I posted these a couple of weeks before the election, but I see more and more of them cropping up in the comments, so I think it’s worth reposting it for newcomers.

1) The polls are ALL wrong, the real position is obviously X

Er… based on what? The reality is that opinion polling is pretty much the only way of measuring public opinion. We have some straws in the wind from mid-term elections, but they tend to be low turnout protest votes, don’t tend to predict general election results and are anyway quite a long time ago now. Equally a few people point to local government by-elections, but when compared to general election results these normally grossly overestimate Liberal Democrat support. If you think the polls are wrong just because they “feel” wrong to you, it probably says more about what you would like the result to be than anything about the polls.

2) I speak to lots of people and none of them will vote for X!

Actually, so do pollsters, and unless you regularly travel around the whole country and talk to an exceptionally representative demographic spread of people, they do it better than you do. We all have a tendency to be friends with people with similar beliefs and backgrounds, so it is no surprise that many people will have a social circle with largely homogenous political views. Even if you talk to a lot of strangers about politics, you yourself are probably exerting an interviewer effect in the way you ask.

3) How come I’ve never been invited to take part?

There are about 40 million adults in the UK. Each opinion poll involves about 1,000 people. If you are talking about political voting intention polls, then probably under 100 are conducted by phone each year. You can do the sums – if there are 40,000,000 adults in the UK and 100,000 are interviewed for a political opinion poll then on average you will be interviewed once every 400 years. It may be a long wait.

4) They only interview 1000 people, you’d need to interview millions of people to make it accurate!

George Gallup used to use a marvellous analogy when people raised this point: you don’t need to eat a whole bowl of soup to tell if it is too salty, providing it is sufficently stirred a single spoonful will suffice. The same applies to polls, providing an opinion poll accurately reflects the whole electorate (e.g, it has the right balance of male and female, the right age distribution, the right income distribution, people from the different regions of Britain in the correct proportions and so on) it will also accurately reflect their opinion.

In the 1930s in the USA the Literary Digest used to do mail-in polls that really did survey millions of people, literally millions. In 1936 they sent surveys to a quarter of the entire electorate and received 2 million replies. They confidently predicted that Alf Landon would win the imminent US Presidential election with 57% of the popular vote and 370 electoral votes. George Gallup meanwhile used quota sampling to interview just a few thousand people and predicted that Landon would lose miserably to Roosevelt. In reality, Roosevelt beat Landon in a landslide, winning 61% of the vote and 523 electoral votes. Gallup was right, the Digest was wrong.

As long as it is sufficent to dampen down sample error, it isn’t the number of people that were interviewed that matters, it is how representative of the population they are. The Literary Digest interviewed millions, but they were mainly affluent people so their poll wasn’t representative. Gallup interviewed only a few thousand, but his small poll was representative, so he got it right.

5) Polls give the answer the people paying for it want

The answers that most clients are interested in are the truth – polls are very expensive, if you just wanted someone to tell you what you wanted to hear there are far cheaper sources of sycophancy. The overwhelming majority of polling is private commercial polling, not stuff for newspapers, and here clients want the truth, warts and all. Polling companies do political polling for the publicity, there is comparatively little money in it. They want to show off their accuracy to impress big money clients, so it would be downright foolish for them to sacrifice their chances with the clients from whom they make the real money to satisfy the whims of clients who don’t really pay much (not to mention that most pollsters value their own professional integrity too much!)

6) Pollsters only ask the people who they know will give them the answer they want

Responses to polls on newspaper websites and forums sometimes contain bizarre statements to the effect that all the interviews must have been done in London, the Guardian’s newsroom, Conservative Central Office etc. They aren’t, polls are sampled so they have the correct proportion of people from each region of Britain. You don’t have to trust the pollsters on this – the full tables of the polls will normally have breakdowns by demographics including region, so you can see just how many people in Scotland, Wales, the South West, etc answered the poll. You can also see from the tables that the polls contain the right proportions of young people, old people and so on.

7) There is a 3% margin of error, so if the two parties are within 3% of each other they are statistically in a dead heat

No. If a poll shows one party on 46% and one party on 45% then it is impossible to be 95% confident (the confidence interval that the 3% margin of error is based upon) that the first party isn’t actually on 43%, but it is more likely than not that the party on 46% is ahead. The 3% margin of error doesn’t mean that any percentage with that plus or minus 3 point range is equally likely, 50% of the time the “real” figure will be within 1 point of the given figure.

