Voodoo polling corner

No proper national polls in the papers this weekend (though the Scottish Mail on Sunday does have a Scottish Opinion poll), but there is what proports to be a selection of constituency polls in the Sunday Express.

The Sunday Express claim to have constituency polls in Salford, Worcester and Basildon, which show the BNP ahead in Salford and the Conservatives ahead in Basildon and Worcester. Of course, in theory these could be properly conducted polls carried out with appropriate sampling techniques and weighted to be representative of the relevant constituencies. If so, the swings are off the scale.

I suspect however, they are nonsense – straw polls of the first 500 people the Sunday Express could grab off the street. We can’t tell, but the warning signs are there. As well as the implasibility of the figures themselves, there is no mention of the pollster who conducted the survey in the report, suggesting there wasn’t one. Secondly, the results a quoted to a single decimal place, given most polls have a margin of error of around 3% false precision like this is normally a sign that the person who produced the figures doesn’t know what they are doing. The cherry on the cake is that Salford and Basildon constituencies are both to be abolished at the next election anyway, to be replaced by Salford & Eccles and Basildon South & East Thurrock.

On the subject of voodoo polls, there was a vintage example on the London Daily News website, who took an open access poll on their own website which allowed multiple voting seriously. They updated the story saying “The poll referred to in this article has been removed due to a clear attempt by a political group to sway the results”. I hate to break it to them, but the poll would have been meaningless even if there hadn’t been orchestrated attempts to fix it. Polls that are open to all don’t work, since people who are interested in the subject are more likely to take part, people who take part will not be demographically representative of the county, and because people are free to manipulate and fix the poll.

UPDATE: Even worse – Wales on Sunday had this shocker of a Voodoo poll, done just using people who happened to visit their website. They’ve even tried to extrapolate figures for each individual MP in Wales from the figures, which must be unrepresentative, unweighted samples of about 40. Naughty step, now.


21 Responses to “Voodoo polling corner”

  1. Gotta love voodoo polls…

    Randomly, Tony, where could we find that Scottish voting intention poll? I’d be -very- interested to see that, considering what has appeared to show up on the (somewhat undersized) crosstabs for Scotland.

  2. Stuart has put up a link on the previous thread.

  3. Tony-
    Thanks, and…oy. I know there will likely be a bit of a bounce, but that’s not pretty.

  4. when is the next real poll coming out im getting board with no polls to chew over.

  5. Yes but what ARE the results of this Mail on Sunday poll.

    It is true that they are not particularly reliable BUT it is the best of what we know thus far. The Scottish samples are great for the Nats – but how does it stack up in this poll?

  6. SNP – 32%
    Labour -20%
    Tory-8%
    Lib Dem-8%
    Green-2%
    Other-4%
    Would not vote-25%

    Removing would not vote

    SNP 43%
    Labour 27%
    LibDems 11%
    Cons 11%

    Using Electoral Calculus

    SNP 48 seats
    Labour 8 seats
    LibDem 3 seats
    Cons zero seats

  7. The numbers match what has been reported in the Cross Tabs.

  8. This is a bit off-topic, but the BNP’s website has been hijacked by anti-BNP people. The title of it has been changed to something that i won’t say on here. Getting back on topic, i wonder if this will make the news, and give the BNP a bump in the polls? I hope not.

  9. Very irresponsible of the Express to publish such a poll, but what’s new I guess…

  10. If the result of the Pendlebury by-election is anything to go by (although I think that at present that is in the Eccles constituency) the BNP would be nowhere near winning in Salford or its successor constituency.

  11. doonhamer, tories would have zero seats in scotland? Ouch.

  12. That Scottish opinion poll smacks of utter rubbish to me, not only does it seem to run totally against every single other Scottish opinion poll thus far 2008-2009, but we have no idea if the sample is representative (and I strongly suggest it is not).

    Labour 20%, in Scotland! I’ll have a toke on whatever your having! And the Scottish Conservatives being out performed by the Liberals? Nonsense, the last system three poll (they tend to be most reliable as far as i can tell) places tories on 19%- and the last you gov poll placed the figure at 21%. And all other YouGov Scottish Opinion poll ratings have been 20% since January.

    Sorry to rain on anyones hopes, but the only believable figure in that quite frankly was the SNP figure on 32% (the sytem three TNS poll had them on 30%).

