Archive for the 'Pollsters/polling' Category


What will next set of polls show? I have no idea

Friday, September 6th, 2019

This afternoon a friend asked me what I thought the next set polls, which I’m expecting this weekend, would show. My honest answer is I don’t have a clue. As Ed Miliband’s pollster points out above calling David Cameron a chicken in 2014 and 2015 didn’t have any negative impact for David Cameron.

As we can see the Tories are going for the Corbyn is a coward meme, which they think could work I suspect it could given Corbyn’s many requests for a general election but at the back of my mind the fact Boris Johnson has flopped at getting an election it might make him look impotent.

Coupled with the other sub optimal stories that have happened to Boris Johnson this week where he’s looked like Gordon Brown without the people skills, the resignation of his brother is one of those things that do seep into the mind of the voters because it’s a bit of drama that they can enjoy.

But I can see some switchers from the Brexit Party moving to the Tories because the expulsion of pro EU MPs like Ken Clarke will show to them that Boris Johnson really will deliver Brexit on Halloween.

I can also see the Brexit Party surging if they think the Benn bill is going to see the referendum overturned.

Finally I can also see Labour gaining from pro EU voters who have liked Corbyn effectively halting a No Deal Brexit.

These competing forces makes calling the next set of polls difficult, so my official prediction is that I do not know what the next polls will show, all I can say is people will spin them and over interpret them.

So I’ve made my prediction for the next set of polls, time for PBers to make their predictions in the comments below.


Update – We have the first poll of the weekend


The Remainers of the Day. Why are pollsters consistently finding more Remainers than you would expect?

Friday, September 6th, 2019

I don’t take opinion polls very seriously and nor should you. For all that, they tell us something and some of the time we have no better clue as to what is going on than what they tell us. Right now, they seem to be telling us something rather interesting.

For many months, pollsters have consistently found appreciably more respondents in their sample who said they voted Remain in 2016 than said they voted Leave. Since Leave won 52:48, this is not what you would expect. For example, the most recent YouGov, Survation and Ipsos MORI polls have all shown this effect. The Ipsos MORI poll was conducted on a sample that on an unweighted basis would have voted 57:43 Remain.

Pollsters can deal with this of course in the weighting of the sample, but there comes a point where such a consistent finding needs to be considered further. Just why are pollsters’ samples so consistently askew in this regard?

There are quite a few possible explanations, and several of them may contribute to the effect. Let’s have a look at some of them.

Some people who said they voted Remain have forgotten that they voted Leave

As you would expect, the pollsters are well ahead of me when looking at such anomalies. Anthony Wells of YouGov looked at this a while back so far as concerned recollections of voting in 2017.

What he found was that memory is a slippery, plastic thing.  If you compare what YouGov respondents say they did in the 2017 now with what they said a couple of years ago, an appreciable chunk of respondents have retrospectively edited their vote from Labour to elsewhere.

We might easily be seeing a similar effect when voters are being asked how they voted in the referendum, deciding with the benefit of hindsight that rather than voting for Leave they came out for Remain.

If they have indeed forgotten, it seems tolerably safe to assume that they now identify with the Remain cause. If so, it would be wrong to downweight.

Some people who said they voted Remain are lying about the fact they voted Leave 

Some of those people who have retrospectively changed their votes might not be doing so innocently. Some might be deliberately lying. Why would they do a thing like that?

There are two possible reasons pointing in opposite directions. Some people might be embarrassed about the choice that they made. We can take it that they now identify with Remain and should not be downweighted. Others, however, may regard it as socially unacceptable to be identified as a Leave supporter. If so, pollsters do need to downweight to reflect their concealed preferences.

Some people who said they voted Remain did not in fact vote at all

You know the type. They tweet #FBPE, they sign petitions, they might even go on marches. Voting in the referendum, however, was a step too far. Not that they would admit that, of course.

If the Remain figure includes such people, the pollsters are right to downweight their contribution. There is no reason to assume that they will behave differently next time.

Some people who voted Leave are reluctant to take part in opinion polls

Allied to the shy Leavers who claim to have voted Remain are those Leavers who do not want to take part in opinion poll surveys. There will be some Remain voters who are similarly unenthused, but if the refusals skew in the Leave direction pollsters need to unskew by upweighting their presumed allegiances.   

Some people who voted Leave are harder for pollsters to find

The people who respond to opinion polls are going to be unrepresentative in one way or another. The hope of pollsters is that the ways in which they are unrepresentative don’t matter for the matters being polled about.

One big risk – relevant to any political poll but it seems particularly relevant in relation to the EU referendum – is that the respondents to an opinion poll may be disproportionately enthralled by politics. If those who find politics tedious but still troop out to vote react differently from the political wonks, the poll results will be awry.

This seems entirely possible. If it is correct, Leave respondents will need to be upweighted (and Remain respondents correspondingly downweighted). But even this won’t work reliably because engaged Leavers and disengaged Leavers might well be reacting differently.

