[UPDATE, 11pm : The Survation datasets are now out, and show that viewers in Scotland think Nicola Sturgeon won the debate by a massive margin of 68% to 17%. More details can be found HERE.]
Here are the Britain-wide numbers...
Who do you think 'won' the debate? (Survation, respondents across Britain) :
Ed Miliband 34.7%
Nicola Sturgeon 31.1%
Nigel Farage 27.1%
Natalie Bennett 4.7%
Leanne Wood 2.4%
Even though a close second for a 'wicked separatist' is absolutely astonishing in any Britain-wide poll, my strong suspicion is that it was even better than that. Survation was the least favourable for Sturgeon of the four firms that conducted instant polls after the first debate, and it seems likely that YouGov in particular would have had her well ahead tonight.
UPDATE : Even Survation have Nicola Sturgeon clearly ahead among Britain-wide respondents when the question is asked in a slightly different way...
Putting aside your own party preference and basing your answer on what you saw or heard during the programme, which one of the 5 leaders do you think performed the 'best'? (Survation, respondents across Britain) :
Nicola Sturgeon 35.2%
Ed Miliband 29.3%
Nigel Farage 25.5%
Natalie Bennett 5.3%
Leanne Wood 4.7%
It's probably the 'putting aside your party preference' bit that makes the difference here - obviously there are far more Labour than SNP voters across the whole UK, so if respondents aren't asked to set that aside, it leaves Miliband with an in-built advantage.
After the first debate, YouGov used "leaving aside your own political preference" in the wording to their headline question, which probably goes a long way to explaining why they reported Sturgeon as the clear winner when other firms didn't. Another factor was that they included more undecided voters in their sample.
Thursday, April 16, 2015
Here's how the Lib Dems magically get themselves into the lead in (some) of their comfort polling
Slightly surprisingly, the Liberal Democrats have released the datasets for the internal poll of East Dunbartonshire that they leaked yesterday - one of what Ashcroft famously referred to as their "comfort polls". So they've helpfully made it very easy for us to spot the working of the conjuring trick which has somehow got them (just about) into the lead in the poll, in spite of the word on the ground being that they're well behind, and probably not even in second place.
Here's how it was done...
* The results were weighted by 2010 vote recall. On the headline numbers, this resulted in respondents who said they voted SNP being weighted down from 53 to 33 (a drop of almost two-fifths), while respondents who recalled voting Lib Dem were upweighted from 73 to 90. Assuming that a significant proportion of people are probably getting their 2010 and 2011 votes mixed up, this factor alone is sufficient to introduce a huge distortion, and to transform what would have been a comfortable SNP lead into a small Lib Dem lead.
* No other form of political weighting was added to help balance out any distortion from the 2010 weighting (a practice used by some other pollsters, albeit admittedly not Ashcroft). Respondents were asked how they voted in the independence referendum, producing too big a lead for No, and yet the headline voting intention figures were not weighted by recalled referendum vote. Again, that alone would have been sufficient to put the SNP in the lead.
* The poll departs from standard good practice by not asking the headline voting intention question at the start of the question sequence. It's in fact asked fifth. The big problem is with Question 4, which names the local candidates and asks respondents to rate them. Unsurprisingly, this works in Jo Swinson's favour, because only 3.3% of the sample have not heard of her, compared to 49.7% who haven't heard of SNP candidate John Nicolson. (Although Mr Nicolson is a television personality, he's been off our screens for quite a while, and is probably more recognisable for his face and voice than for his name.)
* When the voting intention question is finally asked, it's posed like this : "If the general election was tomorrow, how would you vote in the East Dunbartonshire constituency knowing who is standing?" (my emphasis). People try to keep their responses to polls logically consistent, and if you've just said that you like Jo Swinson and haven't heard of John Nicolson, it's very hard to suddenly say you're planning to vote for John Nicolson, particularly when the question is insisting that you take into account who is standing. So it's likely that some people who plan to vote SNP (or indeed Labour) without being overly fussed about the candidates will have been coaxed into falsely saying that they are going to vote for Swinson. This is the twisting effect of question sequence that was famously illustrated in a Yes Minister scene, in which Sir Humphrey gets Bernard to say he is both in favour and opposed to the reintroduction of National Service.