    Even once you removed the ‘would not vote’ the figures decend into an even greater farce! The SNP on 43%, that is wholly unsupported by every other major poll; and the whole thing seems a blip originating from an unreliable source.

    Sorry for the negativity but it had to be pointed out.

  13. It sounds very unlikely that the BNP could be ahead in the Salford constituency as a whole. The Conservatives being ahead in Worcester and Basildon is not exactly surprising given Labour is averaging 25% in the polls at the moment.

  14. Dean,

    A survey of 650 people isn’t that big and I am not sure about Scottish opinions accuracy anyway, but I am not sure I would be so dismissive.

    Looking at Anthony’s Scottish intentions table the Tories have been as high as 20% in full Scottish polls since summer but they have also been as low as 14%, although that is as far back as summer 07. If the expenses affair has knocked 24% off the Tories nationally then a bigger drop wouldn’t be out of the question.

    The figures for the Libdems are about what we often see they have been averaging 10-15% for over a year and of the three main Uk parties they seem to be the least effected.

    Labours poll figure in Scotland over the last year has been between 29 and 38% so given the governments poor performance and expenses hitting them arguably the hardest although 20% is low not impossible.

    What it does show I think is that an SNP that has always done well in the Euros and was already doing well in the polls, is like UKIP the main beneficiary of the swing to others caused by the expenses affair.

    Hopefully this weekend we might see a raft of Euro polls and at least one proper one in Scotland, especially as we have a by election coming up too.

    If I had to hazard a guess as to where we are now I’d go for;

    Lab 25-30%, Tories 15-20%, LibDems 10-15%, SNP 30-40% other +/-5%,

    Not very precise as it could result in anything from both Labour and the SNP and the Tories and Libdems neck to an SNP landslide and the Tories fourth. It could also see the Tories come close to overtaking Labour.

    The truth is with the current public mood we really are in new territory and it will be next week before we really know how the public have reacted.

    The last week I have been out canvassing and we are getting a fair hearing. Among our own supporters we are getting the vast majority still with us and prepared to vote, a very good sign for what could be a very low turnout election.

    As to those we have lost they are overwhelmingly staying at home and there is no sign of them leaving us for anyone else.

    As one of my mates told me after going round the streets leafleting;

    ” The public seem in two minds, half say “hang the bastards” and the other half think hangings to good for them”…….

    Peter.

  15. Sorry that should be 2-4% off the Tories not 24%….

    Peter.

  16. I agree with Peter.

    Scottish Opinion has not been particularly reliable in the past. However they have shown no particular bias towards the SNP – for example their widely reported poll in Glasgow East showed Labour with a clear lead.

    The other aspect to consider is that for the last two weeks or so EVERY Scottish sample of a UK poll has shown a soaraway SNP vote.

    We could well be in landslide territory for the Euros and seachange for the General in Scotland.

  17. Guys (Dean in particular),
    Do remember that once you kick out “would not vote”, this is the “real” result (since other pollsters throw out the “wouldn’t vote” crowd):
    SNP 43%
    Labour 27%
    LibDems 11%
    Cons 11%

    Peter’s suggested range is:
    SNP 30-40%
    Lab 25-30%
    Tories 15-20%
    LibDems 10-15%
    other +/-5%

    So the SNP is a little high and the Tories are a little low. Labour is “in range”, as are the LibDems, but all in all nobody is more than 4 points off of where they “should” be…and I could easily see the SNP benefitting from an anti-Labour tendency (Duverger’s Law and all).

    The “Labour on 20%” -is- rubbish, but that’s also not the result when you look at it. 27%, just below their other lowest, is hardly out of character right now, and I can see the Tories sliding some as well (as they have elsewhere). While I’d expect them to be higher, the poll may have just been a little off in that regard, or Scotland may just be acting a little nutty.

  18. @thealeaxweb “doonhamer, tories would have zero seats in scotland? Ouch.”

    They’ve only got one just now, and they had none in 1997.

    No reason to be shocked that I can see.

  19. “or Scotland may just be acting a little nutty.”

    Wouldn’t be the first time, by a long way……

    Peter.

  20. Anthony,

    Do you know if we are getting any polls before the end of the month ? Hopefully not ICM who seem to be on a different planet to other polling companies !

  21. I just read the shocking voodoo poll in the Wales on Sunday, and realised I actually used to know the journalist who wrote the article!!