ComRes have published a new poll of voting intentions in LD-Con seats in the South West for ITV. Full details are here. The topline figures are CON 44%, LAB 13%, LDEM 26%, UKIP 10%. Given these are all seats that the Liberal Democrats won in 2010 this is a huge turnaround – in 2010 the Lib Dems had an overall lead of 8.5% over the Tories in these seats, now they are 18 points behind, a whopping great swing of 13 points. If there was a uniform swing of this scale across these seats the Lib Dems would lose the lot.

Depressing for the Lib Dems, but wholly at odds with previous polling evidence in these seats. Lord Ashcroft has polled Lib Dem held seats pretty comprehensively, so we actually have constituency polls in 12 of the 14 seats included in this sample, and they paint a very different picture. Compared to the 13 point LD>Con swing in the ComRes poll Lord Ashcroft found an average LD>Con swing of about 4 points.

The difference between these two sets of polling is much larger than can explained by margin of error – they paint a genuinely contradictory picture. If ComRes are right the Lib Dems have collapsed in their heartland and face wipeout, if Ashcroft are right they are holding up against the tide and should retain around half those seats.

Explaining the difference is a little harder. It could, of course, simply be that public opinion has changed – some of Ashcroft’s polling was done late last year… but most of the Lib Dem collapse in support came early this Parliament, so this doesn’t ring true to me. Looking at the rest of the methodology both polls were conducted by telephone, the political weighting was much the same, the turnout weighting not vastly different.

My guess is the difference is actually a quite a subtle one – but obviously with a large impact! Both Ashcroft and ComRes asked a voting intention question that prompted people to think about their own constituency, candidates and MP to try and get at the personal and tactical voting that Lib Dem MPs are so reliant upon. However, looking at the tables it looks as though ComRes asked that as the only voting intention question, while Ashcroft asked it as a two stage question, asking people their national preference then their local voting intention. The results that ComRes got in their constituency question are actually extremely similar to the ones that Ashcroft got in his initial, national question.

This sounds weird, but it’s actually what I’d expect. When I first wrote the two stage voting intention question back in 2008 my thinking was that when people answer opinion polls they want to register their support for the party they really support, not a tactical vote or a vote for their local MP… and even if you ask the question slightly differently, that’s the answer you are going to get. If you really wanted to get people’s local voting intentions, you needed to first give them the opportunity to express their national support and then ask them their local support.

That though, is just the theory. As I’ve written before when writing about constituency polls of Lib Dem seats and marginal polls of Lib Dem battlegrounds, we don’t really have the evidence from past elections to judge what the most accurate methods are. Hopefully we’ll get enough different constituency and marginal polls over the next three weeks to give us the evidence to judge in the future.

Meanwhile tonight’s YouGov poll for the Sun has topline figures of CON 34%, LAB 35%, LDEM 8%, UKIP 13%, GRN 5%


Lord Ashcroft released another batch of constituency polls earlier today, this time revisiting some of the Lib Dem seats where he had previously found close battles. In Lord Ashcroft’s previous polling in Lib Dem seats he’s often found wide variation from one seat to another, and it’s the same here – in some seats the Lib Dems are holding on against the national tide, in other seats they are doing very badly indeed.

Camborne and Redruth was an ultra marginal between the Conservatives and Lib Dems at the last election. In June 2014 Ashcroft polled the seat and found a close three way battle between the Conservatives, Labour and UKIP. The picture in this poll is far less exciting – a very lead 13 point Tory lead.

North Devon and St Austell and Newquay both had narrow one point Tory leads last time, this time they had more comfortable seven and six point leads for the Tories.

North Cornwall, St Ives and Torbay all saw much less movement. Torbay and North Cornwall both had neck-and-neck ties when Ashcroft last polled them, this time he found a one point Lib Dem lead and a two point Lib Dem lead. St Ives has gone from a one point Lib Dem lead to three points, showing almost no swing from LD to Con at all since the general election.

Turning to the two Lib Dem seats where Labour is the main challenger, Julian Huppert in Cambridge has now opened up a nine point lead over Labour, reducing the swing from LD>Lab to just three points, which would be exceptionally good in a LD/Lab seat.