What's interesting of course is that the Lib Dems have done a large number of these polls, but have only released a small fraction of them. That suggests even a rigged methodology isn't sufficient to produce a favourable result in many seats.
* * *
Have you ever had one of those nightmare journeys over a ridiculously short distance that leaves you wondering if a celestial power is conspiring against you? Yesterday morning I was due to take part in one of Derek Bateman's audio recordings at around 11.30, but the Stagecoach bus I was planning to catch turned up early, and I missed it by literally twenty seconds. So I texted Derek to let him know I would be late. After waiting an eternity, the bus I finally caught managed to shed its drive shaft midway during the journey. I didn't have the heart to text Derek again to tell him the bus had broken down, if only because it would have sounded like a classic "the dog ate my homework" excuse. So instead I hopelessly tried to make up the time by running when I got to the city centre, and I eventually arrived at the studio 50 minutes late. Thankfully everyone was very understanding, although when the recording is put on the website I suspect you'll still be able to hear me gasping for breath!
Here's how it was done...
* The results were weighted by 2010 vote recall. On the headline numbers, this resulted in respondents who said they voted SNP being weighted down from 53 to 33 (a drop of almost two-fifths), while respondents who recalled voting Lib Dem were upweighted from 73 to 90. Assuming that a significant proportion of people are probably getting their 2010 and 2011 votes mixed up, this factor alone is sufficient to introduce a huge distortion, and to transform what would have been a comfortable SNP lead into a small Lib Dem lead.
* No other form of political weighting was added to help balance out any distortion from the 2010 weighting (a practice used by some other pollsters, albeit admittedly not Ashcroft). Respondents were asked how they voted in the independence referendum, producing too big a lead for No, and yet the headline voting intention figures were not weighted by recalled referendum vote. Again, that alone would have been sufficient to put the SNP in the lead.
* The poll departs from standard good practice by not asking the headline voting intention question at the start of the question sequence. It's in fact asked fifth. The big problem is with Question 4, which names the local candidates and asks respondents to rate them. Unsurprisingly, this works in Jo Swinson's favour, because only 3.3% of the sample have not heard of her, compared to 49.7% who haven't heard of SNP candidate John Nicolson. (Although Mr Nicolson is a television personality, he's been off our screens for quite a while, and is probably more recognisable for his face and voice than for his name.)
* When the voting intention question is finally asked, it's posed like this : "If the general election was tomorrow, how would you vote in the East Dunbartonshire constituency knowing who is standing?" (my emphasis). People try to keep their responses to polls logically consistent, and if you've just said that you like Jo Swinson and haven't heard of John Nicolson, it's very hard to suddenly say you're planning to vote for John Nicolson, particularly when the question is insisting that you take into account who is standing. So it's likely that some people who plan to vote SNP (or indeed Labour) without being overly fussed about the candidates will have been coaxed into falsely saying that they are going to vote for Swinson. This is the twisting effect of question sequence that was famously illustrated in a Yes Minister scene, in which Sir Humphrey gets Bernard to say he is both in favour and opposed to the reintroduction of National Service.
What's interesting of course is that the Lib Dems have done a large number of these polls, but have only released a small fraction of them. That suggests even a rigged methodology isn't sufficient to produce a favourable result in many seats.
* * *
Have you ever had one of those nightmare journeys over a ridiculously short distance that leaves you wondering if a celestial power is conspiring against you? Yesterday morning I was due to take part in one of Derek Bateman's audio recordings at around 11.30, but the Stagecoach bus I was planning to catch turned up early, and I missed it by literally twenty seconds. So I texted Derek to let him know I would be late. After waiting an eternity, the bus I finally caught managed to shed its drive shaft midway during the journey. I didn't have the heart to text Derek again to tell him the bus had broken down, if only because it would have sounded like a classic "the dog ate my homework" excuse. So instead I hopelessly tried to make up the time by running when I got to the city centre, and I eventually arrived at the studio 50 minutes late. Thankfully everyone was very understanding, although when the recording is put on the website I suspect you'll still be able to hear me gasping for breath!
