« | »

WP: Polls Have To Be 4% Off For Romney Win

From the Washington Post:

Polls would have to be wrong by four points for Romney to win

by Dylan Matthews | Mon November 5, 2012

“The only poll that matters is on election day,” goes the old cliché. It’s a reassuring sentiment for Mitt Romney supporters, given that recent polling shows their candidate running behind in many key swing states. And there’s a kernel of truth to it: There’s absolutely a chance the polls are all wrong.

But just how wrong would current polls have to be for Romney to win the election? Robert Erikson, a prominent forecasting specialist at Columbia, and his colleague Karl Sigman did the math. They estimate that if the current polls are correct, Obama has a 99.9 percent chance of winning…

But what happens if the polls are wrong, and biased (in the statistical sense, not the ideological sense) in Obama’s favor? If they’re two points too favorable to Obama, Erikson and Sigman estimate that there’s still an 65.9 percent chance Obama wins; if they’re four points off, there’s a 1.7 percent chance he wins, making a Romney win a near certainty…

And isn’t it amazing. But somehow almost all of the polls always oversample Democrats by at least 4%. Including, the latest and last Washington Post/ABC News poll, which oversampled Democrats by 6%, just to be on the safe side. (Dem/Rep/Ind = 35/29/32%.)

From the Washington Post:

WaPo-ABC tracking poll: final weekend tally is Obama 50, Romney 47, still a ‘margin of error’ contest

By Jon Cohen, Peyton M. Craighill and Scott Clement | Mon November 5, 2012

Heading into Election Day, likely voters divide 50 percent for President Obama and 47 percent for his challenger, Republican Mitt Romney, according to the latest, final weekend release of the Washington Post-ABC News tracking poll…

Nobody can deny that the DNC’s hometown paper, the Washington Post isn’t giving its all for the cause. (As well as any credibility they might still enjoy.)

A nail-biter throughout, the presidential contest remains closely competitive through its last days, even as most voters perceive a likely win for the president.

Because the news media has beaten this into their heads for at least 17 months.

In regular polls since early July, neither candidate ever gathered more than 50 percent of likely voters, and neither ever slipped below 46 percent. Across nearly 7,000 interviews with likely voters from Oct. 18 through Sunday evening, less than four-tenths of a percentage point separates Obama and Romney…

No matter how outrageously they oversampled Democrats. Which is pretty telling, when you think about it.

(Again, they oversampled them by 6% for their final poll: Dem/Rep/Ind = 35/29/32%.)

The difference between the candidates in the final weekend tally is right at the 2.5 percentage margin of sampling error for the final four-night sample of 2,345 likely voters. This makes Obama’s being at plus three points over Romney an edge only by the slimmest of margins, well below conventional measures of statistical significance…

Er, if Obama’s lead is within the 2.5% margin of error, how is he leading by "plus three points"?

Still, hitting 50 percent is a first for Obama since the poll in early July, with Sunday interviews marking Obama’s single best day of the tracking poll…

Imagine that! What are the odds!

Just over 10 days ago, the tracking poll see-sawed in Romney’s direction by the same, slender 50 to 47 percent.

For the record, that poll ten days ago ‘only’ oversampled Democrats among likely voters by 4%. Dem/Rep/Ind = 34/30/31%.

It is clearer that the president made progress in other areas. He has re-gained an advantage when it comes to understanding the economic problems people are having in the country, and, over the final week, has drawn back to running evenly with Romney in voter trust to handle job No. 1: the economy.

Because the economy is so much better now than it was 10 days ago.

Obama has also closed the gap among white voters, inching back above the 40 percent threshold some analysts see as critical to his reelection. In the final days, white voters divide 56 percent for Romney, 41 percent for Obama. More than three-quarters of non-whites, 76 percent, back Obama, 20 percent side with Romney.

The president has also neutralized Romney’s previously large advantage among political independents. Independents divide 48 percent for Romney to 46 percent for Obama; Romney’s advantage had peaked at 58 to 38 percent 10 days ago.

In other words, 18% of Independents have swung over to Obama in just the last 10 days. Which is simply preposterous.

This article was posted by Steve Gilbert on Tuesday, November 6th, 2012. Comments are currently closed.

One Response to “WP: Polls Have To Be 4% Off For Romney Win”

  1. geronl

    Gallup and Rasmussen say Romney is ahead by 1%


« Front Page | To Top
« | »