Yes draws level for the first time ever in independence Poll of Polls

As you may already have seen, the first detail from the new Panelbase poll for Wings Over Scotland has been released - and it's the headline numbers on independence.

Should Scotland be an independent country?

Yes 49% (+2)
No 51% (-2)

Over the seven independence polls that Panelbase have conducted since the referendum, the Yes vote has ranged from 45% to 51%.  However, the 51% result was not directly comparable to the others, because the question asked was : "Knowing what you know now, if the independence referendum was tomorrow how would you vote?" Arguably, the "knowing what you know now" bit might have nudged some people towards thinking that their vote 'ought' to have changed. In the other six polls, Panelbase seem to have stuck rigidly with : "If the referendum was held again tomorrow, how would you vote in response to the question: Should Scotland be an independent country?" Until today, that question had produced a Yes range of between 45% and 48%, meaning that the 49% in the new poll is a record-breaking high. It's not quite a record high for a Panelbase poll using the referendum question in some form, though, because there was one conducted in August 2013 that put Yes on 51%. (That was the famous poll that John Curtice could never refer to without using the words "apart from one much-criticised Panelbase poll", which basically meant that he had criticised it quite a lot!) But post-referendum polls are not comparable to pre-referendum polls anyway, because Panelbase now use weighting by recalled referendum vote, which tends to lower the reported Yes share.

So is the increase for Yes in today's poll statistically significant? Not necessarily - if the true position (or "true" according to the Panelbase methodology) has remained unchanged at around 47% since the referendum, the standard 3% margin of error could easily produce results of 45% or 49% now and again. But, as I always say, if a poll result falls outside the previous normal range, it generally tells you something of interest. Either it means that the state of play has changed, or it changes our understanding of what "unchanged" means. In this case, if we were to assume that public opinion has remained steady, it would still be good news for Yes, because plainly a normal range of 45% to 49% is marginally healthier than a normal range of 45% to 48%.

Across the various post-referendum polls from the four firms that have used weighting by recalled referendum vote, 49% isn't actually unusually high, although it's above average. The best Yes showing in a poll of that sort (excluding the Panelbase poll with an unusual question) was 51% with Survation in March.

There's not much more to be said until the datasets are released, but what I can do is update the Poll of Polls. I think you might enjoy this...

SCOT GOES POP POLL OF POLLS

MEAN AVERAGE (excluding Don't Knows) :

Yes 50.0% (+0.4)
No 50.0% (-0.4)

MEAN AVERAGE (not excluding Don't Knows) :

Yes 46.3% (+0.3)
No 46.3% (-0.4)

MEDIAN AVERAGE (excluding Don't Knows) :

Yes 49.2% (+0.5)
No 50.8% (-0.5)

(The Poll of Polls is based on a rolling average of the most recent poll from each of the firms that have polled on independence since the referendum, and that adhere to British Polling Council rules. At present, there are six - YouGov, TNS, Survation, Panelbase, Ipsos-Mori and ICM. Whenever a new poll is published, it replaces the last poll from the same company in the sample.)

It goes without saying that this is the best result for Yes since the Poll of Polls started two years ago. The really telling stride forward came with the sensational Ipsos-Mori and TNS polls in September, but the changes shown by Panelbase have been just enough for Yes to draw level for the first time.

*  *  *

Click here for the Scot Goes Pop fundraiser : closes on Monday morning.