Wednesday, April 15, 2015
Sensational poll commissioned by the Lib Dems suggests the SNP are within touching distance of winning EAST DUNBARTONSHIRE
Thanks to my namesake James on the previous thread for alerting me to the fact that the Lib Dems have leaked another of their internal constituency polls - this time East Dunbartonshire. The methodology used in these polls moves heaven and earth to produce artificially good results for the Lib Dems (ie. leading questions asked before the voting intention question, plus strict weighting by 2010 vote recall), so the fact that the SNP still find themselves in a 'statistical tie' in one of their very toughest target seats is pretty extraordinary.
East Dunbartonshire voting intentions (Lib Dem poll) :
Liberal Democrats 34.5%
SNP 32.1%
Labour 16.2%
Conservatives 13.1%
Greens 2.0%
UKIP 0.7%
On the face of it, this poll is also devastating for Labour, because some projections have suggested they could gain East Dunbartonshire, even if they lose a large number of seats to the SNP. However, it's possible they've suffered disproportionately from the Lib Dem-friendly methodology.
East Dunbartonshire is one of the seats Populus have been polling this week, so if that proves to be an Ashcroft poll it will make the real state of play a lot clearer. Let's put it this way - I strongly suspect the Lib Dems aren't really in the lead, even allowing for Jo Swinson's personal vote.
Presumably the reason for leaking the poll was to establish the Lib Dems as the "only way of stopping the SNP here" for propaganda purposes, but Ashcroft could well muddy the waters in that respect.
Tuesday, April 14, 2015
Ed Miliband doesn't even seem to want your vote
A second "quick note" of the day (I'm really going to have to dream up a different phrase), this time to let you know that I have a new article at the International Business Times, about the way in which Labour are treating the Scottish voters they need to win back with contempt. You can read it HERE.
Massive Populus constituency polling underway - could it be Ashcroft III?
Several people have either emailed or left comments over the last couple of days to say that they've been interviewed by Populus via telephone. It appears to be constituency polling, because the call is aborted if the interviewee turns out to be in the wrong constituency. So far I've heard about nine seats -
Ross, Skye and Lochaber
Edinburgh North and Leith
Edinburgh South
East Dunbartonshire
Glasgow South-West
Dumfriesshire, Clydesdale and Tweeddale
Fife North-East
Berwickshire, Roxburgh and Selkirk
East Renfrewshire
From the questions that were recalled, it initially sounded like internal polling for one of the London parties, but there's no discernible pattern in the above list - other than the SNP, no party is in contention in all nine. Another possible explanation is that it's a third round of Ashcroft constituency polls - he's already polled four of the nine seats on the list, but it could be that he's revisiting them to see if there's been any change (he's done that in a number of English constituencies). Time will tell.
* * *
On the previous thread, David Halliday pointed me in the direction of an article on Common Space about the current polling situation, which makes several misleading points. In particular, it's stated that -
"In Monday's TNS Poll (TNS does face to face interviews) the headline figure for the SNP was 52 per cent but the actual raw figure before weighting was 29 per cent. The number of undecided in the TNS poll was 29 per cent - obviously these numbers are in stark contrast to what is being portrayed in the media...How the polling companies weight their polls is giving a huge boost to the SNP numbers..."
The reality is that the SNP haven't benefited at all from the weightings TNS have applied. In respect of the headline numbers, there were 217 SNP voters before weighting, and 219 SNP voters after weighting - near-enough identical. What is really meant by "actual raw figure before weighting" is "actual figure after weighting but before undecided respondents have been stripped out", which is an entirely different point. Because there is such a large number of undecideds in this poll (hardly untypical for TNS), the SNP vote is of course much higher after those respondents are removed, but so is the Labour vote, the Tory vote and the Lib Dem vote.
It seems to me the average reader will be left with the highly misleading impression that all of the polling firms are using some kind of very weird weighting scheme which is uniformly flattering the SNP by a massive amount. Nothing of the sort is happening. YouGov's weighting tends to boost the SNP a little, but not dramatically.
