Sunday, October 11, 2015

Sturgeon mustn't become a prisoner of the pollsters

I didn't see Nicola Sturgeon on the Marr show this morning, because I've been recovering from a truly epic journey to Newcastle and back to see Scotland's decisive pool match at the Rugby World Cup (more on that later).  But I gather she was more explicit than ever before that a substantial and sustained shift in public opinion could be a trigger for a second independence referendum.

I suppose in a sense this is to be welcomed, because for the first time it makes clear that the fabled "material change of circumstances" is an event that the Scottish people can have some control over themselves, and won't necessarily have to be something that the London government does or doesn't do.  But what troubles me is that the only measure we have of public opinion is polls.  That means apparent shifts in public opinion can be artificially generated by changes in polling methodology, but it also means that real shifts can be concealed by changes in methodology.  That's already happened to some extent - the real average increase in the Yes vote since last September is markedly higher than most polls have reported in their headline numbers.  The reason is that four of the six active pollsters have introduced weighting by recalled referendum vote, which in most cases hurts Yes.

We have, therefore, already seen a substantial and sustained shift in public opinion.  Perhaps it hasn't yet been substantial enough.  But the fact that we tend to underplay what has already been achieved should serve as a warning of the dangers of appointing the likes of Peter Kellner as our adjudicators.  It's not inconceivable, for example, that the next Yes surge could be hidden from view by a new incarnation of the notoriously convoluted (and secretive) 'Kellner Correction'.

44 comments:

  1. I hope you were allowed to wave the flag of Scotland to support Scotland? I seem to recall such vile nationalism being banned on one of your previous outings.

    ReplyDelete
  2. Would the party's own canvassing be more reliable?

    Personally, I think the SNP don't do enough to promote independence by pointing out the limitations between it and devolution. Too many Scots wouldn't know what freedom was if it stared them in the face - as it did on September 18th last year. They are so used to being managed and accepting third rate governance.

    ReplyDelete
  3. Don't the SNP have their own polls with their own methodology?

    ReplyDelete
  4. I'm sure the SNP will have their own polls, but if "public opinion" is going to be a driver she's going to have to refer to published polls which everyone is aware of. So watch out if there is a measurable shift towards independence for a slew of polls with questions specially designed to get headline figures which appear to challenge that shift. We're not going to get a clear picture of anything waiting for headline polls in the "Scotsman" and "Times" demanding independence.

    ReplyDelete
  5. Natural demographics movements account for a large part of the Yes gains over the past year. With the oldest demographic being more heavily towards No, we lose as much as 100 No voters a day through their passing. At the opposite end, it's harder to predict, but we could be gaining as much as 100 a day. So the overall movement towards Yes, all other things being equal (big assumption, I know) is 100-200 per day. At that rate, Yes will be in the majority by 2017-18, and comfortably in the lead by 2020.

    Note: I am NOT hoping for the demise of our elderly, who are a valued part of our society. I'm merely observing a natural process.

    ReplyDelete
    Replies
    1. Could we please, please, please stop kidding ourselves with this "demographic inevitability" stuff. We are not going to get a Yes majority just by waiting for long enough. Nor do natural demographic movements "account for a large part of the Yes gains over the past year".

      Delete
    2. Aye, okay then James, I'll wheesht.

      Bet Yes is in the lead by 2020 though, whatever the reason.

      Delete
    3. Yes is in the lead right now, if Ipsos-Mori and TNS are to be believed.

      Delete
    4. Hard work by activists will bring us independence.I'd like to ask James why he thinks demographics are irrelevant though.I understand the whole thing about people getting more conservative as they age,but I think the gulf in support between very old voters and very young voters has more to do with ideology/confidence/information sources etc than with conservatism.

      Delete
    5. There is no demographic inevitability. I know half a dozen Yes voters who have lost their jobs since the Referendum and have basically said eff this crap and have emigrated. Meanwhile locals to me searching for a home are regularly outbid by folk from Brit Nat Toryshire who will be using those houses as nothing more than holiday homes or eventual retirement homes, and based on my experience they will be Nawbags.

      Demographics aren't irrelevant though, Migration demographics will be very damaging to the Yes cause. We will have an equally hard job convincing those who voted No to change to Yes, that is the bottom line.

      Delete
  6. Replies
    1. Maths doesn't add up. Even with quotient 10, the green 2nd votes are not enough to win several of those AM seats.

      Delete
    2. Hmm. I'll recall that comment until I study the methodology. Where are the regional vote percentages coming from? Are the samples big enough to give 2 decimal place vote predictions for Green and Lib Dems?

      Delete
    3. I'm pretty confident the AMS algorithm is implemented correctly. I originally wrote it and ran it against the 2011 election results to verify my understanding of it was correct.
      Regional vote percentages come from from historical results with moving averages applied on top, Scotland-wide polling, then regional sub-polling applied after. The sample counts are under the tables. There's no accuracy justification for using 2 decimal places, I just like how it looked in the tables.

      Delete
  7. Should be other engagement mechanisms that triangulate poll data....

    ReplyDelete
  8. Should be other engagement mechanisms that triangulate poll data....

    ReplyDelete
  9. How you feel about this really depends on how you view the Bloc Quebecois.

    If you believe, as I do, that the Bloc Quebecois decline is entirely due to their failure to deliver a third Referendum in 1999 when they still had a majority led to them losing any credibility as a "vehicle for independence" then you will likely be concerned that the SNP will inevitably fall back.

