing inferences from the kind of messy data about real-world phenomena that David can only call “garbage”. Let’s have a real discussion of the statistical issues here.
The problem is, you can “statistically” prove anything you damn well please if you make the appropriate assumptions, and Stefan’s analysis is based on a faulty one:
If we make the reasonable approximating assumption that the percentage of votes given to Rossi in a count is a normal random variable, we can use statistics to calculate the odds that Rossi truly won more than 50%.
But the CalTech/MIT studies clearly state that variation in results from one count to then next is not simply random: recounts are more accurate.
Tabulations may change from the initial count to the recount for a variety of reasons: ballots may be mishandled; machines may have difficulty reading markings; people and machines may make tabulation errors. Because recounts are used to certify the vote, greater effort is taken to arrive at the most accurate accounting of the ballots cast. The initial count of ballots, then is treated as a preliminary count, and the recount as the official.
I am loathe to continue disputing Stefan’s “statistics” because that is exactly what he wants — it is nothing more than a well-worn rhetorical device intended to distract readers from our only substantive point of disagreement: are recounts legitimate? CalTech/MIT clearly says “yes,” but the reason Stefan won’t concede on this issue is that if Gregoire ultimately wins — in a very legal, if statistically insignificant way — Stefan and his sour band of neocons will continue to argue that her governorship is illegitimate.
His Tourettes-like spouting of Excel functions aside (not to mention his cowardly, dismissive, dishonest, and OCD-like focus on the definition of “statistical tie”), I think it is fair to say that Stefan and I agree that we will not come out of this election with confidence that we have accurately measured the will of the people. (And let’s not start a bullshit debate over “accuracy” versus “precision.”)
His notion that Rossi will be the statistical winner, whatever the outcome of the hand recount, is based on rhetorical convenience, not statistics.