Saturday 20 September 2014

Thoughts from Comres - Were 'Yes' ever in the lead?

Were 'Yes' ever in the lead?
We are all experts with the power of hindsight. The airwaves this weekend will be packed with post hoc analysis of what happened in Scotland, fitting the final result to a preferred narrative. This makes a change from the approach sketched out in our previous Pollwatch:
The media love a tight battle. From now until the date of the referendum this will be a “knife edge” contest with “everything still to play for”.
Now that the results are in, the commentariat have switched effortlessly from the John Motson, commentary box style of punditry, marvelling at the ebb and flow of the contest, to a back in the studio, post-match critique of the “shocking defending” on show, replays and tactical diagrams galore.
Post-match analysis
So which explanations can be fit to the actual results?
Maybe it was Gordon Brown’s speech of his life, perhaps it was the “Shy Noes” who were afraid to admit their position to pollsters, or you might prefer to argue that people changed their minds at the last minute when they realised the enormity of the situation.
Proving exactly what has happened over the course of a political campaign is difficult. Some pollsters showed a sudden surge for “Yes” in the closing weeks, while others showed a more consistent position from June onwards. Following a political campaign can be like standing outside a football stadium listening to the crowd and trying to get a feel for which team is ahead. Nobody knows the score until the final whistle has blown.
Did “Yes” ever stand a chance?
There were some strong bits of evidence that were ignored by many observers, though. In our previous Pollwatch we argued:
The evidence from previous referendums worldwide is that most “Don’t know” respondents will end up backing the “status quo” option on voting day.
Essentially, this means that to win a referendum, the “change” option needs to be polling above 50% – before “Don’t knows” are excluded from the tally. This never happened at any point in the contest. As the eminent psephologist Professor Michael Thrasher has said, “I doubt the Yes campaign were ever ahead.”
Talk of the difference being within the margin of error rather missed the point. Yes, a single survey result typically has a margin of error of +/- 3 percentage points, but the average of a series of polls ought in theory to be much more accurate than that. Better Together were always ahead on this “poll of polls” measure:

Likewise, the idea that differential turnout could have swung the result towards “Yes” overlooked the fact that all the demographics historically associated with higher turnout – older people, more affluent ABC1s, and those who have voted previously – were skewing heavily towards a “No” vote. (Contrast the 75% voter turnout in Glasgow with the 84% of the electorate who cast their ballot in Edinburgh.)
Decisive moment or knee-jerk reaction?
If we accept this analysis, then it has big implications for the Westminster politicians who changed tack just over a week ago to offer a much more comprehensive devolution settlement to Scotland.
David Cameron, Ed Miliband, and Nick Clegg will be keen to argue that their decisive move worked to shore up the “No” vote and was the reason that the eventual lead for the pro-Union side was wider than any pollster had predicted.
This seems unlikely. The Québécoise sociologist Claire Durand of the University of Montreal drew upon her experience of analysing polling data during Quebec’s 1995 independence referendum to predict in August that “Yes” was a very long way from victory:
The Scottish Yes side needs a very major event in order to gain the support of a majority of Scottish people.
Her projections redistributed “don’t know” responses far more heavily towards “No” than towards “Yes”, in line with Quebec's experience. Throughout September, she repeatedly showed that while “Yes” had made small gains each week from the beginning of August, it had still not come close to threatening an upset.
Her projected outcome on Friday 12th September showed “Yes” on around 45%, with less than a week to go:
The best that can be argued for Gordon Brown’s cross-party deal on Scottish powers (agreed on 8th September) is that it may have prevented the “Yes” vote from climbing further, to around 46%. Or indeed the polls may have systematically overestimated stated “Yes” support in a way not factored into Prof Durand’s model.
Either way, the move to afford Scotland greater powers looks like a knee-jerk reaction – opening a Pandora’s box in Westminster that creates problems for both Mr Cameron and Mr Miliband in the run-up to the General Election.
What next for Westminster?
Our latest research for ITV News shows that a majority of British people (54%) now support a move to prevent Scottish MPs in Westminster from voting on issues that do not impact on Scotland. More controversially, two fifths (40%) of the population now support the creation of an English Parliament, and nearly half (48%) support devolution of powers to major cities and regions in England and Wales.
The noises coming from Conservative MPs since the Brown-Cameron Pact are likely to be only a hint of what is yet to come. Major constitutional change is something that scares many Conservative and Labour politicians alike.
ComRes will be polling MPs, Future MPs, MSPs, and the general public across the UK in the coming weeks to assess what impact this could have. But with the law of unintended consequences now in play, we are very much back in the commentary box with John Motson: “it’s nil-nil, and anything could happen.”
Follow ComRes on Twitter for the latest polls and analysis:@ComResPolls
Andy White, Senior Consultant
Be prepared for GE2015 with the new ComRes Election Toolkit:

The 2015 Battlebus is an online survey of 1,000 adults living in the 40 most marginal constituencies where Labour and the Conservatives share first and second place between them and battle head-to-head to get their candidate elected. This survey offers unique access to the opinions of those voters who will win or lose the election for the main parties - all at omnibus price levels.
In the run up to the election, and whilst the parties are drafting their manifestos, this research tool is ideal for ensuring that each of the parties know the importance of your policy issues to those who will be decisive in getting them elected. This can be very powerful for lobbying material or for generating media hits.
More information here.
Future MPs survey

Based on forecasts using our long-term voting intention surveys and careful psephological analysis, we have formulated a method of gauging the most likely composition of the House of Commons after May 2015.
Guaranteeing a sample of 100 of those MPs and PPCs who are most likely to take a seat in Parliament after 2015, ComRes is offering its clients a chance to gain vital insight into the levels of support for policy issues post 2015, enabling organisations to be on the front foot for when the new Parliament sits.
More information here

ComRes, Four Millbank, London, SW1P 3JA

No comments:

Post a Comment

Comment is open to all feel free to link to this blog.