It looks like you're using an Ad Blocker.

Please white-list or disable in your ad-blocking tool.

Thank you.


Some features of ATS will be disabled while you continue to use an ad-blocker.


(politics) Pollsters Can't Agree

page: 1

log in


posted on Oct, 18 2004 @ 10:35 PM
Pollsters continue to make inconsistent predictions as to which candidate is leading and by how much. The tighter the race gets, the less reliable polling interpretation seems to get. Pollsters seem to be engaging in more art than science in their selection of interpretive tools and crunching of formulae.

ASHINGTON, Oct. 18-What is going to happen on Election Day? It depends on which pollster you ask.

President Bush leads Senator John Kerry by a margin of eight points among likely voters, according to the most recent poll from Gallup, USA Today and CNN. The margin of sampling error was four points.

But wait: Mr. Bush is up by only three points in the latest tracking poll from ABC News and The Washington Post, although with a margin of error of three percentage points.

Not so fast: The race is actually roughly even, according to the latest New York Times/CBS News Poll. And Time magazine's new poll says much the same thing.

But while the headlines they produce may diverge, the actual findings of these polls may not be so different. The differing conclusions reflect how different pollsters use complex formulas to interpret very similar findings among self-described registered voters and try to come up with a result they think best accounts for who will actually show up at the polls.

The different interpretations have drawn a litany of complaints from partisans on both sides. Some are questioning everything about the surveys, including pollsters' political motives, their methodologies and whether accurate polling can be done in the age of cellular phones that cannot be called and caller ID systems that make screening out unfamiliar numbers easy.

Please visit the link provided for the complete story.

While there seems to be a developing consensus that Bush will prevail, it seems that this is a reading of the "collective gut-feel" rather than scientifically validated interpretation. Valid science needs to be widely accepted and peer reviewed, repeatable to the same results, and based on a known error that is factored out. While the polling itself may manage to meet the tests of reliability, the art of interpretation may bear as close a relationship to science as astrology does to astronomy.

All we can reasonably say is that it is a close race.

Related News Links:

Related Discussion Threads:
POLITICS: Bush Opens 4 Point Lead In latest Reuters/Zogby Poll
Lies, Damned Lies, Statistics & 2004 Campaign Polls

[edit on 18-10-2004 by G_Scard]

[edit on 18-10-2004 by G_Scard]


log in