New design
As you'll have noticed if you are reading this on the site (if you've got it in an RSS feed you'll just have to come here, dammit!) I've overhauled the site design - this should be the design that graces the site
Anthony Wells
FAQ: Wording
FAQ: Question Wording The wording of polling questions can have a huge impact on the answers - I will write a much longer article on that in the future. For the moment I want to look at the far simpler question of the wording used for voting intention questions. The
FAQ: Don't knows
FAQ: Dealing with don't knows In 1992 the British polls famously got it wrong. All the polls showed Labour ahead or the parties neck and neck. In fact the Conservatives had a solid lead. In the post-mortem that followed one of the problems that was identified was the
UKPR Polling Average
Very soon I am going to launch a weighted average of the polls, the UKPR polling average. I've thought long and hard about this because generally speaking I don't like polling averages. There is no statistical justification for a polling average - the different companies do
You may have missed...
I've been busy for the last couple of days, so here's a catch up of various poll findings from the last couple of days. Firstly since it's Prince Charles's 60th birthday, a YouGov poll in the Telegraph showed a majority of people
UKPR Projection
mysql_connect("localhost", "ukpoll_ajwells", "haddock"); mysql_select_db ("ukpoll_pollresults"); $avscores = mysql_query ("SELECT * FROM currentproj"); $normproj[1]= mysql_result ($avscores, 5, "Conseat"); $normproj[2]= mysql_result ($avscores, 5, "Labseat"); $normproj[3]= mysql_result ($avscores,
Populus show lowest Tory lead since April
Populus's monthly poll in the Times is out and has voting intention figures - with changes from their last poll - of CON 41%(-4), LAB 35%(+5), LDEM 16%(+1). The poll was conducted between the 7th and 9th November, so is the first to be carried
Tories retain an election winning lead with ICM
ICM have a new poll out in the Sunday Telegraph. The topline figures, with changes from the previous ICM poll, are CON 43%(+1), LAB 30%(nc), LDEM 18%(-3). The poll shows no significant change in Labour and Conservative support from the previous ICM poll, conducted a fortnight or
FAQ: Turnout
FAQ: Likelihood to Vote Turnout at the last few elections has been only around 60% - so 4 out of 10 people, whatever they told pollsters, didn't actually bother to vote (theoretically at least, actually the real percentage of people able to vote who do is higher than
Calculating Swings
A question that occasionally comes up in the comments here is how exactly you calculate a swing in an election. It obviously needs answering since the BBC managed not only to get it wrong on their coverage last night, but still had it wrong on the Today Programme this morning
US Election Day Open Thread
No UK polls today (I believe Populus's monthly poll is going to be next month) the focus is naturally on the USA. We know what the polls say - Obama will win, and probably win big. As ever, do be wary about the inevitable leaks of exit poll
The mobile phone vote
Over at Comment Central Danny's sidekick Alice picks up the interesting fact that there is a signficant difference in US polls that include cellphones and those that do not - if the sample includes cellphones Barack Obama has a 4 point bigger lead. Alice's conclusion is