Saturday, May 24, 2014

More 'devastation' from Tom Holland

You might remember a couple of weeks back I posted a brief Twitter exchange I had with the English historian Tom Holland, who seems to be obsessed with preventing Scotland from governing itself, largely on the basis that independence would for some reason ruin his memory of a favourite jigsaw puzzle from childhood.  Here's the sequel (it isn't in strict chronological order because otherwise it would be harder to follow) -

Tom Holland : Are the Scots morally superior to the English? A poll cited by Brian Wilson suggest we're all much the same.

Me : We're not morally superior to Canadians either, but that's not an argument for having Stephen Harper as our PM.

Tom Holland : You're not in a hugely successful 300 year old partnership with Canada, though.

Me : I presume you realise Yes voters don't share your view of it as being "hugely successful"?

Tom Holland : I do. Naturally, I think they're wrong.

Me : No wonder, you don't have to live with the nukes in your back-yard - and you almost always get the govt England votes for.

Tom Holland : Would the Tories have had to go into coalition without Scotland?

Me : No. Would we have noticed the difference?

Tom Holland : Probably - but that's not quite the point.

Me : What is the point? Scotland must be held hostage so that England can be dragged 0.03% leftwards by Nick Clegg?

Tom Holland : I'm sure people in Surrey were as resentful of Gordon Brown as people in Glasgow were of Margaret Thatcher. That's democracy.

Me : No, it's not democracy. It's a dysfunctional union. That problem can be sorted, and you don't seem to have a reason not to try.

Tom Holland : Nor do you share a small island with the Canadians.

Me : The UK isn't particularly small - it has almost 1% of the entire global population.

Tom Holland : Less than 1% sounds quite small to me!

Me : 1% of the world's population on a "small island"? As islands go, that's pretty big.

Tom Holland : No, by my reckoning, less than 1% is small.

Me : You need to get out more. There's a whole world of genuinely small islands out there.

Tom Holland : Your logic is devastating.

Me : But your sarcasm isn't. If Britain is a "small island", how many islands can you name with a bigger population?

Tom Holland : We are a small island relative to the large continental powers that dominate/will dominate the 21st century.

Tom Holland : The comparison is with China or the US, not Guernsey.

Me : I see. So "small island" is not a comparison with other islands, but with non-islands? We are therefore a large island?

Tom Holland : No. Australia is a large island. Greenland is a large island.

Me : Both with much smaller populations. Even in geographical terms, Britain spans one-ninth the length of the Northern Hemisphere.

Tom Holland : Your knowledge of geography is as impressive as your ability to miss the point.

Tom Holland : (responding to the 'dysfunctional union' tweet) Well, naturally, I disagree. Let's leave it at that.

Me : Yes, you always seem to leave it when the questions get difficult.

Tom Holland : You seem to me to be dealing in slogans, rather than substantive points. Doubtless you feel the same about me. So - enough.

Me : Rubbish. I asked you a substantive question about nuclear weapons last time and you instantly vanished.

Tom Holland : What question did you ask about nuclear weapons?

Me : "Inhuman weapons within 30 miles of where I live are not 'spin' - they're all too real. Who put them there, and why?"

Tom Holland : I grew up with a whole stash in my backyard. Didn't mean I wanted independence for Wessex.

Tom Holland : If any part of Gt Britain gets nuked, we're all in the s**t.

Me : The context of my question was your claim that Scotland already chooses its own govt. How can we veto nuclear weapons?

Tom Holland : Join CND?

Me : That's a pathetic response. Do you now accept that Scotland does not choose the way it is governed at present?

Tom Holland : Getting rid of nuclear weapons won't make Scotland any safer if they're simply removed to England. It's a British problem.

Me : Yes, it would make us safer. Neither is that the point - why should others choose whether Trident is located on the Clyde?

Tom Holland : It needs to be solved at a British level. I'm with you on getting rid of Trident. But it's a problem for us all in Britain.

Tom Holland : Of course Scotland chooses how it's governed. It has multiple layers of government, all elected.

Me : So how do we use those layers of elected [government] to eject Trident against London's wishes? That's my question. Joining CND won't help.

Tom Holland : I feel we're going round in circles, & TBH I can think of better uses of my time - such as doing the shopping. A bientôt.

Me : Translation: "Scotland cannot choose, I don't think it should be able to choose, but I can't admit that directly." Enjoy Tesco.

Tom Holland : A Parthian shot (at this point he links to a poll conducted by Tory billionaire Lord Ashcroft purporting to show that Scots are not as opposed to nuclear weapons as we think - an odd tactic given that it actually shows Scots are opposed to Britain having nuclear weapons by a margin of 48% to 37%)

Me : Well, let's put it to the test, shall we, and actually let the Scottish people decide? As opposed to, y'know, deciding for them?

* * *

There were a few points that I deliberately didn't respond to, because asking three questions at once would have let him off the hook and allowed him to choose which ones to 'notice'. As far as the question of whether removing Trident to England would make Scotland safer is concerned, of course the literal answer is "yes it would" - if Glasgow was the direct target of a nuclear attack, the population would be annihilated instantly, as opposed to having at least some opportunity to protect themselves from the atmospheric fallout that would be produced by an attack across the border. But that's also not the point. Having the democratic right as a country to decide whether we possess nuclear weapons or not allows us to contribute to the global drive to eliminate the existential threat posed by nuclear warfare. It's even open to question whether it would be feasible for London to maintain an independent nuclear 'deterrent' without being able to host it on the Clyde.

In any case, does the fact that London is closer to France than it is to Scotland mean that British nuclear weapons are a "Franco-British problem"? Or does nuclear fallout do the polite thing and stop at the English Channel in Tom Holland's world? And what about French nuclear weapons? Does the fact that Paris is closer to Brussels than it is to Biarritz mean that the French arsenal is a problem that must be solved at "Franco-Belgian-Dutch-German-Swiss level"? After all, all of these countries and more would be "in the s**t" if France was attacked. Where does this logic end?

