line -->
  • Thursday, January 20, 2005


    Still Analyzing Those Pesky Exit Polls

    The following quote is from an article apparently defending an analysis of the exit poll numbers from the 2004 election. I've said it before but it deserves restating: Exit polls on election day are much more accurate than other types of polls. Pollsters do not have to compensate for "likely voter" stuff. The following is from Stolen or Lost? by Steven F. Freeman:
    Editor's Note: This is in response to Russ Baker's "Election 2004: Stolen or Lost," originally posted on

    Baker dismisses the validity of exit polls, but prominent survey researchers (e.g., Asner 1999, Cantril 1991:142), political scientists (e.g., Edwards & Wayne 1999:84), and journalists (e.g., Jurkowitz 2000) concur that they are highly reliable. As far back as 1987, political columnist David Broder wrote that exit polls "are the most useful analytic tool developed in my working life" (1987:253). Edwards & Wayne (1999:84) caution only that, "... the problem with exit polls lies in their accuracy (rather than inaccuracy). They give the press access to predict the outcome before the elections have been concluded."

    An exit pollster himself for over 20 years, Saint Louis University professor of political science Ken Warren (2003) has never had an error greater than 2 percent, except one time – in a 1982 St. Louis primary. In that election, massive voter fraud was subsequently uncovered...

    Temple University professor of mathematics John Allen Paulos wrote in a column in the Philadelphia Inquirer that "huge differences between the final tallies and the exit poll percentages occurred in 10 of the 11 battleground states, all of them in Bush's favor. If the people sampled in the exit polls were a random sample of voters, Freeman's standard statistical techniques show that these large discrepancies are way, way beyond the margins of error."...

    Because of their reliability, exit polls are used to verify elections around the world. When exit polls deviated from the official count in Serbia and the former Soviet Republics of Belarus, Georgia and the Ukraine; the world – led by the U.S. – accepted exit poll numbers over the official count, and in three of these nations, the election results were successfully overturned...

    Lack of election transparency, alas, also plagues our exit polls. Baker's unnamed source comments, "To say you want the raw data is ludicrous ... ," but elsewhere in the world, exit poll data are released as soon as voting ends. Here in the U.S., the media consortium's exit poll data were promptly corrected to conform to the count, leaving no public record of the original projections. Two and a half months after the election, despite all the questions surrounding its integrity – and the integrity of NEP – we're still waiting for these data.

    In his parting shot, Baker writes, "Half-baked conspiracy theories are damaging to the public confidence in democracy." One can understand why incumbent politicians would try to dismiss threatening thought as "conspiracy theory," but a serious journalist would not use pejorative labels so as to avoid engaging in the merits of a discussion.

    Scrutiny of an election with many unanswered questions does not damage public confidence in the democracy; absence of scrutiny does.

    << Home

    This page is powered by Blogger. Isn't yours?