Here is a lovely graphic setting out the seats as we have and under pure PR. 

http://www.audiencenet.co.uk/votes-vs-seats/

Ummm. Would that have delivered a UKIP/Tory coalition? 

Simon

On 9 May 2015, at 12:04, Macfarlane, Alison <[log in to unmask]> wrote:

An even bigger question is why all the preceding polls got it so wrong and whether their results afftected voting behaviour. There is an article on this on 'The Conversation'. https://outlook.office365.com/owa/#path=/mail

There is also an article there about the case for PR. I would suggest that Cameron will probably ignore it. If he can rule forever on a third of the vote, why should he bother to implement PR?

Alison Macfarlane

________________________________________
From: David Firth <[log in to unmask]>
Sent: 09 May 2015 08:09
To: [log in to unmask]
Subject: Re: UK election result

To answer Allan's questions.

Two JRSS-A papers dealing with (1) the exit-poll methodology, and (2) the method used for the BBC's on-air updating based on declared results:

1.  Curtice, J and Firth, D (2008). Exit polling in a cold climate: The BBC/ITV experience in Britain in 2005. Journal of the Royal Statistical Society A, 171, 509–539.  DOI: 10.1111/j.1467-985X.2007.00536.x

2.  Brown P J, Firth D and Payne C D (1999). Forecasting on British election night 1997.  Journal of the Royal Statistical Society A 162, 211–226. DOI: 10.1111/1467-985x.00131

Public interest after the 2010 election also prompted me to produce a less technical "explainer" page about the exit polling methods:
 http://warwick.ac.uk/exitpolling
-- not yet updated for the 2015 exit poll results but I'll do that soon.

(Google delivers that on the first page of results for me (search term "exit polling uk"), but then I suppose Google does know who I am!  Your mileage may vary.  But others do seem to be finding it -- it was accessed in the last 2 days more than 17,000 times, from nearly 14,000 distinct IP addresses.)

I hope that helps.

All the best -- David Firth

--
Professor David Firth
Director, Warwick Data Science Institute
http://warwick.ac.uk/dfirth

You may leave the list at any time by sending the command

SIGNOFF allstat

to [log in to unmask], leaving the subject line blank.

You may leave the list at any time by sending the command

SIGNOFF allstat

to [log in to unmask], leaving the subject line blank.

 

You may leave the list at any time by sending the command

SIGNOFF allstat

to [log in to unmask], leaving the subject line blank.