Thursday, 02 September 2010

Pollsters ponder Clinton's New Hampshire surprise

Search for answers as to why pre-election polls ‘failed' to predict Clinton win

US-- Pollsters are today poring over their survey numbers after Hillary Clinton's surprise win in the New Hampshire presidential primary defied their expectations.

Virtually all pre-election polls pointed to a victory for Clinton's Democratic rival Barack Obama, following his triumph in the Iowa vote.

However, the final count yesterday put the former First Lady ahead with 39% to Obama's 36%.

Newspaper headlines were quick to highlight the ‘failures' of the polls; however, experts have called for time to investigate the discrepancies before jumping to conclusions – among them Nancy Mathiowetz, president of the American Association for Public Opinion Research (AAPOR).

Writing on the association's website, she said that while the Clinton numbers were uniformly off, the same polls were “surprisingly accurate” in measuring support for other candidates, including those of the Republican party.

Late deciders; a surge in female support for Clinton following a teary-eyed speech on Monday; and the bi-racial nature of the contest have all been given as possible reasons why the polls failed to reflect the New York senator's final tally.

However, The Huffington Post's Daniel Nichanian writes: “The polls did not get this election wrong because any careful reading of them would have to concede that [Tuesday's] voting looked widely unpredictable.

“The media is now trying to push the responsibility on pollsters, when what is to blame is the way they chose to interpret the surveys and run with the storyline of an unstoppable Obama.”

Both Nichanian and pollster John Zogby said there was movement towards Clinton in surveys conducted the day before the vote – although this would have been missed by most polls released that same day as fieldwork would have been carried out over the weekend.

ABC's director of polling Gary Langer said: “In the end there may be no smoking gun.” He wrote on his blog: “Those polls may have been accurate, but done in by a superior get-out-the-vote effort, or by very late deciders…

“The data may tell us; it may not. What's beyond question is that it is incumbent on us – and particularly on the producers of the New Hampshire pre-election polls – to look at the data, and to look closely, and to do it without prejudging.”

Author: Brian Tarran

Have your say

Please add your comment. You can include links, but HTML is not permitted.
Your email address will not be displayed on the site

Mandatory
Mandatory
Mandatory
Mandatory

Related images