8 ) Polls always get it wrong

In 1992 the pollsters did get it wrong, and most of them didn’t cover themselves in glory in 1997. However, lessons have been learnt and the companies themselves have changed. Most of the companies polling today did not even exist in 1992, and the methods they use are almost unrecognisable – in 1992 everyone used face-to-face polling and there was no political weighting or reallocation of don’t knows. Today polling is either done on the phone or using internet panels, and there are various different methods of political weighting, likelihood to vote filtering and re-allocation of don’t knows. In 2001 most of the pollsters performed well, and in 2005 they were all within a couple of points of the actual result, with NOP getting it bang on.

9) Polls never ask about don’t knows or won’t votes

Actually they always do. The newspapers publishing them may not report the figures, but they will always be available on the pollsters’ own website. Many companies (such as ICM and Populus) not only include don’t knows in their tables, but estimate how they would actually vote if there was an election tomorrow and include a proportion of them in their topline figures.


675 Responses to “REPOST: Too frequently asked questions”

1 2 3 4 5 14
  1. One thing I would say though is that, barring a Conservative catastrophe of epic proportions in the next week, Labour will not get a majority. Their job now is to stop the Tories from seizing power – it is all they can do IMO.

  2. Blimey – Sky just actually did something interesting. Viewers WATCHING overwhelmingly voted Clegg, viewers LISTENING overwhelmingly voted Brown.

  3. I do not think the ‘who won debate’ polls are of any significance except the clear impact that the first one made on the population. That impact was indelible. With due deference to those who know better, despite my feeling at the beginning of the campaign that Lib Dems would do slightly less well than last time (22 against 23 in 2005), it seems that a good lift has now been consistently achieved.

    Last night’s debate was clearly just a ‘core vote’ encouragement exercise and will be forgotten already.

    I watched the football with a small screen edition on my lap with their words on and I should be surprised if anyone in the swing-voter category lasted more than half an hour. It was monumentally tedious. I don’t remember any new question or any new answers from anyone, compared with the first debate.

    So it’s all over now and tomorrow’s polls should be the final guide with only last-minute waverers to guess at. As they will decide the final outcome, we should not get too excited about the polls between now and Thursday (barring an Event).

  4. For those who are interested, 8 million was the BBC 1 peak at around 9pm.

    Based on the 15-minute breakdowns (I hang out on another forum that’s very interested in ratings analysis! :)) viewing figures started at 6.2m, climbed to that peak in the 9-9.15 segment, then fell back to about 7.4m and stayed there.

    There’s no way of measuring “churn”, but I guess we can assume more people saw the non-economic bits of the debate than the economic bits.

    And FWIW count me in among those who can’t qbelieve Cameron edged the polls after repeatedly dand obviously dodging important questions. I’m an LD supporter myself, but frankly would have given last night to Brown…

  5. @Matt,

    Ironically, you are correct to say that the net poll gain for blue will not be much.

    These debates are not about who wins, voters prior to the debates had Cameron comfortably in front in terms of expectations.

    Let me say it as clear as i can, Gordon Brown comfortably exceeded people’s expectations of how he would perform. His average accross the polls held up steadily.

    In terms of poll predictions, annoyingly ICM and MORI’s fieldwork will be part prior to the debate. I have a little to say on the various polling companies and how they seem to score debates but I will post that in a separate post.

  6. And for what it’s worth, the average figures and percentages of the total viewing audience were:

    BBC1 7.264m (27.9 percent)
    BBC News 617,000 (2.4 percent)
    BBC HD 213,000 (0.8 percent).

  7. Matt – Because Cameron communicates better, that doesn’t mean he “wins” on policy etc.
    We really will have to see what the VI polls tell us in the next few days.
    Remember, you don’t have to like GB to vote Lab

  8. Very interesting FAQs.

    Re: post-debate polls … what scientific significance do they have? They’re not representative samples of the UK electorate. They’re unrepresentative samples of those who saw the debate ie about 15% of the electorate? Or are they being weighted to reflect the UK electorate?

    Also, what are the criteria for someone ‘winning’ the debate? Isn’t the question, who would make the best PM or leader, much more pertinent?

    If so, according to ICM in The Guardian today, Brown won, Cameron second and Clegg third. Strange indeed that there is so little reporting of that.