Finally Lord Ashcroft re-polled Sheffield Hallam, Nick Clegg’s own seat. Naturally this is the poll that got the most attention, as he continues to show Clegg trailing Labour. Voting intentions were CON 16%, LAB 36%, LDEM 34%, UKIP 7%, GRN 6% – a whopping great swing of 19.5% from LibDem to Labour. The Lib Dems criticised the poll for not including candidate names, saying this would have boosted Clegg. Lord Ashcroft pre-empted the criticism by saying that he already asked the constituency specific question and feared putting candidate names in the question would give too much prominence to that as a factor and would risk showing too much of a candidate effect. Both are perfectly justifiable arguments – the reality is we don’t know. Constituency polls have been very rare in the past, so we don’t have lots of constituency polls with and without candidate prompting from previous elections that we can compare to results to make a judgement. There is simply no evidence that would allow us to judge whether candidate prompting in constituency polling is less or more accurate.


-->

Back to those Lib Dem private constituency polls they were so keen to brief the press on last month. When we left the story it had emerged that the polls had been done as purely field & tab, so there was no British Polling Council requirement to release them (that is, Survation just made the phone calls, the actual method and analysis was done by the Lib Dems themselves. In the same way, for example, ICM or Populus’s call centres are sometimes commissioned to do the phone calls for other companies and it doesn’t make it an ICM or Populus poll). Now the Lib Dems themselves have released one of the polls, in Hornsey and Wood Green – tables are here.

Hornsey and Wood Green is the seat of Lynne Featherstone and has Labour in second place. Lord Ashcroft’s polling of Lib Dem seats shows them doing far worse in LD -v- Lab seats than in seats where they are up against the Tories. In Hornsey and Wood Green itself Ashcroft found the Lib Dems trailing by 13 points. The Lib Dems own poll shows them only behind by one point.

As ever, one should be particularly suspicious of polling produced by political parties – certainly one should ignore them unless they cough up the actual tables so we can see what they’ve been up to. In this case the Lib Dems have done just that, so we can see for ourselves. As we knew from Survation’s earlier statement, the polls were not conducted using Survation’s own methodology, but using a methodology directed by the Liberal Democrats. There were a couple of specific factors:

  • The first was that the poll was weighted to actual past vote. There are essentially three approaches to past vote weighting in constituency polling. One is to assume the problems of false recall and people moving constituency are insurmountable, and not to use past vote weighting at all. This is what Survation do in their own polls. Another is to estimate some level of false recall and factor that into your weighting targets, which I think is what Ashcroft does in his constituency polls. The third approach is to assume no false recall and weight to the actual shares of the vote in 2010, which is what the Lib Dems did.
  • The second is that the question itself included the names of the party candidates, which is generally thought to boost the Lib Dems. This is not necessarily a bad thing – certainly I have grave doubts about polls done in Lib Dem constituencies that just ask a standard voting intention question. The alternative approach taken by Lord Ashcroft is to ask a two stage question, asking people a standard voting intention question and then to think about their specific constituency. This also gives the Lib Dems a significant boost.
  • The third was question order. The Lib Dems did not ask voting intention first, instead they asked people to rate Lynne Featherstone first. It is possible that this boosted her personal vote in the subsequent voting intention question.

All three of these methodological choices probably helped the Lib Dems. However that doesn’t necessarily mean they are wrong. I wouldn’t personally have made the same weighting decisions as them, or asked a question before the voting intention question, but that’s the beauty of publishing the tables for people to see: we can judge for ourselves what to believe. The candidate naming question is perfectly reasonable – the fact is, because constituency polls have historically been very rare we don’t really know what the right approach is. It may be that a raw standard question actually gets the best result, it may be that the two-stage question with a constituency prompt gets the best result, it may be that prompting with candidate names gets the best result, it could even be that prompting people to rate their MP first gets the best result (though my own guess is that it is forcing respondents too strongly to consider the candidate). Unless someone is nice enough to commission and release lots of constituency polls using different approaches very close to the election, we will never know.