The underlying message of the article is "there is no room for complacency", which I would thoroughly endorse, but I think it's possible to get that message across without making bogus points about how the SNP's position in the polls is supposedly much worse if you "drill down". It isn't. The SNP's position in the polls is absolutely fantastic. If they don't win a truck-load of seats, it'll be for one (or more) of three reasons - a) a significant late swing back to Labour, b) industrial-scale tactical voting, or c) methodological flaws across the whole polling industry of the sort we saw in 1992.
On the latter point, it was mentioned on the previous thread that the SNP were significantly overestimated in the polls in the run-up to the European elections last year. That's true, but all of the firms in question (Survation, YouGov, Panelbase and ICM) have changed their methodology since then, and introduced weighting by recalled referendum vote. So there's no reason to assume that history is bound to repeat itself.
Ross, Skye and Lochaber
Edinburgh North and Leith
Edinburgh South
East Dunbartonshire
Glasgow South-West
Dumfriesshire, Clydesdale and Tweeddale
Fife North-East
Berwickshire, Roxburgh and Selkirk
East Renfrewshire
From the questions that were recalled, it initially sounded like internal polling for one of the London parties, but there's no discernible pattern in the above list - other than the SNP, no party is in contention in all nine. Another possible explanation is that it's a third round of Ashcroft constituency polls - he's already polled four of the nine seats on the list, but it could be that he's revisiting them to see if there's been any change (he's done that in a number of English constituencies). Time will tell.
* * *
On the previous thread, David Halliday pointed me in the direction of an article on Common Space about the current polling situation, which makes several misleading points. In particular, it's stated that -
"In Monday's TNS Poll (TNS does face to face interviews) the headline figure for the SNP was 52 per cent but the actual raw figure before weighting was 29 per cent. The number of undecided in the TNS poll was 29 per cent - obviously these numbers are in stark contrast to what is being portrayed in the media...How the polling companies weight their polls is giving a huge boost to the SNP numbers..."
The reality is that the SNP haven't benefited at all from the weightings TNS have applied. In respect of the headline numbers, there were 217 SNP voters before weighting, and 219 SNP voters after weighting - near-enough identical. What is really meant by "actual raw figure before weighting" is "actual figure after weighting but before undecided respondents have been stripped out", which is an entirely different point. Because there is such a large number of undecideds in this poll (hardly untypical for TNS), the SNP vote is of course much higher after those respondents are removed, but so is the Labour vote, the Tory vote and the Lib Dem vote.
It seems to me the average reader will be left with the highly misleading impression that all of the polling firms are using some kind of very weird weighting scheme which is uniformly flattering the SNP by a massive amount. Nothing of the sort is happening. YouGov's weighting tends to boost the SNP a little, but not dramatically.
The underlying message of the article is "there is no room for complacency", which I would thoroughly endorse, but I think it's possible to get that message across without making bogus points about how the SNP's position in the polls is supposedly much worse if you "drill down". It isn't. The SNP's position in the polls is absolutely fantastic. If they don't win a truck-load of seats, it'll be for one (or more) of three reasons - a) a significant late swing back to Labour, b) industrial-scale tactical voting, or c) methodological flaws across the whole polling industry of the sort we saw in 1992.
On the latter point, it was mentioned on the previous thread that the SNP were significantly overestimated in the polls in the run-up to the European elections last year. That's true, but all of the firms in question (Survation, YouGov, Panelbase and ICM) have changed their methodology since then, and introduced weighting by recalled referendum vote. So there's no reason to assume that history is bound to repeat itself.
A bit more about the TNS poll
Just a quick note to let you know that I have a new article at The National about yesterday's extraordinary TNS poll, which saw the SNP's lead almost double from 16 to 28 points. You can read it HERE.
Monday, April 13, 2015
SNP vote soars into the stratosphere in breathtaking TNS poll
TNS have today published their third full-scale Scottish poll since the referendum...