  9. @Giles,

    “And FWIW count me in among those who can’t qbelieve Cameron edged the polls after repeatedly dand obviously dodging important questions. I’m an LD supporter myself, but frankly would have given last night to Brown…”

    I’m guessing that it’s more than likely that you want a Lib-lab coalition and don’t like centre-right parties? I’m also guessing you like the Tories the least out of the 3 main parties.

  10. @MATT

    “Their job now is to stop the Tories from seizing power – it is all they can do IMO.”

    I think that is the best they could have hoped for all along really.

    what has changed in the last week is that from being in a position to be the largest party in a hung parliament that has clearly changed back to the Conservatives again – with the growing possibility that they could secure an overall majority.

    although considering the economy maybe it is a good election to lose…

  11. last roll of the dice – here comes Tony!

  12. Matt – More votes doesn’t necessarily follow from winning the debate (where the victory is decided by the adeptness of the communication)

    More votes would follow from policy commitments that benefitted the voters. That’s why I believe Clegg’s £10k tax band has led to his increase and Cameron’s £2m IHT threshold led to his (regardless of who is helped and by how much relatively)

    The voters are aware they’re being asked to fill the big hole. They find any promise to ease the burden irresistible – at least to the extent that they want some-one other than Labour.

    Then there’s the Brown factor (incumbency, length at the crease, incremental enemy-making) which probably is the least tractable aspect for him.

  13. Eoin Clarke,
    I disagree that the polls were’bang on ‘ in 1983. Certainly in the final week of the campaign a significantly bigger Tory majority than actually occurred was being predicted – with a lead in excess of 20% and the SDP/Lib Alliance in second place.. Whilst the 144 Tory majority was a disaster for Labour it was still 100 lower than many had expected in the closing days of the campaign!

  14. @Eion

    You are such an expert I wonder if you might help me on something.

    I am speculating that if the Tories are the biggest party but short of an overall majority, what sort of change to the voting system might be acceptable to them , so they can offer a referendum to LD in return for support.

    I have heard that AV plus is best for the Tories. It is also true that a reduction in the number of MP’s and an evening out of the size of contituencies removes much of Labours advantage under the current FPTP system.

    HAs anyone crunched the numbers to see what a combination of these two changes would do? Might the Tories be able to live with such a change?

  15. Anyone who read this forum during the debate last night will know that most people simply can’t HEAR the answers of the candidates they like the least.

    They hear the answer they like (dog whistle blows) then they don’t actually listen at all to the answers they don’t as they’re too busy disagreeing in their mind/remembering counter arguments.

    this is dangerous IMO as it makes it impossible for you to be objective. It might amaze you to know that there were many “good answer Clegg’s” and “nailed that one Cameron’s” from me mixed in with the “Yep, THAT’s the answer Brown’s” from me.

  16. I don’t expect the polls tonight to change much because I think people will generally vote for the party that makes them the best off financially and who they feel represents them the best (i.e. families with kids will be more likely to vote Labour, young people (i.e. students) will be more likely to vote Lib Dem, and older people will be more likely to vote for the Tories.) The debate won’t change this too much IMO.

    Tories up 1%
    Labour unchanged
    Lib Dems up 1%

  17. YouGov has always been the polling company to award the highest % of voters whom think Cameron won the debate. ICM and Comres disagree with YG quite considerably on this.

    Put it this way:

    YG had DC leading GB by 16%
    ICM had DC leading GB by 6%

    To put it another way, DC’s lead with YG was two and a half times bigger than ICMs.

    I, for one, find that very interesting. With ICM’s gold standard reputation, we are in for an interesting 7 days.

  18. “Matt – More votes doesn’t necessarily follow from winning the debate”

    Yeah, that’s what I was saying (and predicting) i.e. little change.

  19. @John,

    I would not reccomend AV+ minus or any type for blue.

    They would fare best under STV. Let me tell you why. A signifacne proportion of Scotland and Wales vote blue but there is rarely any seats to show for it. With AV+ reds/yellows could gang up on them.

    Under STV seat portions and share of the vote enjoy a strong correlation. Also blue would be awarded for their higher turnout.

  20. @JohnTT

    As far as I know nobody keeps track of what predictions were made on the basis of a poll result so obviously what i am saying is anecdotal. Nevertheless I remain convinced that every time we have a general election the media will at some point present the poll results as leading to a hung Parliament with the LibDems having the balance of power. Of course they do – with the polls showing 35% party 1 30% party 2 and 23% party three, that would seem to lead to a hung Parliament with LibDems holding the balance of power. Actually this just doesn’t happen.