With all that said, I’ll still be giving no real weight to the Lib Dem private polls for completely non-methodological reasons. I would advise people to ignore them because of potential publication bias. The Lib Dems have commissioned about 120 of these polls, they’ve released one. I don’t think it overly cynical to ponder whether they may have chosen to release one putting them in a relatively good position, rather than one showing them getting a soaking. With sample sizes of 400 or so people, the Lib Dem polls have a margin of error of +/-5% (and that’s on each figure, so on the lead between one party and another it’s double that). By definition, normal random sample error means some of those polls will be overstating the true Lib Dem position by as much as 5 points, others understating it by that much. We have no way of knowing whether there are many other private Lib Dem polls that show the party doing even worse than in the publicly available polls, which they have chosen not to publish. And, to be fair, short of publishing all their private polling there is no reasonable way the Lib Dems can prove it either.


The Lib Dems have been out and about briefing journalists about what their polling shows. This morning the Guardian, May 2015 and The Spectator have all written about it.

Private polling always has a certain allure when spoken of in the media, there is that whiff of forbidden, insider knowledge. It really shouldn’t – beyond asking whether such private polling actually exists, the first major caveat to any claims that private polling shows something different to publicly available stuff is “why should it?”. Political polling doesn’t really make much money, it’s normally done as a shop window to get a polling company’s name known and to create a reputation for accurate research. It is in polling companies’ interest for their voting intention polls to be as accurate as possible, so the publicly available stuff really is the best we can do, there is no more accurate version of the data held back for private clients. Therefore, most of the time when political parties claim their private polling shows them doing better than the public polls it suggests they are making it up, or they have been commissioning stuff that asks things in a skewed way for propaganda purposes (what Lord Ashcroft has called in the past “comfort polling”).

Even if the full details of private polls are released, with all the methodology and tables available for scrutiny, you should still view them sceptically. Parties decide which polls to release or brief journalists on, if any. One thing you never see is a political party releasing a poll that is not helpful to them, so even if the polling itself is above board, there is a strong publication bias; only the stuff that helps the party is published.

To illustrate that, cast your mind back to the polling of Lib Dem seats conducted by Lord Ashcroft. One of the most obvious findings was how much the Lib Dem performance varied – in some seats like Eastborne, Birmingham Yardley or Sutton & Cheam the party is doing very well indeed. In other seats like Somerton and Frome, Chippenham and Brent Central they are doing atrociously. Imagine the very different narratives that could be created by selectively releasing polls from those first three seats, as opposed to selectively releasing polls from the latter three.

So what should we make of the Liberal Democrat claims? Well, the polling does genuinely exist – Survation are a proper company and while the newspaper reports don’t include specifics, several journalists have assured me they were shown the actual figures. For once, there is also a legitimate reason why the Liberal Democrat polling might show them in a better position than the published polling – the articles suggest they prompted using candidate names. We know that a lot of Lib Dem support is reliant upon tactical voting and personal votes, so it seems reasonable that polls that include the candidate names in Lib Dem held seats might show the Lib Dems doing better. Until we see tables we can’t tell what other methodological factors may have been at play.

The articles claim that the Lib Dems have done about 100 constituency polls, while it seems journalists were shown results from about a dozen or so, so it is impossible to know how representative this group were, or whether they were cherry-picked to create a good impression of the Lib Dem performance.

Even if you take the claims that the Liberal Democrats make at face value, they don’t actually show much that contrasts with existing publically available data that much. According to the Guardian the party “is on course to remain “competitive” in seats that would fall if there was landslide against the Lib Dems, such as Cheltenham, St Ives, Cardiff Central, Eastbourne, Solihull, Cheadle, Leeds North West, Cambridge and Bermondsey.” From talking to several other journalists who were there, I’m told they were also shown figures from St Austell and some other Labour facing seats, so perhaps a dozen in total.

The word “competitive is vague” – it could mean both a little ahead… or a little behind. As it happens, Lord Ashcroft has conducted polls in nine of those seats, and in most of them the Lib Dems are indeed “competitive”. In three of them (Cheltenham, Cheadle, Eastborne) Ashcroft found clear Lib Dem leads, in two others (Bermondsey and St Ives) he found the Lib Dems just ahead (though I’m told the Lib Dem polling shows them doing better than that). In Cambridge Lord Ashcroft he found them a point behind… but that counts as “competitive” in my book. The other three are St Austell & Newquay, Solihull and Cardiff Central, where Ashcroft found the Lib Dems trailing. If the Lib Dem data was kosher, then it may well show the Lib Dems doing better in those seats… but polls vary, and perhaps there are other, unmentioned, polls that show the Lib Dems doing worse than in Ashcroft’s polling.