Scottish voting intentions for the May 2015 UK general election (TNS, 18th March - 8th April) :
SNP 52% (+6)
Labour 24% (-6)
Conservatives 13% (-1)
Liberal Democrats 6% (+3)
Greens 3% (-1)
UKIP are not listed because they're literally on zero (there were two respondents interested in a Farage à trois, but they were rounded down to zero).
These figures mean that TNS are suggesting an absolutely astonishing trend over the last few months. Their first post-referendum poll in January/early February produced an SNP lead of 'only' 10%, which made it look as if they were going to slot in as one of the most Labour-friendly pollsters. A second poll not long afterwards saw the lead increase to 16%, which was pretty much in line with most online pollsters. Now, in one fell swoop, the lead has reached 28% - which completes a rapid transformation for TNS and leaves them as one of the two most SNP-friendly firms. (The other is Ipsos-Mori, which also showed a position of SNP 52%, Labour 24% in their most recent poll - but that was way back in January.)
Now it's true that last week's YouGov poll also showed the SNP lead reach a record level, so it would be wrong to instantly dismiss the TNS poll as an obvious outlier. It now seems much more likely that there has been further movement to the SNP at some point over the last few weeks. But the sheer scale of the swing suggested by TNS over such a relatively short period of time is not something that has been recorded by any other firm so far, and it would be just as well to remain cautious until it is. I can't see any obvious methodological change that would be generating an illusory swing, so it may just be that margin-of-error effects are exaggerating the trend slightly.
But that's not much comfort for Labour - to state the obvious, they desperately need to be gaining ground, and the mounting evidence that the swing is in completely the opposite direction will be greeted with unmitigated horror in McTernan HQ (which in normal circumstances is renowned for being such a happy, jolly sort of place).
Scottish voting intentions for the May 2015 UK general election (TNS, 18th March - 8th April) :
SNP 52% (+6)
Labour 24% (-6)
Conservatives 13% (-1)
Liberal Democrats 6% (+3)
Greens 3% (-1)
UKIP are not listed because they're literally on zero (there were two respondents interested in a Farage à trois, but they were rounded down to zero).
These figures mean that TNS are suggesting an absolutely astonishing trend over the last few months. Their first post-referendum poll in January/early February produced an SNP lead of 'only' 10%, which made it look as if they were going to slot in as one of the most Labour-friendly pollsters. A second poll not long afterwards saw the lead increase to 16%, which was pretty much in line with most online pollsters. Now, in one fell swoop, the lead has reached 28% - which completes a rapid transformation for TNS and leaves them as one of the two most SNP-friendly firms. (The other is Ipsos-Mori, which also showed a position of SNP 52%, Labour 24% in their most recent poll - but that was way back in January.)
Now it's true that last week's YouGov poll also showed the SNP lead reach a record level, so it would be wrong to instantly dismiss the TNS poll as an obvious outlier. It now seems much more likely that there has been further movement to the SNP at some point over the last few weeks. But the sheer scale of the swing suggested by TNS over such a relatively short period of time is not something that has been recorded by any other firm so far, and it would be just as well to remain cautious until it is. I can't see any obvious methodological change that would be generating an illusory swing, so it may just be that margin-of-error effects are exaggerating the trend slightly.
But that's not much comfort for Labour - to state the obvious, they desperately need to be gaining ground, and the mounting evidence that the swing is in completely the opposite direction will be greeted with unmitigated horror in McTernan HQ (which in normal circumstances is renowned for being such a happy, jolly sort of place).
Sunday, April 12, 2015
At last! A leaders' debate with rules.
I'm thrilled that BBC Scotland have heeded my call on Thursday that much stricter rules should apply to future leaders' debates. As far as I could gather, the rules for this morning's Sunday Politics Scotland debate went as follows -
1) When Nicola Sturgeon is answering a challenging question, the moderator should personally ensure that SHE CANNOT COMPLETE ANY SENTENCE WITHOUT AGGRESSIVE INTERRUPTION.
2) Jim Murphy, Ruth Davidson and Willie Rennie should not be asked any challenging questions by the moderator.