    A party seeking independence must be credible and seen as a vehicle to deliver it. In Ireland the IPP lost crediblity and, fortunately for them, another vehicle came into the picture. In Scotland, much like Canada, I do not see an alternative vehicle appearing.

    ReplyDelete
  10. James is entirely right about not relying on changing demographics. So is Robin McAlpine when he says we shouldn't be hoping the Tories do the job for us. Undoubtedly both do help. But the only way we will win this for sure is if we go out there and convincingly argue the case for independence and that means everyone going out there and talking to those who voted no, especially the most vulnerable groups - i.e. our pensioners.

    Do that and we WILL win.

    ReplyDelete
    Replies
    1. Glasgow Working ClassOctober 12, 2015 at 12:11 AM

      Those of us who voted NO will be out on the streets again you can be sure of that. The most vulnerable can be helped by taxing the better of Scots just a little bit more. But you will not respond to that last sentence will you as that is Nat si policy.

      Delete
    2. Eat your cereal.

      Delete
    3. Sunshine on CrieffOctober 12, 2015 at 9:31 PM

      "Taxing the better of Scots"? Who are these better Scots you want to tax?

      Delete
    4. Glasgow Working ClassOctober 12, 2015 at 10:27 PM

      You by Crieff.

      Delete
    5. Eat your cereal

      Delete
  11. It doesn't have to be opinion polls, what about actual polls? You've just won nearly every Westminster seat, you'll no doubt win a majority in May at Holyrood. You're next step is to win some councils in 2017.

    These are polls that cannot be disputed by anyone.

    ReplyDelete
  12. Would a 55% plus share of the vote for the SNP at the next Holyrood election be sufficient to be a trigger?

    ReplyDelete
  13. I think if the SNP take 68 seats then it sends a message that people are wanting a referendum. But only if the SNP put having a referendum in the 5 year term in the manifesto.

    Remember they won the last majority by doing so. The SNP need to lead as well as just listen.

    ReplyDelete
  14. It is only 4 years since the leader of the demlibs in Scotland was telling us that there was no need for a referendum. if you want independence (he used a different word most times) then vote SNP.

    In other news. The herald is doing a nice job in smears started by that bigot K(KK) hague. And it's brilliant in its moronicity.

    P Murell (aka Mr Sturgeon) sacked M Thomson from her position in BFS as he knew she was a wrong un. Thus proving that BFS was an SNP front and that Mrs Murrell is a liar.

    He doesn't seem to have thought it through though. If PM was willing to sack MT from BFS then why did he allow her to become an MP? Blinded by their extreme nationalism they just can't help themselves. Twats!

    ReplyDelete
  15. They are tying themselves in knots with their muck raking. Who are the people leaking all these personal emails? How low has Scottish journalism got that they don't follow the news they try and make it!

    ReplyDelete
  16. Glasgow Working ClassOctober 12, 2015 at 12:04 AM

    James. I hope you did not meet any nasty anti Scots, English types on your journey. You must still be getting over your trauma on the way to Arran on the Cho Cho.

    ReplyDelete
  17. Nicola has also explicitly stated that a split vote in the EU Referendum will be a big trigger for another referendum. Which can't happen if at least a conditional referendum pledge is not in the manifesto.

    ReplyDelete
  18. When I first read the headline I thought it said "Sturgeon mustn't become a poisoner of the pollsters". A can understand misgivings about polling methodology, but that would be a little drastic.

    ReplyDelete
    Replies
    1. Funny you should say that.I keep reading someone telling a certain troll to "eat your carseal".

      Delete
  19. Guardian / ICM monthly GB poll released today (fieldwork this weekend past). Scottish sub-sample: SNP 54, Lab 22, Con 18. Overall figures Con 38, Lab 34, Ukip 11, LD 7, SNP 5, Green 3.

    http://www.icmunlimited.com/data/media/pdf/2015_oct_guardian_poll.pdf

    ReplyDelete
    Replies
    1. Am I alone in thinking that Labour are doing okay(ish) in the GB polls considering the opprobrium heaped on Corbyn?

      Delete
    2. Labour are consistently getting about half of the unionist vote in opinion polls.Whether Kezia can now kick on and capture a bigger share of that dwindling sector remains to be seen.I have my doubts though.The blue Tories are a bit sceptical about switching allegiance to a party led by Jeremy Corbyn.I think Kezia needs to better articulate her Blaitite leanings.

      Delete
    3. I wasn't meaning in Scotland specifically, but in GB polls as a whole.

      Delete
    4. Glasgow Working ClassOctober 12, 2015 at 10:44 PM

      Himmel mein gott wee Nicola is squirming on Newsnight Sotland just now about taxing the better aff to stop austerity. Hypocrite. You need to aquire money to help. DUH.

      Delete
    5. Eat your cereal.

      Delete
  20. Glasgow Working ClassOctober 12, 2015 at 9:11 PM

    Excellent article by the arch Tory Fraser Nelson on Sturgeon and the Nat sis. How right he is the Nat sis do not give a shit for the poor.

    ReplyDelete
  21. Glasgow Working ClassOctober 13, 2015 at 12:25 AM

    Nat sis gone tae sleep tae think again. Running oot of excuses.

    ReplyDelete