|Proportion who did what they said
New study looks at what went wrong
As we all know the 2010 general election wasn’t a good one for the pollsters. The Lib Dems were very much over-stated with the Tories, and to a much greater extent, Labour being under-stated.
The one bright spot was the remarkable success of the exit poll which for the second election running got the leading party seat total precisely right.
On the Research site the leading political scientist and chair of the British Polling Council, Professor John Curtice and ICM boss Martin Boon have just published a study.
A key part was going back to those who had been questioned in the final ICM poll and asking what they had actually done. The table above was the outcome.
So this may explain a little but ICM found that “those who switched to the Liberal Democrats at the last minute almost equalled those who defected.”
Another suggested issue, differential turnout, which nearly all polls tried to take account, seemed, according to the study, to have been relatively unimportant. “Liberal Democrat supporters were no more likely to stay at home than their Labour counterparts.”
A key element was what been described in the past the â€˜Shy Tory syndromeâ€™. That is the “differential failure to declare their voting intention by those who in the event vote for one party rather than another, perhaps because they feel that their choice of party is currently unfashionable.”
Curtice and Boon write: “The inquest into the 1992 debacle suggested that a reluctance by those who eventually voted Conservative to declare their intentions in advance helped explain the failure of the polls on that occasion. This time it seems to have been voting Labour that was regarded as unfashionable. In 2010 no fewer than one in five of those who actually voted failed to declare their voting intention when interviewed by ICM for its final poll â€“ and they were nearly twice as likely to vote Labour as Liberal Democrat…”
No doubt ICM and others will be looking at ways of dealing with this in the future.
What the study doesn’t cover is the the differential performance between the various forms of polling as shown in the 2010 PB polling accuracy league table.
Five of the top six pollsters carried out their surveys by phone. Five of the bottom six carried them out online. You would have thought that the “shy Labourite” notion would have been less relevant when respondents are filling in an online questionnaire.