    Now what normally happens is that as we get closer to election day the pollsters change their strategy somewhat. They stop looking at (cheap to prepare) vote share polls and start looking at (expensive) polls of significant numbers of people in marginal constituencies.

    Now there was a ComRes poll recently that showed the LibDem surge only appears in Labour/LibDem marginals. This is what I expected. The assumption has been that the LibDem surge was because Nick Clegg had done so well in the TV debates. I don’t think that is the case – it is because Gordon Brown did so badly and people focussed their attention on how best to unseat him with tactical voting in their own constituencies. The ComRes poll suggests it is not a LibDem surge – it is an “anybody but Gordon” surge that actually will see both the Conservatives and LibDems do very well against Labour. I think (based on past polling behaviour) that the Labour vote will actually be once again as much as 6% lower than the pollsters predict due to Labour voter apathy – perhaps as low as 20%. Pollsters can’t handle the current situation – the lessons they learned can only cope with simple Labour/tory swings. Tactical voting on a massive scale to unseat as many Labour MPs as possible they cannot deal with and won’t predict accurately until they start doing less simple vote share polls and more polls looking specifically at the marginals and considering how tactical voting will play out.

  21. @John Fletcher

    I am speculating that if the Tories are the biggest party but short of an overall majority, what sort of change to the voting system might be acceptable to them , so they can offer a referendum to LD in return for support….

    ————–

    It’s very unlikely that the Conservatives will offer any change to the voting system.

    If they are the largest party and are invited to form government, they will form a minority administration and try to push through a budget.

    This will probably fail.

    The Conservatives will then – quite rightly – be able to accuse the other parties of provoking a budgetary crisis.

    This will lead to the dissolution of parliament and a second election in late summer/early autumn. The Conservatives hoping to win a clear majority.

  22. The debate matters little if the Tory-Labour lead remains unchanged. A lead of 8-9%+ would obviously be very pleasing for the Tories (unlikely to happen IMO).

  23. Graham,

    ref 1983 I have used ICM’s polls for that statement. You oculd be entirely correct I would be interested where you got the data from? :)

    ICM’s poll graph is available on the wikipedia webiste (if you scroll down) for the 1983 election.

  24. An 8% lead for the Tories would be pretty good for them tonight IMO, especially after the tightening of the polls a week ago. 8%, or thereabouts, was where we were before the start of the election campaign too.

  25. @ Matt,

    I won’t deny that’s true – though my political preferences are largely dictated these days by the Murdoch issue and the need to protect the BBC ( I had one of those George Osborne letters through the post and sent it back agreeing with all of their motherhood and apple-pie statements, but saying that nevertheless I could not possibly consider voting Tory because of their statements on the Beeb! :))

    Anyway, that’s OT and possibly partial (though I hope that stating my opinions without attempting to twist the polls to fit them, isn’t beyond the CoC).

    BUT I tried to put my personal preferences to one side and I didn’t see anyone else in the debate avoiding questions as egregiously as Cameron. It appears this wasn’t an issue for a substantial number of viewers, though as always we should remember this is a “who won?” question rather than a “rank in order” one…

    * NB: Just to make it clear, I don’t work for the Beeb – I just believe in it passionately, and decry the state of commercial broadcasting in this country! :)

  26. FWIW

    I’m not a Tory voter but did think Cameron just about won the debate last week.

    I thought he was well beaten by Brown last night though.

    (And I’m not a Labour or Lib Dem voter either!)

  27. Final polls of the 2005 campaign were;

    YouGov 32:37:24
    MORI 33:38:23
    Harris 33:38:23
    ICM 32:38:22
    NOP 32:36:23
    Populus 32:38:21
    BPIX 33:37:21
    ComRes 31:39:23

    So the average was C 32, Lab 38, LD 22.
    The final GB results were C 33, Lab 36, LD 23

    The 3% swing from Lab to C would have given Labour a majority of 104 under UNS. It was actually 66.

  28. This time next week it will all be over.

    I can’t wait.

  29. Giles – here here!

  30. @Eoin

    I am not an expert but I thought that STV meant an end to individual constituency MP’s. Am I wrong?

    @David in France.

    I tend to agree with you but as I said I am speculating. At the end of each debate Cameron and Clegg approached each other and Cameron lightly gripped Cleggs elbow. Then the two of them looked down on GB. They were just like the two advantaged, upper class, public school boys they are looking down on the grammar school oik. I actually think they could work together as individuals, and was wracking my brain as to the conditions that might be acceptable to both parties for this to happen.