Oh, and in case you're wondering, Great Britain is the third most populated island in the entire world, behind only Honshu in Japan, and Java in Indonesia. It is also the ninth largest island in the world in terms of geographical area (excluding Australia, which should properly be considered a continent). Tom Holland may think that pointing this out is silly, but if he's going to use emotive George Galloway-esque language such as "partitioning this small island", he's got to be able to justify his definition of "small".

The introduction to Tarkovsky's classic sci-fi film Stalker describes the USSR as "our small country".  I laughed at that one as well.

Why do ICM think that only 45% of Scotland's voting-age population is male?

This is something that I haven't really paid much attention to, so thanks very much to Calum Findlay for pointing it out.  In the datasets for their referendum polls, ICM are absolutely explicit about where they get the targets for their weightings from -

"Data were weighted to the profile of all Scottish adults aged 16+.  Data were weighted by sex, age, social grade and region. Targets for the weighted data were derived from Census 2011."

So what does the 2011 census say about the breakdown of Scotland's over-16 population by gender?

Female - 2,280,734 (52.08%)
Male - 2,098,338 (47.92%)

Essentially a 52-48 split in favour of women, then.  It's therefore a touch hard to understand why ICM weighted their sample for last weekend's referendum poll so that it looks like this -

Female - 54.74%
Male - 45.26%

As I always say in these situations, "pollsters may have their faults, but they're not blithering idiots".  ICM will have done this deliberately, and they'll have done it for a specific reason, but for the life of me I just cannot even begin to imagine what that reason could be.  As far I can recall, every other pollster is using something very close to the more obvious 52-48 weighting.  In case you're wondering, it's not because ICM think women are more likely to vote - these are the figures for the whole sample before turnout weighting was applied.  (And indeed they found that men are in fact slightly more likely to vote anyway.)

Although men are currently more pro-independence than women, adjusting the weightings so that men make up 2.66% more of the sample normally wouldn't make much difference.  But in the case of this particular poll, the roundings in the published figures worked against the Yes campaign, so simply getting the gender weightings right would be sufficient to reduce the rounded No vote after Don't Knows are excluded by 1%, and to increase the Yes vote by 1%.  In other words, the figures should be Yes 43%, No 57%.

And that's before we even take account of the fact that for a second poll in a row, ICM have far too few respondents who were born in Scotland, and far too many who were born in England.  Reweighting the sample to bring those numbers into line with the census data would reduce the No lead even further. (I make it Yes 44%, No 56%, although admittedly it was such a complicated calculation that my brain was turning to mush, so don't take those numbers as gospel!)

If I was going to hazard a guess, I would assume that ICM aren't even bothering to weight by country of birth, and although they've probably noticed that the figures don't tally up with reality, they're not addressing the problem due to 'institutional inertia'.  But the gender issue is much harder to explain, because getting the right number of men and women is one of the most basic tasks of any pollster in any poll.

Then of course there's the even bigger issue of the bizarre introductory question that ICM used, which may have unsettled people and influenced how they responded to the referendum question in the first place.  With almost every successive closer look, last weekend's poll comes across as even more of a shambles.

Friday, May 23, 2014

UKIP surge : what now?

If nothing else, the success of UKIP in the English local elections has been a PR disaster for Labour.  Without the emergence of a populist anti-establishment party led by a public schoolboy stockbroker, the routine protest vote against an incumbent government would have been hoovered up by Labour, who would have racked up a sizeable lead in the national popular vote.  That would have been built on candy floss, but nevertheless it might have created the illusion in some Scottish minds that Ed Miliband was heading towards Downing Street.  I haven't seen the BBC national projected vote shares yet (perhaps it's being revealed as I write this!), but if the changes reported in key wards are anything to go by Labour are going to have a lead over the Tories of somewhere in the region of 2%.  That is an absolutely hopeless position for them at this stage in the electoral cycle.

The flip side of all this, though, is the effect on the opinion polls of the UKIP surge in the coming days and weeks.  We know that most UKIP voters are disaffected Tories, so a snowball effect would have the potential of harming the Tories disproportionately and leaving Labour with a bigger lead (albeit on a very low share of the vote).  But the fact that UKIP have done so well against Labour in the north of England may mean that the rules of the game are changing rapidly.  If Farage's mob are no longer being seen as the Tory B Team in places like Sunderland and Hull, Ed Miliband's (and Blair McDougall's) worst nightmares may all have come true at once.

Scot Goes Pop crowdfunding appeal raises £3475

As the English local election results are proving so sluggish (although it's already clear they're an unmitigated calamity for Labour), I just thought I'd quickly take this opportunity to give you the final total for this blog's fundraiser. £3425 was raised on Indiegogo, and in combination with a very generous non-online donation that arrived by post yesterday, the grand total is an amazing £3475 - almost exactly £1000 more than the original target figure, which was reached within the first 24 hours.

It's testament to the genuinely organic grass-roots nature of the Yes campaign (as opposed to the utterly bogus "grass-roots" nature of Vote No Borders) that so many independent fundraisers like this are achieving their targets so quickly. I do still worry that this has been one of the less worthy ones, because to some extent it's simply funding me to continue doing exactly what I've been doing up to now without previously needing any funding. But as we all know, life does sometimes get in the way at the most inconvenient of moments, and the timing in this case has just been extremely unfortunate. Hopefully it isn't a zero-sum game, and bigger fundraisers such as the SNP's 'Double Your Donation' and National Collective's 'Yestival' won't have been adversely affected. As promised, I'll set aside some of the money for advertising, although I may now have to consider options other than Facebook - I got a shock two days ago when I tried to set up a second cheap ad, and was told that the expected reach was only a fraction of the figure for the first ad. I have a horrible feeling I was suckered in by the age-old "introductory price" wheeze! But I'll have a look around and see what the most cost-effective options are.

Once again, my heartfelt thanks to all 170 people who donated, and to the many people who publicised the fundraiser on social media and on other sites, and in particular to Tris, who did a big splash on Munguin's Republic about it. Thanks also to the people who sent supportive messages by email - I think (and hope!) I've responded to everyone. I'll put up the 'Backers' page as soon as possible, although I'll take my time over it, because I need to be careful that no-one who requested anonymity is accidentally included on the list.

