renton

tell that to all the other sovereign nations.

Which had nothing to do with the poll being intepreted as coming from the Labour party, and everythign to do with accept social norms about the amoral evilness of the tory party (and which is factored into polling these days, showing that such effects can be screened for) Still, what about those high levels of DKs huh?

Yeah, why would they? Also, while picking me up on that, what's your take on dismissing a poll as an outlier becuase of the number of DKs, when every single other poll shows the same?

Except that every pollster is seeing DKs at around that level or higher (and has been since 2012), much higher in some cases, 25% odds for TNS. Besides it's not a case of giving "No answer" it's a case of saying I haven't made my mind up yet - two different scenarios. The preamble is given in the NNS article and to my mind is fairly neutral - there is also no reason to suggest the methodology is different from other PB polls carried out for the Times. I'm also unsure how a selected sample would guess it was an 'SNP' poll, or why that would make them more inclined to say Yes. Finally, Survation had a poll at 39.3% this month, so 40% in PB is not exactly a stretch.

No more so than other online pollsters

Exactly why would this be? So long as this poll uses the standard methodology and preamble of the other pb polls then it is comparable. There is no doubt the SNP commisioned poll did have a different methodology. There is no reason to suspect this one does as yet. Who commissions the poll is irrelevent. Only the methodology is.

Assuming of course, that the polls are bang on, and assuming that Yes do not make any more headway like they did since January, and assuming that all those C2D2E 'missing million' voters don't come out on the day as well. I dn't think No are relaxed and just waiting it out.

well aye, it's not like you were ever likely to see momentum for an increase in a No vote, for them it's a holding action. Throw the kitchen sink at it in order to stem the flow to yes - to make folk wary and think twice.

What momentum? There is no momentum - in either direction, if you look at it ove rthe course of February into March, its stagnant. ICM for reasons alluded to above cannot be said to be jumping one way or the other with any reliability, most of the rest are 'no change' - if you look at it over a 3 to 4 month scale, then yes have had some momentum but it all depends on how you look at it. Thing about survation was that a 0.2% change in either headline figure would've tipped yes up to 40% after rounding, and No down to 47% after rounding, in which case the headlines would have been announcing a two point narrowing of the gap and yes breaching the magic 40%. 0.2%, that's two folk in the sample. As for your tourism thing, not sure any of that is relevent - why would they be nationalists? How come the oil workers came out in favour of Yes?

So, your graphic missed out the Feb 22nd Panelbase poll that showed the No gap closing by 2 points, you should also be aware that ICM changed their methodlogy twice. Their upweighting on age groups contributed to the upsurge in Yes vote in the January poll, after which they changed their weighting again, which contributed to the 5 point turnaround in February, so it's honestly quite hard to get a decent trend on recent ICM ones. Who care about Ispos Mori - if they are rigfht Yes are dead ducks and have been since the start (they are also the statistical outlier). The polls have stagnated through february from January, the survation questions from the last poll are interesting in so much as they demonstrate how few people seem to have been affected by Osborne, currency Standard life and the rest.

They saved the party by destroying it. Tell me, what is the point - the actual fucking point - of the Labour party winning an election if they are just going to ape the neoliberal concensus, if they are simply not going to enact even the merest hint of democratic socialism? Being electable is a bad joke if you don't have policies.

It's actually pretty static, Yes went up by 1, so did No, but then on an error of +/- 3% a 1% swing is neither here, nor there . Another +/-0.2% on the headline figures would have been rounded up to the magic 40% and the No lead would've been reduced by two points, on a sample of 1,000 people, two folk changing their minds would have led to far more dramatic headlines! Such is the limitations of charting political progress via polls. The positive aspect for yes here is that yes has not slipped back when measured against the previous Survation polls.

I posted that one because it doesn't average out the results, in other words you can resolve the individual points for each pollster per month, it was really not much more than superimposing a set of individual graphs for each pollster. Alas it does not resolve methodology changes made by pollsters. Still, as a broad picture it is instructive to a degree.

Why is it so hard for folk to understand that you cannot just take each different pollster together. it's not a like for like comparison. That goes for both sides, the Yes vote isn't jumping from 37% to 32%, it's a difference in how ICM and Ipsos process their data.

You'd think that after a few months they'd be immobile, not through complete decomposition, but surely the nervous tissue in the muscles, that control motion would rot quite quickly, and it's not like the zombie's digestive systems work (else why decompose in the first place), do they breathe still? Doe the heart beat? from doomed scientist guy in the first season I took it that whatever the infection is it keeps neurons firing in the lower part of the brain that controls motor functions, thus the corpse's muscles receives electrical signals to move about - how selective is that though, if the zombies can pump blood and process food, they wouldn't decompose - and if they don't, surely the blood would eventually pool in their legs, or coagulate altogether? I just don't see a zombie being a threat for more than a few weeks or months. You'd think the bigger threat would be all the secondary infections caused by a whole load of unburied dead bodies lying around. I know, I'm over thinking it.

Assuming a perfectly linear trend, then Yes will be 5-7 points behind on referendum day, thus needing a swing of about 2.5-3.5% when the DKs have to make a decision. It's not enough, and Yes need to accelerate the rate at which they cultivate votes, but that's possible - there is no innate physics that decides that the trend should be linear, it could slow down, speed up, go logarithmic, bottom out..... all it does serve to show is that when looking at the big picture, Yes have made some progress, eliminating a quarter of the No vote lead in a six month spell from September to now.

Yeah, except this guy's methodology is sound, it's a line, with all the No leads from the various polls, plotted by month. What's not to like about that?

Whatever, in this case he's not trying to bring new data to the table, merely collating the already available data. Thats icm, pb, yougov, tns, angus reid and ipsos. Take from it what you will

Someone making a graphical representation of the poll of polls that appears on the 'scot goes pop' blog

If you think your kids are better served by the UK then thats fine, but please dont describe it as 'strong' its politically weak, same with being able to make decisions economically too. We arent a strong part of the UK and never will be. Wether or not thats better or worse for your kids is up to you

No it's someone elses, includes all polls up until rhe ipsos mori one just done, which would appear in the upper right hand quarter

http://networkedblogs.com/Uq6eV quite anecdotal in places, but an interestin discussion nonetheless.

Well, until Ipsos release their full data sets, no. As for the continuing dominance of No, it's shed a quarte rof that lead in the last 6 months, it needs to accelerate that trend by a factor of two in order to be ahead in the polls on polling day. Ipsos-Mori will never eveng et that close, it's adherence to 2010 Westminster polling, the stealth pre-amble and even the landline phone data collection method all skews their data. They ar enow the statistical outlier when everyone else has converged.

No, those two figures are likely sub samples of the original data set, so it remains to be seen how the other percentiles between the bottom and top pan out. There are clear dmeographic splits in this referendum, if you are young, male and working class to middle class - that covers the most likely to vote Yes, you can work your way back to find the likely No voters, generally the most affluent groups, women by a factor of two to one. I don't think that those two figures show anything extraordinary.

What the hell does it mean by 'least deprived' are we talking top two percentile here? How about the middle class, lower middle class? Taking the top and bottom is no surprise, those most shat on are happy to try their lot, those who have made the most out of the system will not be inspired to change the game - what about the great mass in the middle though?