  31. @Giles,

    “I won’t deny that’s true – though my political preferences are largely dictated these days by the Murdoch issue and the need to protect the BBC ( I had one of those George Osborne letters through the post and sent it back agreeing with all of their motherhood and apple-pie statements, but saying that nevertheless I could not possibly consider voting Tory because of their statements on the Beeb! :) )”

    I see. Thanks. For what it’s worth, I think the Libs would form a good coalition with the Tories. Whilst I disagree with NC on quite a few issues, as a Tory voter at this GE, I do find some of the Lib policies appealing.

  32. @ Eoin

    “1997: Polls overstated Labour’s lead by c.6%”

    Curtice points out that there was up to a 12 point variation in the lead pollsters gave tp Labour – ‘greater than in any previous election’ – and that in other circumstances it could have been a ‘public relations disaster’, e.g. with a 3% Tory lead they’d have shown everything from a 6% Tory lead to a 6% Labour lead.

  33. Adrian – yep, polls can’t detect any shift in voting intention after they have finished polling (this was the reason the polls got it wrong in the US in 1948 – producing the famous photo of a victorious Harry Truman brandishing the newspapers that had assumed the polls were correct and gone to print with “Dewey Defeats Truman” as their headline – and in the UK in 1970).
    Pollsters do poll right up to the wire these days though – polling will be continuing to take place right up to Wednesday afternoon. People would have to change their minds very late in the day indeed (and don’t pay too much attention to the polls showing x proportion of people make their minds up in the polling station itself. They might think they do, but most will vote for the party they would have said if asked a few days before)

    Christian – it definitely wasn’t the first voodoo poll, there was a century’s worth of them before that!

    Skudor – if you go on the front page of the site, then on the right hand sidebar there is a link to historical polling from the last four Parliaments.

    SeanR – the Telegraph no longer have a pollster. The Sunday Telegraph and the Guardian both use the same pollster, ICM, who use identical methods for both and produce identical results.

    Jason – that’s been the pattern for years. Conservative voters normally say they are the most certain, Lib Dems are nearly always the least certain. It might be because there are two parties on the centre-left, so people may be more willing to consider switching between them, or could be because the Lib Dems tend to benefit from the plague on both your houses vote and have fewer core supporters.

  34. To be honest, I think all of the leaders, including DC, are being dishonest to the public. I think that whoever gets in times will be tougher than anyone can even imagine, yet none of the parties has been willing to reveal the extent of the spending cuts/problems that lie ahead.

  35. @Matt

    For what it’s worth, I think the Libs would form a good coalition with the Tories.

    __________________________________________

    Please see my post one above yours at 1116. We are clearly thining along the same lines. All the talk has been of a Lab/LD coalition but might that now be changing to a CON/LD coalition of some form?

  36. @RYAN

    “it is not a LibDem surge – it is an “anybody but Gordon” surge that actually will see both the Conservatives and LibDems do very well against Labour. ”

    It is this which may propel DC to Downing Street with an outright majority.
    The Lib Dems have got to be very careful. They will be an even bigger than loser than Labour if they don’t get their hung parliament

  37. @RogerH,

    belwo oare the shares given to red in the final 22 polls of 1997, they afford red an average of 48point something they polled about 43%

    So sorry buddy but the 12% figure you quoted sgnificantly deviates from reality

    43
    47
    51
    51
    49
    48
    47
    47
    53
    50
    48
    42
    48
    47
    49
    45
    50
    50
    50
    49
    53
    49

  38. @John Fletcher,

    “Please see my post one above yours at 1116. We are clearly thining along the same lines. All the talk has been of a Lab/LD coalition but might that now be changing to a CON/LD coalition of some form?”

    You may well be right. I think the Libs will go with whichever party benefits them most.

  39. @John Fletcher,

    technically, that is correct but in reality it is wrong.

    STV has multi-member constituency so it means everybody has an MP link and not just th eones who voted for the FPTP winner.

    If the 62 seats won by LD in 2005 were on average with 46% of the vote, in effect 54% of constituents do not have an MP link. STV avoids that.

  40. @JOHN FLETCHER
    with regard to CON accepting electoral reform. AV+ and STV are both proportional systems that would pretty much stop any party from total power with less than 50% of the vote. So were CON to accept one of them they would be stopping CON from holding total power for (possibly) all time… Do you think they would accept this?