So what have I learned from dipping my toes into the brave new world of crowdfunding? Mainly that there is no shortage of 'experts' and 'consultants' out there willing to help, simply out of the goodness of their hearts. Perhaps I shouldn't be too cynical - for all I know one or two of them may have been offering a genuine service. But I'm really not sure about this guy. If I ever hire a consultant, rest assured that he or she will be considerably less well-groomed than that. It's a point of principle.

Thursday, May 22, 2014

Ignore the siren voices - it's the SNP who are best placed to stop UKIP today

Just a quick warning in case anyone is being taken in as we speak by James Mackenzie's latest attempts on behalf of the Greens to claim that only they can stop UKIP in Scotland.  YouGov's "final Scottish poll" of which he speaks is no such thing - it's a subsample of a GB-wide poll.  Yes, it's a larger than usual subsample, but it's still a subsample.  So it's not possible to claim as James does that "the margin of error is bigger than with a normal 1000 person poll (up to 4.2%, rather than around 3%), but even so..." The margin of error is in fact incalculable, because the figures almost certainly won't have been weighted properly - ie. they'll only have been weighted on a GB-wide basis. What weightings were applied will have been based on YouGov's party ID system, rather than the 2011 vote recall they use for full-scale Scottish polls. That almost always leads to SNP identifying respondents being downweighted massively. In this poll, 165 SNP and Plaid Cymru identifiers were downweighted to count as just 104 'virtual' respondents.

The facts remain the same - not a single full-scale Scottish poll in this campaign has shown the Greens even close to winning a seat today. Most polls (including from YouGov) show that the SNP are best placed to stop UKIP, although there's certainly still a chance that Labour or the Tories could be the ones to pull it off. But if you vote Green you're not "voting tactically" at all - you're effectively abstaining on the question of whether UKIP should have a Scottish seat or not.

Maggie Chapman is a very fine candidate (and an asset for the Yes campaign), and if your number one priority is to have her as an MEP representing Scotland, then by all means vote Green - even though the chances of success look very slim indeed. But just be aware that it isn't going to stop David Coburn or UKIP.

Smoke me a Kipper, I'll be back for breakfast

I'm increasingly optimistic (but far from complacent) that the "Kippers" and their repulsive lead candidate David Coburn are going to just about fall short of taking a Scottish seat in tomorrow's election - and the icing on the cake is that the SNP look like the party best placed to stop them (although it may yet be Labour or the Tories).  South of the border, though, it's a very different story.  Two eve-of-election polls tonight show that the rest of the UK is on the brink of entering into a veritable Farage à trois -

Opinium European election poll (GB-wide) :

UKIP 32%
Labour 25%
Conservatives 21%
Greens 6%
Liberal Democrats 6%

YouGov European election poll (GB-wide) :

UKIP 27%
Labour 26%
Conservatives 22%
Greens 10%
Liberal Democrats 9%
Others 6%

Although the latter figures look like a virtual dead heat, they're not filtered by certainty to vote (unless YouGov have changed their procedures at the last moment). With Farage's supporters being more motivated than others, it's highly likely that we'll be looking at some kind of UKIP victory at the weekend when the votes are counted. What strikes me about both of these polls, though, is the relatively narrow gap between Labour and the Tories. The traditionally low turnout in Euro-elections means there's a greater chance of an upset, and if the Tories do end up outpolling Labour (even if it's the Tories in second place and Labour in third) it could well have an electrifying effect on the referendum campaign. In the recent ICM poll, the No lead fell to just 3% when respondents were asked to imagine how they would vote if they expected a Tory victory in next year's general election.

As for the race in Scotland, if the SNP outpoll Labour by a significant amount, it will go a long way towards proving that YouGov's Scottish sampling and weighting for GB-wide polls is deeply flawed. Most of the firm's Scottish subsamples for the European election have put Labour in the lead, while their full-scale Scottish poll (which used a different if still dubious weighting procedure) had the SNP in a very narrow lead.

Ideally, if this election is to provide some supporting evidence that Yes-friendly pollsters like Survation are getting it broadly right, we'd be looking to see an SNP vote in the mid-thirties or above. That's admittedly a very tall order - it would be an all-time record (beating the 32.6% share of the vote in 1994), and it would mean doing significantly better than in 2009 when the main opponent was a Brown-led Labour party limping towards general election defeat. An SNP vote in the low thirties or below might be a sign that the methodology of No-friendly pollsters such as YouGov is closer to the mark.  Having said that, the gap between the SNP and Labour will also be an important clue - a sub-30 showing for the SNP would be far less troubling if Labour were trailing several points lower.

Wednesday, May 21, 2014

Wisdom on Wednesday : Popular sovereignty

"And what if that other voice WE ALL KNOW SO WELL responds by saying 'We say no, and we are the state'? Well, we say yes, and we are the people!"

Canon Kenyon Wright, chairman of the Scottish Constitutional Convention, speaking at the body's opening meeting. The "we" was an ironic reference (and instantly recognised as such by the audience) to Mrs Thatcher's use of the royal "we" when announcing that she (they?) had become a grandmother.

Nice try, George Eaton, but it's time to reacquaint you with referendum polling reality

Well, we might as well all pack up and go home, chaps.  An oracle walks among us, and he has decreed that the best the Yes campaign can hope for is a narrow defeat leading to Devo Max.  And the name of this new rival to Nostradamus?  Er, well actually it's George Eaton, the tediously tribal Labour hack who also declared two months out from the 2011 Holyrood election that his party were coasting to victory, and that Iain "the Snarl" Gray was about to become our First Minister.  Result?  SNP landslide.

Someone asked me earlier today if I could respond to Eaton's latest fairy-tale reimagining of the opinion polls.  It turns out that comments on his New Statesman piece are already closed (after one day!) so I'll do it here instead.

"Labour MPs might be increasingly anxious about their party's performance in the national polls (today's Populus survey has them a point behind the Tories) but their spirits have been lifted by the latest numbers on Scottish independence. After narrowing for months, the polls have begun to move in the No campaign's favour."

