Latest Polls and Latest Odds

[renton]

Aye, I was just in Vilnius and it was everyone's first topic of conversation.

Ipsos-Mori phoned last night, they've got a poll coming out tomorrow. The guy I spoke to said they were struggling to get enough young people to have an even representation of all demographics, probably what happens when you're conducting polls via landline phones.

Yeah, they've has that problem through the entire campaign.

[John Lambies Doos]

So we are concluding that the polls are way out? Ie they mainly contain old people, people with landlines and do not contain the additional 400k that are registered to vote?

And they are still showing 50 50?

Mmmmmmm

[Granny Danger]

I was listening to a part of a programme on Radio Scotland yesterday with Curtis and Kellner (?) when they said that only one polling organisation relies heavily on telephone polls and that they use mobiles as well as landlines.

Not sure where they get the contact numbers from.

[banana]

I think the conclusion is that we simply don't know. The pollsters themselves admit they may be more off the mark than usual.

Given the close nature of the poll results, some significant unintentional bias in the polling methodologies used would be a massive boon for one side.

[renton]

So we are concluding that the polls are way out? Ie they mainly contain old people, people with landlines and do not contain the additional 400k that are registered to vote?

And they are still showing 50 50?

Mmmmmmm

No, merely that an inability to find enough 'real' respondents in a given poll leads to a large upweighting in those groups, and with it and upwieighting in the statistical margin of error for that group which can lead to inaccurate or volatile results (see Survation and it's inability to find enough 16-24s). I figure that Ipsos consistently No friendly results are something to do with their demographic breakdown of the populace - upweighting in certain age groups would introduce volatility from one sample to the next, but not a consistently depressed Yes vote with repsect to the other pollsters.

[ICTJohnboy]

Yeah this is the commonsense test I've been talking about.

To see it you need to take a step back.

For 2 years we've had both sides campaigning hard.

Neither side will rely on official pollsters - both are doing major private polling.

WQho has changed their strategy recently and to what extent?

Has that change been gradual or sharp?

Does it seem co-ordinated and part of a bigger story or does it smack of headless chicken.

Then you make assumptions about why that might be.

Look at Darling, Cameron on one side and Salmond on the other.

Which if them looks like a man certain of success and which of them looks haunted as though their careers were on the verge of collapse?

This is my very simple gut feel test or commonsense test.

It tells me that BT know they are losing and that they are losing heavily in the most populated areas.

It tells me that two things about Yes. Firstly that they are winning well and secondly that Salmond has the killer instinct to absolutely humiliate BT to ensure our independence mandate is as strong as possible for the forthcoming negotiations.

I have no proof of any of this of course but the above is my growing gut feeling whilst retaining some apprehension about calling this too early. If I was completely impartial looking at this from say Sweden, I'd conclude that Yes were about to win a landslide.

Feel free to pick holes in my amateur analysis.

Great post... Although only one side has been campaigning hard for 2 years. The other side thought they had already won.

[ForzaDundee]

Dundee and Dundee United Mad's polling results (Thus far) are:

Dundee Mad

41 YES (73%)

15 NO (27%)

United Mad

39 YES (81%)

9 NO (19%)

Very surprised to see a higher percentage of Yessers from United. I thought Dundee was the most pro-independence place in Scotland.

Dundee Mad is full of mouth-breathers. Most sensible Dundee fans stay well away from there. The fact they could only muster 15 nos speaks volumes.

[craigkillie]

What I absolutely love is that despite No Thanks orchestrating the most vindictive, nasty, immoral, underhanded, vicious, lie-strewn, desperate campaign in political history, despite them chucking everything including the kitchen sink at us, despite them calling on their friends in big business, world politics and the media at us, despite their best efforts to frighten Scotland into a No vote, Yes are not only neck and neck, but look likely to win.

It fills me full of pride and utter, utter joy.

Based on what? Your gut feeling and some optimistic analysis of the polls by Yes supporters?

[renton]

Based on what? Your gut feeling and some optimistic analysis of the polls by Yes supporters?

A No vote is as likely as a Yes vote based on the current polls.

[Broken Algorithms]

You'd have to say, that given the high turnout expected in comparison to the sample sizes, in addition to the types of people involved in samples, means you've got to be sceptical of how the polls reflect the actually bearing of things. It'll be interesting to see if things truly are neck and neck at the polls.

[Mr Bairn]

I'm skeptical of the high turnout anyway. I know the whole craic about 97% of the electorate registering, but how does that compare to a standard UK election? Also I wonder how many people actually need to go to the trouble of registering, I know that my letting agent did it for us when we moved into the new flat, and they do so for all tenents unless you specifically tick a box asking them not to do so, so I wonder if a lot of people are "automatically" registered by some third party.