    However Portillo did say that they would go for it… Maybe he has some knowledge of CON behind the scenes thinking…

    STV does lose the constituency link – AV+ keeps it…

  41. @Eoin,

    Do you think last night’s debate will enable the Tories to average 35% in the polls now?

  42. @ matt – “none of the parties has been willing to reveal the extent of the spending cuts/problems that lie ahead.”

    I think you’re right but I also think that we (ie the voting public) has to accept some responsibility for that. We don’t really want to hear it and the parties know this. If you recall, a few months ago when Cameron was saying tough negative things about the economic situation, the polls showed a bad reaction to that and commenters and advisers immediately started saying that a more positive message was needed.

    There’s no doubt though that the next few years are going to be tough, whichever party or coalition of parties wins.

  43. @EoinClarke
    Buon giorno :-)

    “YouGov has always been the polling company to award the highest % of voters whom think Cameron won the debate. ICM and Comres disagree with YG quite considerably on this.”

    Still trying to get my head round why the post-debate poll was weighted for people “absolutely certain” to watch.

    Why?

  44. Matt, currently blues are on 34%ish. That will gradaully climb from now until polling day. Probably to 36% as I stated in February.

  45. I cannot comment on the FAQs here that relate to polling data and procedures, although I would like to comment on some of them, as I have a self-denying resolution because of temporary work I am doing.

    However, there are a couple of very important points that I have not seen raised during the extensive discussion of the election and which are general, not relating to any specific poll or their results.

    1. The accuracy of polling predictions have to depend on assuming a reasonably constant register and turnout. However, this assumption is likely to be unreasonable at this General Election. Large numbers of people have registered just before the election. In addition, TV and radio interviews suggest that younger people are going to vote in much larger numbers than in 2005 (actually, there might be polling data that addresses this too, but I don’t know about this data). I think that these factors could lead to a discrepancy between the pollsters’ predictions and the actual result, and it could be quite considerable. It is one that the pollsters cannot reasonably be expected to address. It is up to users to interpret their data sensibly and with caution.

    2. Before the election, I blogged on this site about the relevance of catastrophe theory to psephology. And during this election I think that we may well have seen a statistical catastrophe (a happy one from a LibDem point of view) during the current campaign in the form of Nick Clegg’s performance during the first TV debate.
    Whilst recent events concerning Brown may appear of comparable or greater significance than Clegg’s TV performance, they may not show the same psephological effects because Labour is not near a point in terms of electoral support where change will be catastrophic.
    The financial crisis reflects the operation of economic forces that appear best modelled using catastrophe theory; but the financial analysts failed to see devastating problems because they relied on (easier) multiple regression statistics. We should not make the same mistake when we interpret psephological data.

  46. @ Matt
    I think you are being a little unfair to the leaders. Just imagine if any of the leader came on and told the truth , how many votes would he get?
    The public should be aware of the true situation , but still people prefer to focus on any minor giveaways

  47. @ Eoin

    “So sorry buddy but the 12% figure you quoted sgnificantly deviates from reality”

    Not my figure but that of Professor John Curtic . Best you take it up with him.

    “Labour’s estimated lead was put as low as ten points and as high as 22 points, a range of as much as 12 points. This range was not only greater than in 1992 when it was just three and a half points, but was greater than in any previous election. It is therefore difficult to see how any election result could in truth have provided a collective endorsement of the polls. Indeed, in other political
    circumstances such a range of results could easily have occasioned a public relations disaster. Let us imagine that instead of Labour being well ahead by 13 points, the Conservatives had been narrowly ahead, say by three points. In these circumstances the above set of poll results would translate into everything from an six point Conservative lead to a six point Labour one! No less than four of the six polls would have apparently picked the wrong winner. Instead
    of giving the industry a clean bill of health the press would have been asking how (some) polls could have got it so wrong again.”

    (‘So How well did they do? The polls in the 1997 Election’, John Curtice)

  48. I seem to have a vague recollection of someone once saying that the election campaign is fairly irrelevant.

    Does someone have polling figures from the start of previous elections that can be compared with the final result at those elections?

  49. I defer to EOIN on the STV constituency link… :)

    Out of interest – if there is a big increase in turn-out – how does this affect polling MoEs? Would it invalidate some of the assumed weighting?

  50. RogerH,

    Curtice is talking about range. I, if you wish to check my orinal post, was talking about averages. They are two very different things….

    As Derek pointed out, LD range from 34-23% but noone would deny their average is 28/9%

1 2 3 4 5 14