Thursday, May 15, 2014

Survation headline figures revealed

Quite why we had to be left in 'suspense' overnight is a bit of a mystery, but the Survation headline figures have now been published, in addition to the figures excluding Don't Knows that were revealed last night. They show an identical position to the last poll in the monthly Record series, although the correct comparison is with the more recent Survation poll for the Sunday Post.  There have only been margin of error changes since then.

Should Scotland be an independent country?

Yes 37% (-1)
No 47% (+1)

So the picture painted by Survation recently is indeed one of stability.  But I'm slightly bemused by John Curtice's implication that this is somehow the final piece of the jigsaw that proves his long-running contention that there was a significant swing to Yes over the winter, but no movement in either direction since then.  Let's consider the evidence from the five BPC pollsters other than Survation...

TNS-BMRB are showing the highest Yes vote of the campaign so far (41.3%) after Don't Knows are excluded.  OK, that's only fractionally higher than the previous all-time highs, but it's always at least potentially interesting when a pollster produces numbers outside its normal range.  The Yes vote on the headline numbers has also reached its highest level since TNS changed their methodology and increased the reported number of undecided voters.

Likewise, YouGov appear to be showing - albeit only by a very narrow margin - their highest Yes vote of the campaign so far when Don't Knows are excluded.  We can't be 100% sure of that because YouGov don't reveal their unrounded figures.  But it's a reasonable assumption given that the headline No lead is the lowest to date.

ICM are showing a Yes vote with DKs excluded that is 2% higher than at any previous point in the campaign.

Panelbase have shown stability recently, but they don't actually assist Professor Curtice's theory, because they were entirely out of step with the trend shown by the other pollsters during the winter.  They showed No maintaining (or even slightly increasing) its previous lead after the White Paper, followed by a sudden drop a couple of months ago, followed by stability since then.  The fact that no other pollster has replicated that pattern illustrates how methodology (including data collection method) can lead to the same basic trend being detected at an earlier or later date - it's almost as if some pollsters are on a time delay.  Which brings me neatly on to...

Ipsos-Mori :  If the rumours about the secret mega-poll are true, they would not only mean that Ipsos-Mori have picked up the trend shown by other pollsters a little bit later in the day (possibly due to telephone fieldwork reaching a more small 'c' conservative sample), but also that two out of six BPC pollsters are showing statistically significant movement to Yes since the end of the winter, and that four out of six pollsters are showing the highest Yes vote of the campaign so far in their most recent poll.

When you look at it that way, it becomes clear that the jury is still very much out on the Curtice theory.

* * *


Sorry for the delay in adding the update of the Poll of Polls - I've been on the move all day. As you'd expect, the margin of error changes in the Survation poll have fed through into the averages, and the No lead has fractionally increased, but only to a position 0.3% higher than the all-time low reported in the previous two updates.

MEAN AVERAGE (not excluding Don't Knows) :

Yes 35.8% (-0.2)
No 47.3% (+0.1)

MEAN AVERAGE (excluding Don't Knows) :

Yes 43.1% (-0.2)
No 56.9% (+0.2)

MEDIAN AVERAGE (excluding Don't Knows) :

Yes 43.0% (-0.6)
No 57.0% (+0.6)

(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 headline figures :

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%

And as Survation conduct their fieldwork online, it's also time for an update of the averages for the four online pollsters that have reported so far this year...

MEAN AVERAGE OF ONLINE POLLSTERS (not excluding Don't Knows) :

Yes 38.3% (-0.2)
No 46.3% (+0.3)


Yes 45.3% (-0.3)
No 54.7% (+0.3)


Yes 45.6% (-0.5)
No 54.4% (+0.5)


  1. Meanwhile, over on political racism. Smithson has dumped Ali Carmichael as his beloved new leader of the Fib-Dumbs and is now backing Beaker!

  2. Your bottom link 'here' is not linking to webpage, just for info.

    This seems a nonsense to me!

    Poll of Polls.

  3. Thanks, I've fixed it. That's the second time that has happened this week - you wouldn't think it would be so difficult to copy and paste a link!

    As for the ScotCen Poll of Polls, I do find it hard to understand what the point of the British Polling Council rules are, if someone like john Curtice is going to treat the results of a non-BPC poll just as seriously as all the others.

  4. This seems a nonsense to me!

    It is. Shows the folly of trying to average different polls from different pollsters.

    Add one poll which shows a big swing to Yes from the last one (PSO) + another which shows no real change (Survation) and this = No rising!

  5. Survation certain to vote trends.

    No lead over Yes (ex DK) +7(-2.5)%
    47 Y / 53 N

    Which is closer to Panelbase and ICM results for general intention when asking about September.

    Certain to vote No 30(-6)%.

    Since February.

    Suggests No vote weakening, just less obvious, likely because survation ask what people would vote ‘today’ rather than in September.

  6. Not sure if you mean my post, but if so, sure. Simple linear trends to 10/10 certain to vote data.