Nope. "The polls" have not done any such thing. With the sole exception of the ICM poll, every single poll that has been published recently has either shown movement to the Yes campaign (extremely big movement in the case of Progressive Scottish Opinion), no movement at all, or movement to No that is so tiny that it is most likely to be margin of error 'noise'. As for the ICM poll itself, that could easily be one of the more extreme examples of 'noise' - if the true No lead according to ICM's methodology is roughly 7% or 8% (and two polls from the firm so far this year have shown exactly that sort of lead), then it would be quite possible for the standard margin of error to produce a 3% lead one month and a 12% lead the next without there having been any actual movement in opinion. And that's before we even mention ICM's bizarre methodological change which we only found out about more than 24 hours after the poll was published, and which means that it's impossible to make a direct comparison with previous polls in the series. To put it in a nutshell - without corroboration from at least one other pollster, the sensible assumption is that the trend shown by ICM is not real. Two pollsters have already had the opportunity to back ICM up - Panelbase and Survation both conducted polls that partially overlapped with ICM's fieldwork, and neither showed statistically significant change. Other pollsters will have the same opportunity in the days to come, but as of this moment there is literally no convincing evidence of any movement back to No whatever.

"while another by Panelbase (the Yes campaign's pollster of choice) put it [the No lead] up from five points to seven."

Which is precisely one of the statistically insignificant changes I referred to earlier, but as it happens even that is exaggerated. As I pointed out yesterday, if you look at the unrounded Panelbase numbers the No lead has actually only increased by 0.8%, from 5.7% to 6.5%. I don't know if there's a word for something that is even more insignificant than an utterly insignificant thing, but if there is, that word very neatly describes the statistical irrelevance of the increase in the No lead that Panelbase have just reported.

"Across the six main pollsters, the No campaign's average lead now stands at 14 points."

Actually, on a point of pedantry, it stands at 13 points. Eaton helpfully shows his working in inflating the number - he links to a tweet from "Jackanory" Jim Murphy that once again peddles the brazen lie that the recent Progressive poll showing a 9 point drop in the No lead was not in fact a Progressive poll at all, but was instead a YouGov poll showing a 6 point increase in the No lead. Just to reiterate the truth for the umpteenth time - the most recent polls from BOTH Progressive and YouGov show a DECREASE in the No lead, not an increase. YouGov's last poll was for Channel 4 News, and it showed the No lead narrowing from 15 points to 14 - a new low for the campaign. Progressive's poll was for the Sunday Mail, and it showed the No lead plummeting from 29 points to 20 - again, easily a new low for the campaign from the firm that used to be by far the most No-friendly pollster.

As for Eaton's unspoken implication that the average No lead has just dramatically solidified, in fact it has only recovered to a position that is 2.1% higher than its all-time low, which it sunk to just a few weeks ago. That very limited recovery is almost entirely due to the changes in the ICM poll, which as already stated must be regarded with suspicion - a) because no other pollster has replicated the trend, and b) because of the big alteration in methodology. In other words, the balance of probability is that No are in fact still stuck at their lowest level of support so far, and that Yes have successfully consolidated the gains they made during the winter.

"A narrow defeat might allow the SNP to press for devo max (and even to revisit the independence question at some point) but a defeat it will be."

Hmmm. Do you think we should ask First Minister Gray for a second opinion before we abandon hope completely?

*  *  *

I haven't been able to track it down again (I may be looking on the wrong thread) but there was a comment on Wings last night from someone who claimed to have it "on very good authority" that the unweighted results of the UK government's notorious secret Ipsos-Mori mega-poll were Yes 36%, No 48%.  If the weighted figures are close to that (and if anything Ipsos-Mori's weightings have tended to boost Yes slightly), then it would mean that the No lead of 25 points in the last published Ipsos-Mori poll has more than halved. Obviously there's no way of telling if the claim is true, but it certainly has the ring of plausibility to it - the rumours that Yes were in the lead never seemed very likely given Ipsos-Mori's track record as the most No-friendly BPC pollster, but this kind of whopping reduction in the lead would be entirely consistent with Westminster's determination to keep the poll under wraps.

Such a big turnaround from this campaign's only telephone pollster would mean one thing and one thing only : Game On.

Tuesday, May 20, 2014

Who will weep for the Liberal Democrats this week?

As long-term readers may remember, I've voted for a whole array of weird and wonderful political parties in American elections (including a Vermont "separatist" party, you'll be thrilled to hear).  But in this country, rather boringly, I've only ever voted for the SNP.  I have a feeling that only independence offers the slightest chance of "liberating" me from that habit, because until and unless it happens the SNP will always look like the most rational choice.

However, I did once vote for the Liberal Democrats in a school mock election.  It may seem a rather quaint idea now, but back in those days I had the genuine impression that the Lib Dems were the most radical party on constitutional reform, more so even than the SNP.  I remember hearing Russell Johnston speaking about the state effectively withering away within Europe, being replaced by tiers of governance enjoying equal prestige, of which none would have absolute sovereignty vested in them, even on a theoretical basis.  So in Scotland that would mean four tiers of government sharing sovereignty - local government, Holyrood, Westminster and Brussels.  To the idealistic teenage me, that sounded like a more modern and forward-thinking vision even than independence within an interdependent Europe.

Although I moved away from the Lib Dems long ago, it's actually only been relatively recently that I've realised that they don't actually believe in any of this stuff - it's all just words.  (I'm only talking about the party leadership, by the way. I'm sure that many of the activists and rank-and-file members have much stronger convictions.)  With the enviable position of holding the balance of power in a hung parliament for the last four years, they've actually had the chance to do something to bring their vision closer to fruition, but almost every step they've taken has had the opposite effect.  They've propped up the most anti-European government this country has seen since entering the Common Market, one that is doing what would have seemed unthinkable just a decade ago - inching us closer to the EU exit door.  They moved heaven and earth to block a second question in the independence referendum, meaning the only option voters aren't allowed to choose in September is the one the Lib Dems are supposed to support.  And having achieved that perverse objective, they haven't taken the nuanced stance on the straight Yes/No independence question that the logic of their "federalist" beliefs demands, but have instead gone gung-ho for a No vote irrespective of consequences.

