|
Bush gaining 4 percent in exit polling states impossible Original Source Link: (May no longer be active)
http://www.bluelemur.com/index.php?p=405http://www.bluelemur.com/index.php?p=405
11/8/2004
Odds of Bush gaining by 4 percent in all exit polling states 1 in 50,000; Evoting/paper variance not found to be significant
Filed under: General— site admin @ 3:07 pm Email This
By John Byrne | RAW STORY Editor
A statistical analysis of exit polling conducted for RAW STORY by a former MIT mathematics professor has found the odds of Bush making an average gain of 4.15 percent among all 16 states included in the media’s 4 p.m. exit polling is 1 in 50,000, or .002 percent.
The analysis, conducted by former Associate Professor of Mathematics David Anick, also ruled out any significance of a variance between electronic balloting and paper ballot states, which RAW STORY reported last week.
In fact, the non-electronic voting states of New York and New Hampshire had higher gains for President Bush than states in the exit polls using some electronic balloting: Arkansas, Colorado, Florida, Iowa, Ohio, New Jersey, New Mexico, Nevada and West Virginia.
Moreover, the analysis found that states using optical scan technology to read paper ballots were not more likely to have exit poll variance than other states. Because New York, which uses lever balloting, had such a large variance, the optical scan variance is within the threshold of being statistically explained by chance.
In part, the discrepancy in the site’s earlier reporting came from the fact that New Hampshire and New York were not included in the reported 6 p.m. polling. Both states had the greatest “Bush gains,” by 8.7 and 8.6 percent respectively, and both use non-electronic balloting. The full breakdown of states by electronic and paper balloting can be found here.
Many of the states, however, including crucial swing states like Florida, Ohio and New Hampshire use optical scan technology which “counts” the paper ballots. Since these systems use Windows machines and a simple database (many of which are connected by modems to a central tabulator), these states are subject to hacking as well.
The site chose to use the 4 p.m. exit polling because it polled the largest number of states, which would provide a larger sample. The National Election Pool refuses to release any of their exit polling on any other states, or to break it down by county, without being paid.
On average, Bush made a gain of 4.15 percent when the reported vote was tallied in all sixteen states included in the reported 4 p.m. exit polling conducted by the National Election Pool.
The gain was calculated by taking the difference between Kerry and Bush in the exit poll and comparing it with the difference between Kerry and Bush in the reported vote.
Anick reasons that there are four possible causes of the “Bush gains.” (1) Significantly greater lying or refusal to speak to pollsters in Bush voters versus Kerry voters; (2) Consistent/systematic errors in weighting demographic groups; (3) A surge of Bush voters after 4 p.m., in all states; (4) Systematic tampering/hacking of reported vote totals, in Bush’s favor.
One reason suggested for the anomaly system-wide was that women were oversampled in the exit polling; women favored Kerry by a slight margin. For this to be true, women would have had to have been significantly oversampled in all 16 states. The largest oversampling seen in any state was 54-46 women-men, in one Florida exit poll. That poll suggested a Kerry victory in the state 51-49 percent.
In no state did Bush have a loss. Bush’s support in the reported vote tallies went up in every single state compared with the exit polling.
The Pool conducts exit polling paid for by the Associated Press and five television networks, which is used in part for calling winners.
Besides New Hampshire and New York, Bush also made sizable gains in Florida, 7.0 percent, Pennsylvania, 4.8 percent, and Colorado, 4.6 percent.
Exit polling is used in many foreign countries to determine the legitimacy of the reported results; some note that in the American situation, however, the variance is not of the size at which foreign observers would question an election.
RAW STORY and Dr. Anick have called for the release of the full exit polling for all states by county. No real conclusion can be drawn without all the data, and county by county exit polling would be the best means for examining claims of fraud.
The National Election Pool’s spokesman, at CBS News, has not returned repeated calls for comment.
|
|