[craigkillie]

A No vote is as likely as a Yes vote based on the current polls.

Surely a No vote is marginally more likely than a Yes given the position of the Poll of Polls and other pieces of meta-analysis? Yes can definitely win, but I still think No is the more likely outcome.

Edited September 16, 2014 by craigkillie

[Confidemus]

Surely a No vote is marginally more likely than a Yes given the position of the Poll of Polls and other pieces of meta-analysis? Yes can definitely win, but I still think No is the more likely outcome.

My reasoning for part of it is that, thanks to the work of the Yes grassroots movement, a large demographic of people who have never voted before have registered to vote. It is my belief (and only that - my belief) that these people will be more likely to vote Yes, having had that contact with the Yes movement.

I also believe that this demographic are unlikely to be registered with polling companies and therefore will not feature as heavily in the polling company stats.

I stress that this is my opinion only and part of my belief that Yes will win on Thursday fairly comfortably.

[Well Well]

I'm skeptical of the high turnout anyway. I know the whole craic about 97% of the electorate registering, but how does that compare to a standard UK election? Also I wonder how many people actually need to go to the trouble of registering, I know that my letting agent did it for us when we moved into the new flat, and they do so for all tenents unless you specifically tick a box asking them not to do so, so I wonder if a lot of people are "automatically" registered by some third party.

extreme straw clutching to justify his argument

[Confidemus]

extreme straw clutching to justify his argument

He's just raging because he's been out-trolled by the new influx of trolls.

[Well Well]

Surely a No vote is marginally more likely than a Yes given the position of the Poll of Polls and other pieces of meta-analysis? Yes can definitely win, but I still think No is the more likely outcome.

Even the polling companies say they can't reach the right people to get a proper assessment of how people will vote. Friday morning will be the only result of a poll I will listen to by the returning officer.

[Granny Danger]

Based on what? Your gut feeling and some optimistic analysis of the polls by Yes supporters?

A No vote is as likely as a Yes vote based on the current polls.

Two things make me thing it could be YES.

The campaigns will be responding to their own private polls and the attitudes and actions of recent days suggest both sides polls are showing a YES lead.

The polling prior to the 2011 Scottish Parliament election underestimated the level of desire for change. In fact it was a significant underestimation.

[Mr Bairn]

To be fair, a lot of these first time voters will be voting Yes, but the other big group that polling companies (well internet based ones anyway) struggle to attract ( pensioners) will be voting mainly No.

I think the pollsters have caught on to this and the weighting adjustments have brought the result in polls closer to the "true" (IMO) 50-50 figure. I'd say I'm 60% confident of a No victory purely because the last remaining undecideds tend to go for the status quo when pressed for a decision, but if be rather surprised if there's a clear victory for either side.

[renton]

Surely a No vote is marginally more likely than a Yes given the position of the Poll of Polls and other pieces of meta-analysis? Yes can definitely win, but I still think No is the more likely outcome.

Depends on which you do a poll of polls, there are a couple of different methodologies - either the last set of polls in a month, or the last six polls by all the involved pollsters, at the moment doing a poll of polls base don the latter methodology is likely to depress the Yes position as it includes an oldish Ipsos-Mori (though it looks like that will be shortly remedied). The other issue with poll of polls is that for a long time they've merely generated a false middle through wildly different methodologies - that's lessened now but again, with ipsos in there you are still likely to see a big No lead even though everyone else reckons it's even stevens.

based on the run of the last few polls from PB, Survation, ICM, YG and TNS I'd reckon it's 50/50 - we've seen Yes in the range 46 to 54 over those polls but removing the outliers sees yes in the range 49-51. I'd also go back to something I noted previously, that big yes swings were in Younger groups and C2D2E percentiles - both groups likely to make up a lot of the newer voters who've been undersampled in BPC pollsters.

Against that, you've got the 'silent majority', 'shy no' narrative of which there is absolutley no proof of it being a major phenomenon, but there is the more real possiblity of Yes shedding a couple of points based on previous referendum performances.

How do those two factors cancel out? Does the yes group have a soft edge? Given how the Yes vote held up after last weeks blitz you'd think not much, but then they might waiver when in the actual booth. Will those big swings to Yes in lower income and younger age groups seen by the RIC and the BPC pollsters actually turn up on the day?

I don't think there is much in it, I don't on the face of it see a reason to suppose that No has an advantage at this point, that might change tonight with TNS due out at 5pm and you'd assume the YouGov one out late tonight for publication in the papers tomorrow.

Edited September 16, 2014 by renton

[Colkitto]

There is a Survation poll coming out as I was polled on it yesterday. Hope it's not for the Record again!