Their actions betray them.  When it really comes down to it, tribalistic British nationalism trumps everything for the Lib Dem leadership - it trumps federalism (a Yes vote would produce an outcome much closer to federalism than a No vote), it trumps electoral reform (a Yes vote would ensure that every tier of government in Scotland is elected by proportional representation), it trumps repugnance at an unelected second chamber (a Yes vote would lead to a wholly elected national parliament for Scotland, with no equivalent to the House of Lords), it trumps support for a written constitution and reform of the royal prerogative (only on offer with a Yes vote). Almost every constitutional reform that Lib Dem activists have pounded the streets to evangelise for over the last few decades is on the ballot paper this September - and their leadership is telling them to turn it all down.  Forever.

There's an opinion poll out from Opinium today suggesting that the Lib Dems will take just 5% of the vote in the European elections on Thursday.  That would probably be just about enough to ensure that they win no seats at all across the UK, and move them closer to the fringe status throughout this island that they've already been reduced to at Holyrood (Willie Rennie leads a parliamentary group that is smaller than the Scottish Socialist Party had in 2003).  Unfortunately, their relative strength at Westminster means that they won't become an out-and-out fringe party this side of the referendum, but anything that moves the morale-sapping voices of these phony "radicals" further to the margins can only be a good thing.

*  *  *

For what it's worth (not very much), here is the result of Opinium's small and unweighted Scottish subsample in the European election poll -

SNP 43%
Labour 23%
UKIP 14%
Conservatives 11%
Greens 5%
Liberal Democrats 3%

In terms of seats, that would work out as three for the SNP, two for Labour and one for UKIP.  Under this rather improbable scenario, the best hope of stopping UKIP would be to vote Tory - which hopefully illustrates further why attempts at "tactical voting" under a pure list PR system are soul-destroying and counter-productive.

Monday, May 19, 2014

Concerns mount over ICM's sudden change in methodology

The datasets for ICM's referendum poll have been published, and as a result it's become clear that the methodological changes have gone way beyond the one flagged up by John Curtice and trailed by Martin Boon last month, namely the introduction of a likelihood to vote filter.  In the April poll from ICM that produced a virtual dead heat (a No lead of just 3%), the referendum question was asked first.  But in this new poll showing a bigger 12% No lead, the referendum question was asked third - which ought to set alarm bells ringing immediately, because we know that responses to later questions can be substantially influenced by the wording of earlier ones.  Indeed, John Curtice has spent a fair bit of the last few months rubbishing a poll conducted last summer by the BPC-affiliated firm Panelbase, simply on the basis that it asked the referendum question third.  That poll of course showed Yes in a 1% lead.  A few cynics might wonder why he pounced on methodological bad practice in a poll that showed movement towards Yes (and in retrospect he was probably right to do so, because it was completely out of line with other polls), but hasn't said a word about the same problem in a poll that appears to show a favourable trend for No.

It is of course necessary to look at the wording of the two questions that precede the referendum question before jumping to the conclusion that they might be distorting the result.  The second question is entirely innocuous - it simply asks how certain people are to vote, and as that's a dry, technical question there's no problem with asking it before the main question (other pollsters do the same).  But the first question is a different matter entirely.  It asks -

"Thinking about the referendum on independence for Scotland, do you feel comfortable or uncomfortable being asked which way you might vote?"

Frankly it's hard to think of a dodgier question to ask right at the start, because when respondents come to the referendum question a few seconds later they'll be thinking to themselves, "ah, this is what some people are uncomfortable about being asked", which is bound to influence their reaction in at least some cases. Indeed, a fair chunk of people will have already indicated that they ARE uncomfortable about being asked, which arguably gives them implicit permission to do one of two things - to answer 'Don't Know' even though they do know how they will vote, or to give a completely dishonest answer.

If there's been an explanation offered for the introduction of the 'comfortable' question, and for its positioning within the question sequence, I haven't been able to track it down so far. My best guess is that this constitutes ICM's 'investigation' into the possibility of 'Shy No Syndrome', which Martin Boon revealed last month was on its way. It was already a matter of huge concern that ICM distrusted their results simply because they were so favourable for Yes, and seemed to be actively looking for excuses to adjust the Yes vote downwards, rather than open-mindedly testing for any bias that might be occurring in either direction. Even so, I naively assumed that they would be able to carry out their 'investigation' in a manner that did not compromise the integrity of this month's poll, but sadly that does not seem to have been the case.

So what did this experiment discover? If the point of asking for people's comfort levels is the assumption that some of them are answering dishonestly due to social pressure, what ICM would have been looking for to prove their theory about 'Shy No Syndrome' is evidence that a greater number of people who say they are voting Yes are uncomfortable about being asked the question. In fact, it turns out that the opposite is true. No fewer than 70% of people who say they are voting Yes are "very comfortable" with being asked the question, compared to just 52% of people who say they are voting No. Just 5% of people who say they are voting Yes admit to being uncomfortable, compared to 9% of people who say they are voting No. Whether this disparity came about because ICM effectively gave people 'permission' to feel uncomfortable, and as a result a chunk of respondents who would otherwise have said Yes switched to No (thus distorting the headline referendum figures), is anyone's guess. But given that this very peculiar methodological change coincides with an increase in the No lead that two other pollsters have failed to replicate, it's an obvious suspicion to raise.

Scottish Skier suggested that I should remove the ICM poll from the Poll of Polls due to this bad practice. I can't really do that, because the whole point of the exercise is to throw all the wildly varying methodologies from BPC pollsters into a pot and see what the blend produces. And this certainly isn't the first time that a BPC pollster has used dodgy methodology - remember YouGov's embarrassingly biased preamble about Scotland "leaving the United Kingdom"? But it's undoubtedly a big concern, and it may well be distorting the trend in the Poll of Polls. The best way of judging the real trend for now is to look at recent polls conducted without a change in methodology - and TNS-BMRB, Panelbase and Survation are all showing a relatively stable position, with Yes consolidating the big gains made over the winter.

Incidentally, there are a couple of pieces of good news from the ICM datasets - the Yes vote on the unrounded figures after Don't Knows are excluded is 42.4%, which is obviously a touch higher than the rounded figures for publication suggested. And as seems to be the case every month, the Yes vote rises a touch (this time to 43.2%) after Don't Knows are asked how they are leaning.

