Political polls mean diddly squat

[no name 1]

When a Poll Changes the Way People Think About the Race

By JANET ELDER

Published: November 28, 2007

It was inevitable. A poll comes out and it dominates the news and changes the way people are thinking about the campaign. That’s just what happened last week when ABC News and the Washington Post released a poll of Iowa caucus goers.

While the authors of the poll from the two media organizations chose words like “close” to describe the race, others had a different take. Words like “surge” were being used and Barack Obama was suddenly thought to be the “front-runner” for the Democratic nomination in Iowa.

The poll even showed up in a New York magazine column about the holiday season. They never mentioned who did the poll but wrote: “Barack Obama sledded ahead of Hillary Clinton in the latest Iowa poll, while Hillary Clinton settled for the Democratic equivalent of coal in her stocking.”

That was pretty much the news story last week, “Barack Obama sledded ahead.” But he didn’t “sled ahead.” The poll actually found the race to be close, with results similar to those found a week earlier by The New York Times and CBS News when they polled Iowa, and another by KCCI-TV. The Washington Post headline on the poll story read: “For Democrats, Iowa Still Up for Grabs.”

On the face of it though, the ABC/Washington Post numbers looked dramatic — and they were portrayed dramatically, too, as they often are by the news media.

When asked whom they would vote for if the Democratic caucus were held today, 30 percent of likely Iowa Democratic caucus goers said Barack Obama, 26 percent said Hillary Clinton, 22 percent said John Edwards and 11 percent said Bill Richardson. Support for the other candidates was in single digits.

The poll’s margin of sampling error is plus or minus five percentage points. That is five percentage points on each number. That means support for Mr. Obama could be as low as 25 percent, and support for Mrs. Clinton could be as high as 31 percent.

In theory, when a poll says 40 percent, with a 3 percentage point margin of sampling error, that means that 19 times out of 20, the number would be between 37 and 43 if you interviewed every adult American. But it’s a bell curve. So 40 is the most likely number. Thirty-nine and forty-one are a little less likely. Thirty-eight and 42 are even less likely than 39 and 41. And 37 and 43 are still less likely.

News organizations differ on how strictly to apply the margin of sampling error. But when looking at horse race numbers in a political poll, particularly in Iowa, with its quirky caucus system, historically low turnout (5 percent of Iowans participated in the Democratic caucus in 2004) and rules that change from one year to the next — this year Iowans can register to vote at the door on caucus night — the margin of sampling error is probably best applied in its strictest sense.

Gary Langer, the director of the ABC News poll who has made adhering to polling standards something of a crusade, said: “You’re never going to get a significant lead unless it’s a blow out.”

source

Edited November 28, 2007 by devilette

[Ban Hammer 14,690]

“You’re never going to get a significant lead unless it’s a blow out.”[/i]

so the clinton family has this one wrapped up again eh?

[no name 1]

“You’re never going to get a significant lead unless it’s a blow out.”[/i]

so the clinton family has this one wrapped up again eh?

[Fandango 1,440]

Is that for all polls, or just the ones that show Hill losing?

[Ban Hammer 14,690]

“You’re never going to get a significant lead unless it’s a blow out.”[/i]

so the clinton family has this one wrapped up again eh?

[no name 1]

Is that for all polls, or just the ones that show Hill losing?

All. I'm sick of them. 5, or even 10 points +/- is nothing.