The big betting decision of GE2015 – can we trust the polls?

It’s being reported that the Tories are using John Major’s successful and surprise victory at GE1992 as a model for his party on May 7th. The result from April 1992 will give the blue team hopes of a majority right until the early hours of May 8th 2015.

For GE1992 was the election that the pollsters got wrong and led to big changes in the years that followed

On the Sunday before the election NOP had Labour’s gap at 6% which by the eve of poll had been cut to 3%. ICM by then was down to level-pegging while Gallup found a 0.5% Tory lead – the only pollster to do so in the final week.

What’s amusing when you watch the re-runs of the BBC election results programme is that the whole thing appears to have been set up on the assumption that a Labour victory looked likely.

But by the time all the votes had been counted John Major was returned with an overall majority after the Tories secured a margin of nearly 8% of the GB vote.

The important thing to note is that polling has got more sophisticated since the 1992 disaster with new techniques designed to deal with what appears to have been a systemic bias to Labour.

ICM was the pioneer and became the first to introduce past vote weighting to ensure more politically balanced samples. By GE2005 other pollsters had adopted similar measures and one, NOP, got it spot on.

My reading is that the memory of 1992 will underpin CON hopes right to the end even if the polls remain relatively static.

Mike Smithson

For 11 years viewing politics from OUTSIDE the Westminster bubble

For latest polling and political betting news follow @MSmithsonPB