ICM poll : SNP on course to deny UKIP a seat in the European Parliament

The Scotsman have published further details from their ICM poll, and there must be a fair chance that this will be the final full-scale poll of Scottish voting intentions for the European Parliament prior to the election on Thursday.

SNP 36% (-1)
Labour 27% (-1)
Conservatives 13% (+2)
UKIP 9% (-1)
Liberal Democrats 7% (n/c)
Greens 7% (+3)

That would translate into three seats for the SNP, two for Labour and one for the Tories - effectively meaning that the Lib Dems would lose their only seat to the SNP, who currently have two.  Under this scenario, it would be the SNP who take the last of the six seats and thus perform the almost mythically heroic role of "the party that stopped UKIP".  There are other scenarios in which it might be Labour or the Tories who assume that role, but barring something miraculous it won't be the Greens or the Lib Dems.  So a "tactical vote" for the Greens in the hope of stopping UKIP still looks utterly counter-productive.

In any case, the number one priority for any SNP supporter must surely be to ensure the SNP win the popular vote, because failure to do so might drain momentum away from the pro-independence campaign at a critical stage.  The party may look assured of top place on these numbers, but that could yet prove deceptive - YouGov are showing a much less clear-cut position, and previous European elections have often confounded predictions due to very low turnouts.

It's fascinating that the SNP's vote is virtually identical to last month's in spite of the change in referendum voting intentions.  There are two ways of looking at that - on the one hand it means that we can't put the referendum figures down to there being too few SNP supporters in the sample, but on the other hand it underlines that the referendum race is becoming increasingly decoupled from regular voting intention.  That suggests there's no automatic reason to be suspicious of a Yes-friendly referendum poll just because the SNP are doing particularly well in supplementary questions.  That said, it would still be a cause for some concern if the SNP's performance on Thursday doesn't live up to the forecasts of the broadly Yes-friendly pollsters.

Sunday, May 18, 2014

Will Andrew Marr please stop inventing his own facts?

There is a section of the BBC's guidelines on impartial coverage of the referendum campaign which specifically deals with how opinion polls should be handled by presenters and journalists. To paraphrase what is said, polls should only be mentioned sparingly, and presenters should add a bit of context along the lines of "that's out of line with what we've been seeing recently" in order to ensure that an outlying poll is not given undue prominence. But Andrew Marr seems to have misinterpreted that as an instruction to invent an entirely fictional "context" in order to hoodwink his viewers into thinking that an outlying trend shown by a single poll is in fact typical of other polls. I gather he mentioned the ICM poll in his review of the papers this morning and claimed that a lot of polls had been showing the same thing recently. Let's look at the evidence, shall we? Other than the ICM poll, this is what we've had since Easter -

Survation have shown the No lead dropping from 10 points to 8, followed by a return to the status quo ante of 10 points. So no change there at all.

YouGov have shown the No lead dropping from 15 points to a new low for the campaign of 14 points. Yes, that poll was widely misreported as being good for the No campaign on the basis of an 'apples and oranges' comparison with the numbers from other pollsters, but Marr has a duty as a public service TV presenter to look at the facts, not the spin.

Panelbase have shown the No lead increasing from 5 points to 7 - a tiny increase that could very easily be (and probably is) margin of error 'noise'.

Progressive Scottish Opinion have shown the No lead plummeting from 29 points to 20, albeit with a very long gap between the two polls in question. The No campaign's propaganda has tried to con people into thinking that the new Progressive poll should for some reason be compared with the last YouGov poll rather than the previous poll by the same company, but again, Marr has a duty to cut through the propaganda and look at the facts.

TNS-BMRB have shown no change in the headline No lead of 12 points in their most recent poll, but the raw Yes vote is at its highest level since a major methodological change was introduced several months ago, and on the unrounded figures the No lead has fallen (albeit fractionally) to its lowest level of the campaign so far.

If Marr is aware of all that and still thinks he can justify his claim this morning, then evidently the laws of arithmetic must function very differently in his reality.

* * *

The datasets for the Panelbase poll are up already. It's amazing - they used to be very slow compared to other pollsters, now they seem to be faster than anyone! The first thing to say is that the No lead on the unrounded numbers is somewhat lower at 6.5%, the increase in the No lead is just 0.8% (as opposed to the 2% misleadingly suggested by the rounded numbers), and the raw Yes vote has actually gone up. That makes it even more likely that the tiny increase in the No lead is just margin of error noise, and indeed that the ICM poll is an outlier (in terms of the trend, if not necessarily the headline numbers).

Should Scotland be an independent country? (Figures rounded to one decimal place.)

Yes 40.1% (+0.5)
No 46.6% (+1.3)

With Don't Knows excluded -

Yes 46.2% (-0.5)
No 53.8% (+0.5)

There is also a follow-up question demonstrating that undecided voters are currently leaning (albeit only narrowly) towards a Yes vote. If we "just for a bit of fun" add in their preferences to the overall figures, this is what we end up with after the small remaining number who wouldn't vote at all are excluded -

Yes 47.2%
No 52.8%

Yeah, but "panic over", right?

By the way, it seems highly suspicious to me that Panelbase have not added the preamble they used to the datasets.  Unless no preamble was used at all (unlikely), that may well mean that they've gone back to using their old, subtly biased preamble, probably due to the fact that the poll was commissioned by an anti-independence client.  Whether that's the case or not, such a lack of transparency from a BPC pollster is certainly highly regrettable.  [UPDATE : Calum Findlay took part in the poll and has confirmed the neutral preamble was used.]

John Curtice is in a privileged position, because unlike most of the rest of us he has already seen the unpublished ICM datasets. On the basis of that, he's made an observation that the Yes vote would have fallen further in the new ICM poll if it hadn't been for a methodological change that for the first time takes account of likelihood to vote. I must say that comment troubles me, because ICM have been constantly tweaking their methodology over the last few months, and if you're going to make a direct long-term comparison you really need to unravel all of those changes and take the methodology back to "manufacturer's settings", so to speak. Cherry-picking one particular change gives a misleading impression, because it's highly unlikely that all of the changes are working in favour of the Yes campaign.