Lord Ashcroft has published a new batch of constituency polling. I hesitate to call it marginals polling, since we’ve moving up into some less marginal territory with today’s polls. Ashcroft has polled four different groups of seats in this set (all the tabs are here.)

The first is the next cohort of Lib Dem -v- Conservative marginals, this group are those seats with a Lib Dem majority of between 9% and 15% over the Conservatives, so we are no longer looking at ultra-marginals. The average swing from the Liberal Democrats to Conservatives in these seats is 2%, nowhere near enough to win seats like these. However, as we’ve seen in previous Lord Ashcroft polls of Lib Dem marginals there is an awful lot of variation between individual constituencies – some seats (Carshalton & Wallington and Thornbury & Yate) are actually showing swings from Con to LD. At the other end of the scale two seats are showing large enough swings for the Conservatives to win the seat (North Devon and Portsmouth South, which has a chunky 9 point swing from LD to Con, presumably at least partially connected to the scandal around Mike Hancock).

The second group of seats consists of two more Lib Dem seats with Labour in second place. Lord Ashcroft’s previous polling in LD v Lab seats essentially showed a complete Lib Dem collapse, raising the possibility of an almost complete wipeout for Liberal Democrat MPs where Labour was the main opponent. One of the seats here – Burnley – follows that pattern, with a ten point swing from LD to Lab. The other, Birmingham Yardley, represented by John Hemming, bucks the trend. There is still a 2.5% swing from LD to Lab, but it is smaller than we’ve seen in other LD -v- Lab seats and would be small enough for Hemming to hold on.

The third group of seats is two unusual seats – the close three-way marginal of Watford, and Wyre Forest, an Independent seat between 2001 and 2010. Neither of these really fit into any broader category, but looking at them as individual seats Watford shows little relative movement for the three main parties – all are down a little, UKIP are up a lot but still in fourth place, meaning the Conservatives retain a narrow lead. Wyre Forest was held by Dr Richard Taylor between 2001 and 2010. He’ll be standing again come the next general election for the National Health Action party, but I think under the same Kidderminster Health Concern label that he won on in 2001 and 2005. Ashcroft’s poll currently has the Conservatives holding the seat on 32% with UKIP in second on 27%, Labour 16%, Lib Dem 7%, Green 5%, Other 13%. The others aren’t identified in the poll, but is presumably largely Dr Taylor’s supporters.

Finally Ashcroft polled three of the four seats that will be contested by the main party leaders come the election – Sheffield Hallam, Doncaster North and Thanet South (presumably he didn’t do Witney because he thought it would be too boring… it would seem there comes a point when even Lord Ashcroft saves his money!). Party leaders normally do pretty well in their own seats. It is extremely rare for them to lose their own constituency and they very often outperform their party nationally. Such is the collapse of Liberal Democrat support however people have seriously raised the possiblity of Clegg losing his own seat – Ashcroft’s poll has it very close. Clegg is on 31%, Labour on 28%, just three behind (and this is on the question prompting people to think about their own constituency, the standard voting intention question had Labour a point ahead). Ed Miliband’s Doncaster North seat is traditionally a very safe Labour seat that should pose no concerns for him, but there was some speculation about how well UKIP might do. The BNP have held their deposit there at the last two elections and their was some significant support for the English Democrats too, with the far-right parties now collapsing and UKIP hoovering up that right-wing protest vote it looked as if there could be some potential. In fact Ashcroft’s poll did find UKIP in second place in Doncaster North, but 12 points behind Ed Miliband. Finally Thanet South, the seat where Nigel Farage plans to stand at the general election. Current figures there are CON 34%, LAB 26%, LDEM 7%, UKIP 29% – so UKIP in a strong second place, but not currently quite enough to send Farage to Westminster.