3) When Jim Murphy, Ruth Davidson or Willie Rennie is attacking the SNP, the moderator should allow them to continuing speaking WITHOUT INTERRUPTION, AND AT HOWEVER MUCH LENGTH THEY WANT.
4) When Nicola Sturgeon is attacking the other parties or asking them questions, the moderator must personally ensure that HER VOICE IS COMPLETELY DROWNED OUT.
5) When Jim Murphy, Ruth Davidson and Willie Rennie are talking over Nicola Sturgeon and preventing her from being heard, they must be ALLOWED TO DO SO.
6) If Nicola Sturgeon shows the slightest sign of opening her mouth when someone else is speaking, the moderator must TELL HER TO SHUT UP.
Did you spot any others?
1) When Nicola Sturgeon is answering a challenging question, the moderator should personally ensure that SHE CANNOT COMPLETE ANY SENTENCE WITHOUT AGGRESSIVE INTERRUPTION.
2) Jim Murphy, Ruth Davidson and Willie Rennie should not be asked any challenging questions by the moderator.
3) When Jim Murphy, Ruth Davidson or Willie Rennie is attacking the SNP, the moderator should allow them to continuing speaking WITHOUT INTERRUPTION, AND AT HOWEVER MUCH LENGTH THEY WANT.
4) When Nicola Sturgeon is attacking the other parties or asking them questions, the moderator must personally ensure that HER VOICE IS COMPLETELY DROWNED OUT.
5) When Jim Murphy, Ruth Davidson and Willie Rennie are talking over Nicola Sturgeon and preventing her from being heard, they must be ALLOWED TO DO SO.
6) If Nicola Sturgeon shows the slightest sign of opening her mouth when someone else is speaking, the moderator must TELL HER TO SHUT UP.
Did you spot any others?
Housekeeping note
For quite a while now, some of you have urged me to disable anonymous commenting on this blog, in order to tackle the scourge of trolls. I've finally decided to take that step - but only on a very temporary basis (probably only for a few hours). I think you'll now appreciate why it's not a good idea to do it permanently, because for some reason removing anonymous posting also removes the "Name/URL" option, and effectively means that you need to sign in to an account to comment. That would deter an awful lot of people from posting, and probably cut the number of comments by more than half.
The reason I'm doing it temporarily is to deal with an anonymous unionist troll who's been throwing his weight around over the last couple of days, and who has predictably started to become more abusive as the penny drops that we don't all dutifully surrender at the first sign of his silly scare stories. (He's just described me as "bordering on mentally ill".)
Of course, this won't stop Simon (I call him Simon) continuing to post, but if he wants to do so he'll have to put a name to the bile. Will he be brave enough? I suspect not, but we'll see.
The reason I'm doing it temporarily is to deal with an anonymous unionist troll who's been throwing his weight around over the last couple of days, and who has predictably started to become more abusive as the penny drops that we don't all dutifully surrender at the first sign of his silly scare stories. (He's just described me as "bordering on mentally ill".)
Of course, this won't stop Simon (I call him Simon) continuing to post, but if he wants to do so he'll have to put a name to the bile. Will he be brave enough? I suspect not, but we'll see.
When I find myself in times of boredom, my mate Murphy comes to me, speaking words of narcissism, glory be...
Can you guess which of these is a genuine tweet from Jim Murphy, and which one I've just made up?
"To Mrs Lily Ritchie of Girvan Rd : open your front door now for rare opportunity to see me on Irn Bru crate railing against separation."
"If you live on corner of Heather Ave & Acacia Dr in Barrhead, look out window as doing Sky News on SNP pension cuts."
Yes folks, it's true - one of these is a GENUINE TWEET from Jim Murphy.
"To Mrs Lily Ritchie of Girvan Rd : open your front door now for rare opportunity to see me on Irn Bru crate railing against separation."
"If you live on corner of Heather Ave & Acacia Dr in Barrhead, look out window as doing Sky News on SNP pension cuts."
Yes folks, it's true - one of these is a GENUINE TWEET from Jim Murphy.
Subscribe to:
Posts (Atom)