Panelbase confirms referendum remains on a knife-edge as No campaign lead by just 7%

In perhaps the most misjudged comment of the day so far (although there's still plenty of time), Mike Smithson of Political Betting reacted to the ICM poll by declaring "panic over", and by giving our masters in Westminster his personal blessing to forget all about the Jockland distraction and get on with the much more serious business of the European elections.  Just one snag, though - he was apparently oblivious to the fact that a Panelbase poll was published at the same time as ICM, which showed the No campaign with a lead of just 7%.  That's somehow not quite what I picture when I try to imagine what the end of panic at McDougall Central would look like.

Should Scotland be an independent country?

Yes 40% (n/c)
No 47% (+2)

I don't yet know what the figures are with Don't Knows excluded, but a rough calculation suggests it's most likely to be Yes 46% (-1), No 54% (+1).

In combination with the Survation poll of a few days ago, this is a very strong pointer (albeit not quite absolute proof) that the rise in the No lead seen in the ICM poll is an artifact of the margin of error, rather than something real.  The fieldwork for the three polls will have been conducted at roughly the same time, and it's fantastically improbable that both Panelbase and Survation would have failed to pick up the trend shown by ICM if it actually reflected the reality on the ground.  The recent poll from TNS-BMRB also failed to replicate the ICM trend (quite the reverse - it showed the No lead at its lowest level of the campaign so far), although admittedly that's of less help because the fieldwork is slightly out-of-date.

Taking all of the available evidence together, there are only really two realistic possibilities - a) there has been no movement at all recently, or b) there has been a very small increase in the No lead in the last two or three weeks, probably no bigger than 1% or 2%.  The only reason for entertaining the latter possibility is that this poll breaks a sequence of three Panelbase polls in a row to show a No lead of exactly 5% - but of course even if public opinion had remained absolutely static, it was statistically impossible for that sequence to continue due to the margin of error.  It may just be random chance that this poll has a slightly higher lead rather than a slightly lower lead.  [UPDATE, 4pm : The unrounded figures from Panelbase show that the raw Yes vote has actually increased, and that the No lead has only increased by 0.8%, rather than the 2% misleadingly suggested by the rounded percentages.  That makes it even more likely that the changes are just margin of error noise, and that the ICM poll is an outlier in terms of the trend it shows.  Future polls may prove me wrong, but at the moment my best guess is that there has been no movement back towards No whatsoever.]

That said, one of the fascinations of this poll is that it's the first Panelbase poll in several months to have been commissioned by an anti-independence client.  All of the firm's previous polls for the Sunday Times used a subtly biased (and for a long time highly secret) preamble to the referendum question, whereas all of their recent polls for Yes-supporting clients have used a scrupulously neutral preamble.  So in order to interpret the result of the new poll correctly, it's vitally important to take account of which preamble was used - something which may not became clear until the datasets are published.  If it was the old preamble, then this poll is not directly comparable with the ones showing a 5-point lead, and the most recent poll it can be properly compared to is the one in early February showing a 12-point lead.  But let's hope common sense has prevailed, and that Panelbase have decided to use the neutral preamble from now on regardless of client. [UPDATE : I was a bit troubled that the Panelbase datasets do not reveal the preamble used, but Calum Findlay took part in the poll and has confirmed the neutral preamble was used.]

Either way, though, "Better Together" have repeatedly made clear that they refuse to acknowledge the existence of Panelbase polls conducted by the SNP, Newsnet Scotland, Wings Over Scotland and Yes Scotland, so we can all look forward to McDougall and co mourning the fact that their lead has just dropped a hefty 5% since the last "valid" Panelbase poll.  Unless of course they're about to move the goalposts yet again.  But I can't believe they'd do that - these guys have integrity.

Perhaps the most important point that needs to be made is that the No lead is still below Panelbase's previous normal range of 8-13% - which remained in place as recently as late February, long after other pollsters had started showing a post-White Paper surge for Yes.  So if Panelbase are to be believed, Yes have actually made net progress since the end of winter - a fact which inconveniently refuses to tally with the Gospel according to Professor Curtice.

This is the first poll in which Panelbase have sought a breakdown of voting intention by country of birth, and that has turned up an uncannily similar picture to the one in last month's ICM poll.  Respondents who were born in Scotland favour independence by a 2% margin, while a surprisingly hefty minority of English-born respondents (more than a quarter) are also now in the Yes column.  However, the No vote among English people is somewhat higher than ICM reported.  But of course the most important thing to emerge from the ICM poll was that the sampling was all wrong, and that English people were being significantly over-represented, thus artificially increasing the No lead.  It'll be fascinating to see whether Panelbase's sample is more representative (or indeed has been specifically weighted by country of birth).

*  *  *


Obviously two polls overnight showing an increase in the No lead was always bound to feed into this update of the Polls of Polls, but apart from the fact that these changes may be illusions caused by the margin of error, the other crucial caveat that needs to be borne in mind is that Ipsos-Mori are still represented in the sample by a poll conducted in late February that gave No a handsome lead, whereas there are very strong indications that the firm's more recent secret mega-poll for the UK government showed a much more favourable position for Yes.

As an aside, this is one of those moments that shows up the flaws in the method used by the ScotCen and Financial Times Polls of Polls. The Yes vote in the ScotCen figures (which excludes Don't Knows) currently stands at 43%. The average Yes vote in these two new polls is roughly 44%. So ScotCen may well end up reporting a decreased No lead off the back of two polls that actually show an increased lead!  [UPDATE, 4pm : That isn't how it worked out, but presumably only because favourable polls for Yes just happened to drop off the other end in the rolling average.]

MEAN AVERAGE (excluding Don't Knows) :

Yes 42.0% (-1.1)
No 58.0% (+1.1)

MEAN AVERAGE (not excluding Don't Knows) :

Yes 35.0% (-0.8)
No 48.3% (+1.0)

MEDIAN AVERAGE (excluding Don't Knows) :

Yes 42.3% (-0.7)
No 57.7% (+0.7)

(The Poll of Polls is based on a rolling average of the most recent poll from each of the pollsters that have been active in the referendum campaign since September 2013, and that adhere to British Polling Council rules. At present, there are six - YouGov, TNS-BMRB, Survation, Panelbase, Ipsos-Mori and ICM. Whenever a new poll is published, it replaces the last poll from the same company in the sample. Changes in the Poll of Polls are generally glacial in nature due to the fact that only a small portion of the sample is updated each time.)

