Rob Hayward, the former Tory MP turned psephologist, gave a presentation at ComRes on Monday which has stirred up some comment about whether the polls are underestimating Conservative support.

Historically the polls have tended to underestimate Conservative support and/or overestimate Labour support. It was most notable in 1992, but was a fairly consistent historical pattern anyway. Since the disaster of 1992 this bias has steadily reduced as pollsters have gradually switched methods and adopted some form of political control or weighting on their samples. In 2010 – at last! – the problem seemed to have been eliminated. I hope that the polling industry has now tackled and defeated the problem of Labour bias in voting intention polls, but it would be hubris to assume that because we’ve got it right once the problem has necessarily gone away and we don’t need to worry about it anymore.

In his presentation Rob compared polls last year with actual elections – the polls for the European elections, for the by-elections and for the local elections.

I looked at how the polls for the European election did here and have the same figures as Rob. Of the six pollsters who produced figures within a week or so of the election five underestimated Conservative support. The average level of Tory support across those polls was 22.2%, the Tories actually got 23.9%. The average for Labour was 27%, when they actually got 25.4%.

Looking at by-elections, Rob has taken ten by-election polls from 2014 and compared them to results. Personally I’d be more wary. By-election campaigns can move fast, and some of those polls were taken a long time before the actual campaign – the Clacton polls, for example, were conducted a month before the actual by-election took place, so any difference between the results and the polling could just as likely be a genuine change in public opinion. Taking those polls done within a week or so of the actual by-elections shows the same pattern though – Conservatives tend to be underestimated (except in Heywood and Middleton), Labour tends to be overestimated.

Finally in Rob’s presentation he has a figure for polls at the local elections in 2014. I think he’s comparing the average of national Westminster polls at the time with Rallings and Thrasher’s NEQ, which I certainly wouldn’t recommend – the Lib Dems for example always do better in local election NEQ than in national polls, but it’s because they are different types of election, not because the national polls are wrong). As it happens there was at least one actual local election poll from Survation.

Survation local election: CON 24%, LAB 36%, LDEM 13%, UKIP 18%, Others 10%
R&T local election vote: CON 26%, LAB 36%, LDEM 11%, UKIP 16%, Others 12%

Comparing it to the actual result (that is, the actual total votes cast at the local election, which is what Survation were measuring, NOT the National Equivalent Vote) these figures were actually pretty good, especially given the sample size was only 312 and that it will be skewed in unknown ways by multi-member wards. That said, the pattern is the same- it’s the Conservatives who are a couple of points too low, Labour spot on.

So, Rob is right to say that polls in 2014 that could be compared to actual results tended to show a skew away from the Conservatives and towards Labour. Would it be right to take a step on from that and conclude that the national Westminster polls are showing a similar pattern? Well, let me throw out a couple of caveats. To take the by-election polls first, these are conducted solely by two companies – Lord Ashcroft and Survation… and in the case of Survation they are done using a completely different method to Survation’s national polling, so cannot reasonably be taken as an indication of how accurate their national polling is. ICM is a similar case, their European polling was done online while all their GB Westminster polling is done by telephone. None of these examples includes any polling from MORI, Populus or ComRes’s telephone polling – in fact, given that there were no telephone based European polls, the comparison doesn’t include any GB phone polls at all, and looking at the house effects of different pollsters, online polls tend to produce more Labour-friendly figures than telephone polls do.

So what can we conclude? Well, looking at the figures by-election polls do seem to produce figures that are a bit too Laboury, but I’d be wary of assuming that the same pattern necessarily holds in national polls (especially given Survation use completely different methods for their constituency polling). At the European elections the polls also seemed to be a bit Laboury… but the pollsters who produced figures for that election included those pollsters that tend to produce the more Laboury figures anyway, and didn’t include any telephone pollsters. It would be arrogant of me to rule out the possibility that the old problems of pro-Labour bias may return, but for the time being consider me unconvinced by the argument.

UPDATE: Meanwhile the Guardian have published their monthly ICM poll, with topline figures of CON 30%(+2), LAB 33%(nc), LDEM 11%(-3), UKIP 11%(-3), GRN 9%(+4) – another pollster showing a significant advance for the Green party.


Since the Scottish referendum we’ve had Scottish polls from MORI, Panelbase, YouGov and Survation and they’ve been consistent in showing large leads for the SNP over Labour in Westminster voting intentions. ICM now have a new Scottish poll out and it shows the same as other companies – topline Westminster voting intentions are CON 13%, LAB 26%, LDEM 6%, SNP 43%, UKIP 7%, GRN 4%.

The 17 point SNP lead is smaller than the 24 point lead that Survation recorded at the start of the week (and without tables yet we can’t really speculate why) but would still produce a landslide win for the SNP if repeated in the general election next year. In the Guardian write up they mention some analysis by John Curtice suggesting that Labour may do even worse than uniform swing suggests – looking at responses from areas where Labour was over 25% ahead of the SNP in 2010 shows the Labour vote dropping more there than average. I’d be wary of reading too much into sub-samples of voting intention in a poll that’s only 1000 people to begin with, but nevertheless this seems perfectly plausible for the reasons I mentioned here – when there is a huge drop in support for a political party a uniform swing does start to become untenable due to a floor effect… there are simply too many seats where a party doesn’t have enough support to begin with to lose that much, so they have to lose more votes in places they had more votes.

UPDATE: Full tabs are here, and reallocation of don’t knows did happen and did help Labour – it would have been a nineteen point lead otherwise.


