Big Eck's SNP bigs up a Facebook unscientific poll - Statistics Not Partisanship

I just saw this headline on the SNP website

Facebook poll shows majority for independence

For a start we all know the 'accuracy' of Faebook polling, indeed I was surprised that I hadn't picked up on it before now. It turns out it is one of those questions that get asked on facebook from time to time

Even the SNP report claims that 45% of such a poll is a majority with 42% failing. Now that places the result within any statistical margin of error. But not a clearance of 50% within a margin of error, especially as a Facebook poll cannot be weighted to take out any irregularities or non-representation of the sample group.

When I checked the figures for first preference as this is not a two question option as Caron has been blogging about, were:

Yes to full independence for Scotland 7447 44.3% of decided 46.4%
Yes to devolution max 1356 8.1% 8.4%
No 7239 43.1% 45.1%
Undecided 761 4.5%

Hardly a majority by any measure and too close to call by most I say. Obviously the SNP don't stand for Statistics Not Partisanship.

For Independence SNP Need 75% Support

Next time the SNP tell me that a good vote for this is a vote for Independence I'm going to point out that they'll be needing to ride at about 75% in the opinion polls to have that sort of success. Why?

Currently the SNP are sitting in the mid 30s in percentage terms in recent Scottish polls. But in today's Times to mark 10 years of devolution a Populus poll says that while 41% what more powers short of independence only 21% want Independence therefore at present one in three of the number who support* the SNP do not want Independence.

I'm waiting to hear how the SNP spin their way out of this set of polling results.

I'm also going to this point forward hold up any Nat who says "a vote for us is a vote for Independence" by naming and pointing them back to the stats under the header "A vote for the Nats is a 2/3 vote for Independence."

*Note the two in three is not even all SNP supporters as the Greens and Socialists will account for some of that number.

Spin, Damn Spin and Labour Polling Data

If the figures published in today's Sunday Times really were presented to Labour MSPs earlier in the month they may well be deluding themselves. While the figures are bad for Labour they do not, on first inspection, appear to be as bad as those publised by Professer Curtice earlier this week there is some doubt to their accuracy.

The figures translate into the following seats (Curtice's figures in brackets)

Labour: 43 (35)
SNP: 37 (33)
Lib Dems 28 (27)
Tories: 15 (21)
Others 6 (13)

The problems I detect in the Labour estimates are twofold. Firstly while they are acknowleding that there vote will be down on both constituecy and list vote they appear to be overestimating the effect this will give them on the list. The reason I'm saying this is because of their short changing the other parties. Labour are right to be concerned about the twin threats of the SNP and Liberal Democrats they would be foolish to write of all the smaller parties quite so non-challently. With the exception of the SSP the other minor parties are not showing a sign of not being able to replicate their performance from 2003.

Labour have released these figures to talk up their case ahead of next May's elections. They have acknowledged that things are bad, also they know they can't fool people who know that the SNP and Lib Dems will be big gainers. However, they have massaged the non-headline figures to give their own vote the appearance of being retrievable eleven months out. Therefore personally I'm viewing these figures with a a hefty pinch of salt.

So while the Labour spokesman said they will not be commenting on or discussing this information but the comment was made by the article. Meanwhile the discussion is going on; behind closed dooors for now, just wait for the next strategically spun leek.

Labour Losing Grip of Power

No real surprise in this morning's Scotsman but the latest polling analysis from Prof. John Curtice at Strathclyde University suggest that Labour are in as much trouble North of the border as there were in this months council elections in England. In fact based on English results they fair better than recent results in Scotland.

The breakdown of his analysis based on the Moray by-election would leave:

Labour 30 Constituency MSPs 5 List MSPs 35 in Total down 15
SNP 22 + 11 = 33 up 6
Liberal Democrats 15 + 12 = 27 up 10
Conservatives 4 + 17 = 21 up 3
Greens 0 + 7 = 7 NC
SSP 0 + 2 = 2 down 4
Others 2 + 2 = 4 NC

Now of course it is difficult to draw conclusions from extrapolation of one by-election result and one shouldn't read too much into it. But the trend is there as well that both the SNP and Liberal Democrats look set to be big gainers from Labour's misadventures. The Tories are hardly bounding back and are still relying heavily on list MSPs to maintain their presence.

Interestingly Labour's confidence that they can ride the storm may seem to be on shakey ground. On these findings Prof. Curtice suggests that Labour may lose as many as 16 constituency seats. However, instead of Labour's current rhetoric that they can pick these up off the list he suggests that the spread of their loses and others' gains would mean they'd only make up one off the list system.

With the Lib Dems being the major gainers as they have been in both by-elections this year the effect is a concertina of the big three parties so that Labour are largest with 35 only two ahead of the SNP, and 8 ahead of the Lib Dems. The Tories also manage to emerge with 21 seats which leads to all sorts of permeations for discussions after May next year.