Here are the long-term trend figures, with the updates prior to Easter recalculated to exclude the inactive pollster Angus Reid...

The No campaign's lead in the Poll of Polls mean average (not excluding Don't Knows) :

Sep 2013 - 21.6%
Sep 2013 - 21.4%
Sep 2013 - 19.4%
Oct 2013 - 18.8%
Oct 2013 - 18.4%
Oct 2013 - 18.2%
Nov 2013 - 18.4%
Nov 2013 - 18.0%
Dec 2013 - 17.0%
Dec 2013 - 16.8%
Dec 2013 - 16.4%
Jan 2014 - 14.4%
Jan 2014 - 14.2%
Jan 2014 - 14.2%
Jan 2014 - 15.2%
Feb 2014 - 15.0%
Feb 2014 - 15.5%
Feb 2014 - 15.5%
Feb 2014 - 13.7%
Feb 2014 - 13.3%
Feb 2014 - 14.2%
Mar 2014 - 14.2%
Mar 2014 - 14.5%
Mar 2014 - 14.5%
Mar 2014 - 14.7%
Mar 2014 - 13.8%
Mar 2014 - 13.0%
Mar 2014 - 12.5%
Apr 2014 - 12.5%
Apr 2014 - 12.7%
Apr 2014 - 12.7%
Apr 2014 - 12.3%
Apr 2014 - 11.4%
May 2014 - 11.2%
May 2014 - 11.2%
May 2014 - 11.5%
May 2014 - 13.3%

Support for independence at 42% in new ICM referendum poll

From the moment a few hours ago when the Scottish Tory leader gloated that she was "looking forward" to this month's ICM poll, it was obvious that it was going to show at least some kind of increase on the wafer-thin No lead seen last time around.  But the big question was just how high would the No lead have to be to justify Tory celebrations?  We now know the answer, and it appears that "bad is the new good" for the No campaign, because they are getting excited about exactly the sort of poll results that used to have them screaming "bias" when Panelbase were producing them last year -

Should Scotland be an independent country?

Yes 34% (-5)
No 46% (+4)

With Don't Knows excluded, it works out as...

Yes 42% (-6)
No 58% (+6)

Contrary to the predictable but rather silly spin in the Scotland on Sunday, these figures do not necessarily mean that support for independence has decreased or that opposition to independence has "recovered".  The No lead reported here is within the range that ICM has shown thus far this year, of between 3 and 12 points.  The likelihood is that the last poll from the firm was on the high side for Yes due to normal sampling variation, and that we are now seeing a reversion to the mean - or more likely to something quite a bit higher than the mean.  Unless other pollsters show a significant increase in the No lead in the days and weeks to come (and both Survation and TNS-BMRB singularly failed to do so earlier this week), the changes in this poll will be safely tucked away in the file marked "margin of error illusion".

It's interesting, though, that ICM have proved more volatile than other pollsters.  They've certainly mucked around with their methodology more than others, changing the broad age categories that they use for their weighting procedure at least twice so far this year, and in their last poll they effectively started assuming a 100% turnout by dramatically upweighting non-voters from 2011, thus increasing the reported number of undecided voters.  Ironically, the latter change harmed Yes slightly, and without it the No lead would have fallen even further - so there would actually have been greater volatility.  However, the bottom line is that the more methodological changes there are, the less meaningful it is to make direct comparisons with previous polls.  Time will tell if further tweaks have been made in this poll, although it's certainly troubling that Martin Boon in his commentary last month almost seemed to be looking for an excuse to introduce a mechanism that would artificially boost the No vote.  He had apparently fallen for propaganda from anti-independence campaigners suggesting that No voters are more likely to lie to pollsters about their voting intentions - a claim for which zero evidence exists, and if anything the opposite is much more likely to be true. However, Boon merely suggested that ICM were going to do some research into the matter, so hopefully there's been no jiggery-pokery in this particular poll.

ALERT!  ALERT!  "Better Together" are playing silly buggers yet again : In the wake of the ICM poll, McDougall Central have tweeted a statistical graphic purporting to show that six different pollsters are either suggesting an unchanged No lead, or an increased No lead.  At first glance I thought there was something very fishy about it (well, none of us are going to faint in amazement at that, are we?) and sure enough, the explanation is contained - quite literally - in some hilarious small print at the bottom of the image...

"Source - latest poll by regular pollsters of voting intentions, comparison with previous poll.  YouGov compared with YouGov for Progressive Partnership."

In plain English, what they mean is that they're brazenly pretending that YouGov, who showed a 1 point decrease in the No lead in their most recent poll, are actually showing a 6 point increase in the No lead.  Their flimsy excuse is that the fieldwork for Progressive Scottish Opinion was conducted by YouGov, and that they can therefore count it as a YouGov poll.  This in spite of the fact that YouGov have nothing whatever to do with the weightings that Progressive apply to the raw data, which even the dogs on the street know is much more favourable for No than YouGov's own procedures.

Talk about trying to have your cake and eat it.  It's doubtful whether a non-BPC pollster like Progressive should even be taken into account, but if they are to be included it means that two out of seven pollsters are currently showing a decreased No lead in their most recent poll - and in the case of Progressive the decrease is a whopping 9%.  To get around that little problem, the No campaign are pretending that YouGov and Progressive are exactly the same pollster.  How can anyone take these chancers seriously anymore?

UPDATE : I'm holding off on updating the Polls of Polls (which I'll do in a fresh post) until we've heard the result of the new Panelbase poll.  The Sunday Times seem to have already revealed that the headline Yes vote is unchanged on 40%.  We're still waiting on the figure for No, but that will presumably be in the same ball-park as their 45% share in the last poll (unless of course there has been a dramatic increase or decrease in the number of undecideds).  When taken in conjunction with the Survation poll a few days ago, that would significantly increase the chances that the change shown in the ICM poll is an artifact of the margin of error rather than something real.