Let's review:
Message 20721478
Any questions?
:-)
e
*****
Exit polls most inaccurate since 1988
Thu Jan 20, 6:29 AM ET
USATODAY.com
by Mark Memmott, USA TODAY
The exit polls of voters on Election Day so overstated Sen. John Kerry's support that they rank as the most inaccurate in a presidential election since at least 1988, the firms who did the work conceded Wednesday.
One reason the surveys were skewed, they say, was because Kerry's supporters were more willing to participate than Bush's. Also, they say the interviewers they hired to quiz voters were on average too young, too inexperienced and needed more training.
The exit polls, which are supposed to help the major TV networks shape their coverage on election night, were sharply criticized after the election. Leaks of preliminary data from the polls showed up on the Internet in the early afternoon of Election Day, fueling speculation that Kerry was about to defeat President Bush. After the election, some political scientists, pollsters and journalists questioned the polls' value.
To curb leaks in the future, news organizations have agreed to withhold distribution of the poll information within their businesses until later in the day, instead of releasing data earlier in the cycle.
In a report to the six media companies that paid them to conduct the voter surveys, pollsters Warren Mitofsky and Joseph Lenski, whose firms did the work, said on average, the results from each precinct overstated the Kerry-Bush difference by 6.5 percentage points. "This is the largest we have observed on a national level in the last five presidential elections," they said.
Lenski said Wednesday that issuing the report was something like "hanging out your dirty underwear. You hope it's cleaner than people expected."
Among their findings:
• Their firms hired too many relatively young adults to conduct interviews of voters as they left polling places on Election Day. Half of the 1,400 interviewers were under the age of 35. That may explain in part why Kerry voters were more inclined to participate, since he drew more of the youth vote than did Bush. But Mitofsky and Lenski also found younger interviewers were more apt to make mistakes or not follow procedures than older peers.
• Early results were skewed by a "programming error" that led to including too many women voters. Since women voted for Kerry in larger numbers than Bush, that affected the exit poll analysis.
• In many locations, local officials prevented interviewers from getting close enough to consistently catch voters.
For future exit polls, Lenski and Mitofsky recommended better training and more monitoring of interviewers, the hiring of more experienced polltakers and "working to improve cooperation with state and local election officials."
Lenski said raising the level of voter participation would reduce errors in the future. Just 53% of those asked to complete a questionnaire did so in 2004, similar to past exit polls.
Lenski and Mitofsky noted that none of the media companies that paid for the exit poll data - ABC, CBS, CNN, Fox News, NBC and The Associated Press - made any wrong "calls" on election night. Edie Emery, spokeswoman for the six media companies, issued a statement on their behalf saying they are "pleased to see that steps are being taken to address this."
story.news.yahoo.com |
