Why were the polls so wrong?

Latest analysis from the British Election Survey on why the opinion polls were up the creek can be read here.

They think the explanation had less to do with "Shy Tories" and more to do with the polling companies not estimating correctly what proportion of people would vote.

The conclusion reads:

"Our analysis of the post-election BES data makes us much more sceptical about late swing, “don’t knows” and Shy Tories. By contrast, we are leaning strongly towards differential turnout as part of the explanation and think that it’s likely that sampling and weighting also played at least some role."

Which roughly translates as

"There was a problem with people lying to pollsters, but it wasn't so much Tories lying to the pollsters about being Tories as people who described themselves as Labour voters not being honest enough to admit to admit they were too lazy to vote."

Comments

Jim said…
I told you the election results, and I told you them a month before they happened. I told you Greece would not leave the Euro, and against the odds I got that too. Now just stop it, I will tell you something for nothing, the pro pollsters are lost, they have forgotten the basics of keeping the ear to the ground in a changing world.

You will find the answer on facebook and twitter before you find it in the polls.
Chris Whiteside said…
Stop what, Jim ?

Agree with you absolutely in that the facts demonstrate something is badly wrong with the assumptions and methods used by opinion pollsters, and a wise person will not trust anything they say until they have demonstrated that they have learned from their mistakes and corrected them.

Which is not to say that attempts to work out what they were doing wrong - like the BES paper I linked to - are of no value.

I presume when you say that "you will find the answer on facebook and twitter before you find it in the polls" you mean don't trust any of them?
Jim said…
Sorry, my wording there was terrible. It was not you i was saying stop it to. it was the pollsters and the media hacks. They honestly may as well go home. You got it, my comparison to twitter and facebook was to show that i trust the pollsters about as much as I would trust a facebook status, which is not very much.
Chris Whiteside said…
Thanks for clarifying that, Jim, I thought that was what you meant but wanted to check. :-)

Popular posts from this blog

Nick Herbert on his visit to flood hit areas of Cumbria

Quotes of the day 19th August 2020

Quote of the day 24th July 2020