washingtonpost.com  > Politics > Elections > 2004 Election
Correction to This Article
The number of randomly selected voters who were interviewed Tuesday for the National Election Pool's exit poll was incorrect in an earlier version of this article. The correct number is 13,047.
Exit Polls

New Woes Surface in Use of Estimates

By Richard Morin
Washington Post Staff Writer
Thursday, November 4, 2004; Page A29

An Election Day filled with unexpected twists ended with a familiar question: What went wrong with the network exit polls?

In two previous national elections, the exit polls had behaved badly. Premature calls by the networks in Florida led to a congressional investigation in 2000. Two years later, a computer meltdown resulted in no release of data on Election Day.

On Tuesday, new problems surfaced: a 2 1/2-hour data blackout and samples that at one point or another included too many women, too few Westerners, not enough Republicans and a lead for Democratic presidential nominee John F. Kerry in the national survey that persisted until late in the evening.

In two instances on election night -- the results for Virginia and South Carolina -- the networks held off projecting a winner when voting ended because exit polls showed that the races were too close to call, only to see President Bush win easily in both states.

"The exit polls got it flat wrong," asserted Charles Gibson yesterday on ABC's "Good Morning America."

That is wrong, countered Joe Lenski of Edison Media Research, which conducted Tuesday's exit poll with Mitofsky International for the National Election Pool, a consortium of the major television networks and the Associated Press. "No wrong projections [of winners] were made; the projections were spot on," he said. "The members used this data with sophistication and understanding of what data can and cannot be used for."

Election Day 2004 was a roller-coaster ride for the two presidential candidates and for the political press corps. Successive waves of the national exit poll in the afternoon and evening reported that Kerry had a two- or three-percentage-point lead over Bush nationally and in several key states, including Ohio.

Preliminary exit poll results had leaked throughout the day and were posted on a number of Web sites, including the widely viewed Drudge Report site, which added to the confusion and fanned the media frenzy.

To compound the problem further, a server at Edison/Mitofsky malfunctioned shortly before 11 p.m. The glitch prevented access to any exit poll results until technicians got a backup system operational at 1:33 a.m. yesterday.

The crash occurred barely minutes before the consortium was to update its exit polling with the results of later interviewing that found Bush with a one-point lead. Instead, journalists were left relying on preliminary exit poll results released at 8:15 p.m., which still showed Kerry ahead by three percentage points.

It was only after the polls had closed in most states and the vote count was well underway in the East that it became clear that Bush was in a stronger position in several key battlegrounds, including Ohio, than early exit polls suggested.

Some problems are inevitable. A total of 13,047 randomly selected voters were interviewed Tuesday as they left their polling places, and those results were fed into computers. The accumulated results were reported several times over the course of Election Day.

Results based on the first few rounds of interviewing are usually only approximations of the final vote. Printouts warn that estimates of each candidate's support are unreliable and not for on-air use. Those estimates are untrustworthy because people who vote earlier in the day tend to be different from those who vote in the middle of the day or the evening. For instance, the early national sample Tuesday that was 59 percent female probably reflected that more women vote in the day than the evening.

That is why the early leaks anger Lenski. "The basic issue here is the leaking of this information without any sophisticated understanding or analysis, in a way that makes it look inaccurate," he said.

After the survey is completed and the votes are counted, the exit poll results are adjusted to reflect the actual vote, which in theory improves the accuracy of all the exit poll results, including the breakdown of the vote by age, gender and other characteristics.

© 2004 The Washington Post Company