-->

The monthly ICM poll for the Guardian came out today, with topline figures of CON 28%(-3), LAB 33%(+1), LDEM 14%(+3), UKIP 14%(nc), GRN 5%(-1). Tabs are here. There’s a movement from Con to Lab since ICM’s previous poll, but nothing that couldn’t be normal margin of error – the broader picture still suggests a very small Labour lead, with no strong trend (in November the average Labour lead was 1.6%, so far this month it’s 1.3%).

This is the first time since September that any poll hasn’t shown UKIP ahead of the Liberal Democrats. The previous one was also ICM, and apart from one unusual Populus poll in July you have to go right back to March to find polls from other company doing the same. ICM consistently show the highest level of support for the Liberal Democrats for methodological reasons. This is largely because of how they handle don’t knows – when people say they don’t know how they’d vote, ICM look at how they voted at the previous election and assume that 50% of them will end up voting the same way. This is based on recontact surveys of don’t knows after previous elections and has made polls more accurate in the past… but of course, we can’t know until May whether that will still hold true under the sort of political realignment we seem to be seeing this Parliament. Without the reallocation ICM’s figures today would have been LDEM 11%, UKIP 15% – so it would have been quite a high Lib Dem figure anyway even without the adjustment.

Ipsos MORI’s month political monitor is also due. Today’s Evening Standard reported some figures, but I assume they are saving up the voting intention figures for tomorrow. The data so far is here, and shows people’s optimism about the economy in general (as opposed to their personal finances) dropping to its lowest since last year. I wrote about similar findings from YouGov at the start of the month, so this does appear to be more than a single poll; people’s confidence in the economic recovery does seem to be faltering a bit.


Monday tends to be the day we have the most polls (as telephone polls are usually done over the weekend) and today is no different, with polls from ICM, Ashcroft and Populus.

The monthly ICM/Guardian poll has topline figures of CON 31%(nc), LAB 32%(-3), LDEM 11%(nc), UKIP 14%(nc), GRN 6%(+2). Labour are down a bit on their recent results, their lead back to one point (ICM had been showing Labour and Conservative roughly equal in the summer, but their Autumn polls were showing larger leads).
The weekly Ashcroft poll has topline figures of CON 30%(nc), LAB 29%(nc), LDEM 10%(nc), UKIP 16%(nc), GRN 7%(+1). Having got a repuation for somewhat volatile figures, today’s are rock solid. Voting intentions are almost wholly unchanged since a week ago (tabs are here)
The twice weekly Populus poll has topline figures of CON 34%, LAB 36%, LDEM 8%, UKIP 13%, GRN 4%. A two point Labour lead is wholly in line with Populus’s polls last week and in late October (tabs are here.)

We still have the daily YouGov/Sun poll to come, but so it doesn’t look as the fuss over Miliband’s leadership is having any significant effect. Populus and Ashcroft show no real change and while ICM show a small drop for Labour, in the context of other polls showing no movement it’s nothing that can’t be normal sample variation.


Time for a round up of Sunday’s polls, with new stuff in the Sunday papers from YouGov, Survation, Opinium and ICM.

YouGov’s weekly poll for the Sunday Times has topline figures of CON 33%, LAB 33%, LDEM 7%, UKIP 16%, GRN 6%. The poll also asked a series of questions about how people would vote with different Labour leaders. In a control question asking how people would vote if the leaders remained Cameron, Miliband and Clegg the answers were CON 33%, LAB 31% (so the effect of reminding people of the current party leaders still seems to produce a slight positive Cameron effect or negative Miliband effect). If Yvette Cooper were Labour leader the position would be the same, a two point Conservative lead. If Ed Balls was the leader it would be worse, a three point Conservative lead. In contrast with Alan Johnson as leader Labour would be two points ahead (CON 31%, LAB 33%.

I’ll give my usual caveats about questions like this – people are answering them when on very little information, they don’t know what policies or priorities those alternative leaders would set, how the media would react to them and so on. In the same poll, YouGov found that only 42% of people think they could recognise Yvette Cooper from a photo… if you don’t even know what Yvette Cooper looks like, I’m guessing you don’t have a thorough understanding of what she would prioritise as Labour leader. It’s a response based on a very crude impression of those potential leaders based on what tends to be the very limited public awareness of opposition politicians. Nevertheless, those crude first impressions count, so it’s a good sign for Alan Johnson.

Survation also had a new poll with topline figures of CON 29%(+2), LAB 34%(+3), LDEM 6%(-3), UKIP 23%(-1), and they too asked a series of hypothetical voting intention questions with different Labour leaders. In the Survation poll they displayed a biography and played a video clip of each potential leader and asked people questions about them before the questions. This allowed them to include people with extremely low public awareness like Chuka Umunna, though does of course rely upon the choice of biogs and video clips (given bias is often in the eye of the beholder, choosing clips that even those who don’t like the eventual results think are fair is incredibly tricky). The control question with Ed Miliband had a Labour lead of 4 points. In the Survation poll Yvette Cooper did worse than Miliband (neck and neck with the Tories), Andy Burnham just the same (4 point lead), Alan Johnson and Chuka Umunna did best – both extending Labour’s lead to 8 points. A voting intention question asked after video clips of Labour leaders is obviously skewed towards Labour, but it’s the relative performance between the different leaders that counts, and again it’s good for Alan Johnson, and now also for Chuka Umunna.

Meanwhile the fortnightly Opinium poll for the Observer has topline figures of CON 29%(-4), LAB 32%(-1), LDEM 9%(+3), UKIP 19%(+1).

Finally there was an ICM poll in the Sunday Telegraph. As usual with ICM/Sunday Telegraph polls, this asked the public to predict vote shares rather than ask people how they would vote themselves. The average response now has the Conservatives getting slightly more votes than Labour.