The electorate has changed since 2016

This is not so much a hypothesis as a fact. It may be distasteful to say so but we can be confident that older Leave-leaning voters have been replaced by debutant Remain-leaning voters. Over a period of three years that might already have wiped out the original Leave lead, all other things being equal.

Moreover, there will have been an influx of naturalising immigrants over the last three years (in part so that they can regularise their legal right to stay in Britain). We can expect this group also to lean heavily Remain.

For this reason it seems wrong to reweight the sample back to 48:52 as par.  That was then but this is now. Since most pollsters seem to do this, it appears that the downweighting does indeed seem to be at least a bit overdone.


The only sensible conclusion is that it’s all a bit odd.  It does look as though Remain supporters’ views are being a bit underrepresented in polls (suggesting that the Conservatives in particular might be a bit overstated and that scepticism about the wisdom of leaving the EU is being understated). But I do have this gnawing doubt that the samples being obtained are potentially unrepresentative in ways that might matter quite a bit. You should always be sceptical of opinion polls’ finding. Right now, the scepticism should be turned up to 11.

Alastair Meeks


Jo Johnson’s resignation will only reinforce the doubts that Boris Johnson is only interested in himself and not the national interest

Thursday, September 5th, 2019

In a move more reminiscent of Game of Thrones meets the Milibands Jo Johnson’s resignation as both a minister and an MP has the potential to be the most damaging event in Boris Johnson’s disastrous week. If things pan out as expected, then he either has to deliver an extension to Article 50, break the law, or resign and break the record of George Canning as the United Kingdom’s shortest serving Prime Minister.

The strategy to have an election before the 31st of October looks like failing as the Commons last night left Boris Johnson looking like an impotent porn star, unable perform and becoming a figure of fun.

Back to Jo Johnson’s resignation, Boris Johnson is launching the de facto Tory general election campaign in Yorkshire today. and I’d expect it to be dominated by questions about Jo Johnson’s resignation. As we saw with the Milibands this sort of stuff can be repeatedly used to confirm to the public Boris Johnson’s unsuitably for the top job.

‘His brother doesn’t trust him on Brexit, why should you?’ is the sort of the attack line you can expect to be used, and I think it will work, just look at the polling from YouGov conducted on Tuesday and Wednesday of this week.

Twice as many voters think Boris Johnson puts his own interests of the national interest, that’s a very bad place to be in. His performances in the Commons this last week also hint that he will perform very poorly in a general election campaign.

Also from the same poll Boris Johnson’s strategy to try and go for a No Deal might not be the vote winner his strategist think it will be.

One thing we’ve learned from recent polling failures is that it is not wise to look solely at the headline voting intentions but to look at the supplementaries as well.Boris Johnson trying to sell a No Deal Brexit to the voters might turn out sub optimal for the Conservative party.



This is not a government with any real support for its approach and main policy

Friday, August 30th, 2019

Today sees some polling about Boris Johnson turning the United Kingdom in to a prorogue nation, it’s not particularly pleasant reading for the mandateless Prime Minister whose government has not won a single vote in Parliament.

55% of the public do not trust Boris Johnson to make the right decision on Brexit. Only 13% of the public believe the Prime Minister’s reasons for prorogation, 70% think prorogation was done to limit the opportunities to stop No Deal which the Defence Secretary admitted to yesterday, then Boris Johnson effectively did the same today.

Further polling backs other recent polls that show significantly more people are opposed to No Deal than support it.

I wonder if this is these polling results are an artefact of the partisan times we live in after the 2016 referendum coupled with Boris Johnson lacking a mandate from the country, after all Boris Johnson receiving 100,000 fewer votes in winning the Tory leadership this year than Owen Smith received when he lost to Jeremy Corbyn in 2016.

But yet despite all these supplementaries being sub optimal for Boris Johnson the Tories have an 11% lead with YouGov and the Prime Minister has a 53% lead over Corbyn in leader ratings and Ipsos MORI has a similar result.

As a strong believer that leader ratings are a much better predictor of general election results than voting intention I suspect Boris Johnson will win an autumn general election based on the leadership polling. Oh Jeremy Corbyn, why do you have to be so dire?

My other expectation is that like 1992 the Tories will get absolutely hammered in the following general election as sustained No Deal will be like the winter of discontent meets Black Wednesday and will keep the Tories out of power for a significant period.


PS – For an excellent in depth analysis of the Ipsos MORI polling see this twitter thread by Keiran Pedley by clicking here.


Before we can make judgements about the outcome of an early general election we need new Scotland only polling

Tuesday, August 27th, 2019

The last one was in June

There’s been a lot of GB voting intention polling since Mr Johnson became the new Tory leader and Prime Minister but none of it has been Scotland specific. One thing we do know is that is can be highly misleading keying the latest GB poll shares into Baxter and getting anything that is relevant to Scotland.

North of the border, as we all know, is the part of the UK which has seen the most turbulence in recent general elections. In 2010 Scots LAB won 41 of the 59 seats only to lose all but one of them in the SNP landslide 5 years later.

