Wednesday, June 07, 2006

More Manjoo Fallacies and Lack of Comprehension

This was posted June 7, 2006 on Salon.

In his June 7, 2006 reply to Kennedy’s rebuttal of his earlier critique Farhad Manjoo citing Mark Blumenthal, claims that:

a) The exit poll margins of error for Iowa, Nevada, New Mexico, and Ohio were between 5% to 7%. This is preposterous. Rather than relying on Mark Blumenthal (an unreliable source for quantitative analysis), I urge Manjoo to download the National Election Pool a “Methods Statement” for the Edison Mitofsky (EM) exit polls (produced on Nov. 2 2006) at:

The second page of this statement sets 95% confidence intervals for these polls (for a “characteristic” held by roughly 50% of those polled, for example a Presidential candidate preference for which there is a close to even split) squarely at 4% for sample sizes of 951-2350 – the range of reported sample sizes for these states. However, as Blumenthal knows, the reported sample sizes (also in the methods statements) are about half of what they really are (see Mitofsky correspondence in Baiman June 5 Free Press AAPOR report). For these true doubled sample sizes of 2351-5250, NEP’s own estimated confidence interval falls to 3%. This clearly puts the Ohio discrepancy of about 4% outside of the margin of error - even using NEP's inflated margins of error.

My margin of error calculations (and I believe Freeman’s) find a 2% margin of error with a 30% cluster adjustment factor. As I have stated in my earlier response to Manjoo, this puts Ohio well outside the margin of sampling error with odds of less than 1,900 that Kerry’s reported result is true given the exit poll result. This is not “slight” evidence but rather highly statistically significant, especially one considered with the inexplicable pro-Bush exit poll discrepancies in the two other key battle ground states of Florida and Pennsylvania. As Freeman and I have stated, the odds that these “sampling errors” (in the same direction and of these magnitudes) would occur for these three states simultaneously in less than one in 182,000,000 (i.e virtually impossible - this number is based on doubled sample sizes). Moreover, when one looks at precinct level exit poll data , and not just aggregate state polls, the evidence in even more striking and inexplicable. A fact that Manjoo has not addressed at all.

The question that has to be asked is why are Manjoo (and Blumenthal) trying to dismiss the statistical significance of the exit poll discrepancies when even Mitofsky (in his January report) concedes that they were the largest on record and highly statistically significant?

b) Manjoo’s efforts to dismiss what he calls the “purported rural vote shift” is even more outlandish. As Kennedy points out he doesn’t seem to understand the difference between a popular incumbent who earned more votes statewide than Gore in 2000 and a former Republican judge from Cincinnati who got a “favored son” boost in that region; and an unknown, under funded, very liberal judge from Cleveland, who got 24% less votes than Kerry statewide, inexplicably getting more votes that Kerry in 12 of the most conservative counties (judging by their Bush vote shares) in Ohio!

Moreover, these same 12 counties just happen to be among the only 14 (out of 88 counties) where Bush’s vote is larger than Moyer’s (the incumbent conservative judge) by more than 43%. Moreover, the amount of “excess Bush” vote (more than Bush’s state average of 21% more than Moyer) just happens to roughly match both by county and for entire state the “lost Kerry” vote (what Kerry would have gotten if he had received his state average of 32% more votes than Connally in these counties) without any overall substitution from Moyer to Connally (Moyer’s vote is larger than the state average and Connally’s is smaller than the state average in all but one of these 12 counties).

Farhad, do you understand how absolutely remarkable such a series of “coincidences” is?!!

I challenge you or anyone else to provide a plausible non-vote shifting explanation for these patterns.

Note that the Bush to Moyer ratio is independent of the Kerry to Connally ratio when there is no substitution between Moyer and Connally. It is simply impossible to understand why, out of all the 88 counties, 9 out of 14 cases where Bush does extraordinarily well relative to Moyer, just happen to be in the same counties where Connally does extraordinarily well relative to Kerry?!!!! And it is even more impossible to understand why the relative magnitudes of these impossible undercounts for Kerry and over counts for Bush should so closely match!!!!

I would take this evidence to a trial. Clearly a crime was committed in Ohio. There is simply no other explanation for these patterns other than vote shifting. The only thing we don’t know is who did it and how. And exactly this kind of information is necessary to get serious electoral reform - that you claim to support.


Post a Comment

<< Home