USCountVotes, a nonpartisan scientific research project, issued a statement Monday critical of exit pollsters Edison and Mitofsky’s Jan. 19 report attributing differences between exit poll and election results to possible survey-response rates of Republicans and Democrats.
The researchers say the data does not support such a hypothesis but actually suggests the contrary. The USCountVotes team writes that Edison/Mitofsky assert the “disparity was ‘most likely due to Kerry voters participating in the exit polls at a higher rate than Bush voters’, but no evidence is offered to support this conclusion. In fact, data newly released in the report suggests that Bush supporters might have been over represented in the exit polls, widening the disparity to be explained. The report gives no consideration to alternative explanations involving election irregularities.”
The USCountVotes team faults Edison Media Research and Mitofsky International for failing even to explore the possibility that the election results were faulty, instead focussing only on hypotheses about why the exit polls might have been in “error.” Furthermore, the Edison/Mitofsky report elides from hypothesis to assertion of fact, without the benefit of confirming data.
Edison/Mitofsky are quoted as saying, “While we cannot measure the completion rate by Democratic and Republican voters, hypothetical completion rates of 56 percent among Kerry voters and 50 percent among Bush voters overall would account for the entire Within Precinct Error that we observed in 2004.”
(Within Precinct Error is defined as “an average of the difference between the percentage margin between the leading candidates in the exit poll and the actual vote for all sample precincts in a state.”)
However, this hypothesis is treated as fact on page four of Edison and Mitofsky’s Executive Summary, “It is difficult to pinpoint precisely the reasons that, in general Kerry voters were more likely to participate in the exit polls than Bush voters.” The hypothesis has morphed into asserted reality.
Edison/Mitofsky acknowledge that the differences between the exit polls and the election results are far greater than can be explained by statistical sampling error. The USCountVotes authors write, “Seven of the 50 states . . . had less than 1 percent probability of having the reported difference between exit polls and election results occurring by chance.”
According to the authors, the probability is one in 10,000,000 that seven of 50 states would have such results in the same election.
“The many anecdotal reports of voting irregularities create a context in which the possibility that the overall vote count was substantially corrupted must be taken seriously,” the report concludes.
USCountVotes is creating and analyzing a database containing precinct-level election results for the entire United States in order to do a thorough mathematical analysis of the 2004 election results.
The full text of the USCountVotes statement is available at www.uscountvotes.org/ucvAnalysis/US/USCountVotes_Re_Mitofsky-Edison.pdf
The full text of the Edison/Mitofsky report is available at www.exit-poll.net/election-night/EvaluationJan192005.pdf
Judy Bertelsen is co-chair of the Voting Rights Task Force, Wellstone Democratic Renewal Club