Then 2017 the Tories made something of a recovery and picked up 12 gains to add to the single seat making them the second party in Scotland .

What is hugely interesting for election watchers is that the largest majority that the SNP secured in any of its 36 Scottish seats at the last election was 47%. A large proportion of what they hold is vulnerable something that applies to almost all the parties there.

As the Wikipedia panel above shows the Tories were in something of a mess in the most recent surveys. The numbers suggest that Ruth Davidson’s party could be on the point of losing all but one of the hard won gains from 2 years ago. But is that really going to happen?

So much has happened politically since the last Scottish poll and we have no real sense yet of how the new PM is going down for of the border. Will having Johnson in charge help or hinder the blue team?

Hopefully we should be seeing some new Scotland polling in September. There is tendency for these to come out just before the SNP conference.

Mike Smithson


If BJohnson is planning an election the numbers continue to look good

Friday, August 23rd, 2019

And JSwinson’s response to the PM Corbyn suggestion doesn’t seem to have hurt the LDs

August is generally a month when we see fewer Westminster voting polls and it’s probably because of the possibility of an early election that this year we’ve seen as many surveys as we have.

Even leaving Kantar aside the Tories will feel relatively comfortable about where they are which is being helped by the ongoing poor numbers for Labour. The ambivalence of Corbyn’s party on Brexit and the antisemitism row have taken their toll and its hard to see the party recovering as much in an election campaign as it did at GE2017.

The strongly anti-Brexit LDs have seen their Commons numbers increase by three in recent months with the addition of Umunna who was elected as a LAB MP and Sarah Wollaston who switched from the Tories via TIG and ChangeUK to the party. On top of that was the Brecon by-election gain. They are hoping that the Sheffield Hallam MP will carry out his promise and step down as MP on September 3rd.

The Greens have been prospering well up from 1.6% at GE2017 to 8% in one poll. My guess is that they will pick up more than one MP at an early election if local agreements can be worked out with the LDs.

Farage’s Brexit party has seen a decline partly because it isn’t in the news at the moment and BJohnson has stolen some of their thunder.

Mike Smithson


At least ComRes didn’t bring Nelson Mandela into its controversial poll

Tuesday, August 13th, 2019

When mentioning his name might get better results?

All the discussion over alleged leading questions in the ComRes poll have provided a peg fo me to highlight one of my favourite polls ever.

In the build-up in 2005 to the resolution London’s bid for the 2012 Olympics a poll was commissioned to try to show that people in the capital backed the idea. This was the series of questions in the order that they were put:-

“Are you aware that Nelson Mandela recently came out in support of London hosting the 2012 Olympic Games?” YES 60% NO 39%

“To what extent do you agree or disagree with Nelson Mandela’s view that because London is a diverse city, providing a home to hundreds of different nationalities, it would be the best place to hold the Olympic Games.” AGREE 72% DISAGREE 13%

Would you support or oppose London being chosen as the host city for the 2012 Olympic Games?” SUPPORT 79% OPPOSE 13%

A few years later the SNP specially commissioned YouGov poll over their handling of the release of the Lockerbie bomber. One finding was that voters in Scotland divided two to one in saying that the affair had enhanced Scotland’s reputation.

Just look at the question however. It read “Do you believe Nelson Mandela’s comments in support for the release of Ali Mohmed Al-Megrahi on compassionate grounds has enhanced or damaged Scotland’s reputation internationally?”

I wonder what both the SNP and the London Olympic polls would have produced without the mention of Nelson Mandela?

Mike Smithson


(UPDATED) Could Welsh Labour be about to experience a near wipe-out similar to that which Scottish Labour saw at GE2015?

Monday, July 29th, 2019

Generated by IJG JPEG Library

It is not often that all eyes are on Welsh politics but yesterday’s Tweet from the respected Professor Roger Scully of Cardiff University has really set things going.

We don’t get very much Wales only polling but what there is generally associated with Professor Scully. And for him to be trailing his survey for ITV in this way suggests a sensation.

His tweet reminds me of a similar one from Ben Page of Ipsos-MORI in late 2014 relating to a poll that his firm had produced for STV. There was a similar big build up and then the numbers can and which point pointed to the total collapse of Labour in Scotland. This is, of course, what happened six months later at GE2015. LAB moved from holding 41 of Scotland’s 59 seats to just a single MP.

We know from Wales only polling over the past nine months that Labour’s once invincible position in the Principality is on the decline. Last December Survation had Corbyn’s party in 47% with Scully’s YouGov poll at 43%. In May that was down 25% with the Brexit party just two behind.

At GE2017 Labour won 28 of the 40 Welsh seats. If that number is substantially reduced and there is still no recovery for the party in Scotland then it is very difficult to see how LAB can win most seats overall in a UK general election.

We wait in anticipation for Professor Scully’s new poll. Hopefully it will be out by late morning.

Updated – the poll is now out

Thus LAB drops to its lowest ever level in Wales with the Tories up 7 to take the lead and the LDs up 4. The Brexit party’s down 5 Plaid up 2

Mike Smithson