This comment was posted by a regular contributor who uses the name DunGroanin' in response to my discussion of the Observer's reported 19% opinion poll lead for the Tories. I tho0ught it worth sharing as it offers what seems like an entirely plausible explanation as to why the lead may be overstated:
I spent a lot of time last election blowing major holes in their balls polls, especially the commissioned ones by Opinium for the Obsessive Groaniad. Also one of the reasons why I done with them.
I called it pretty correctly. By looking at their RAW data. And I say the current tory lead is exactly what it was at the end of 2017. If you believe their raw data.
This time I hadn't bothered up till now. Drilling down into data is the key. Even as the representation of the data has changed… in my opinion they have manipulated raw data!
The Obsessives splash yesterday that claims a headline of
‘Conservatives open up 19-point lead with 47% share of the vote'
https://www.theguardian.com/politics/2019/nov/23/tories-renewed-poll-boost-brexit-party-candidates-pull-out-opinium-observer
Now understand that there is a catch up period by Labour as the election campaign proceeds and fair coverage in the media allows that. Last time that ended with the overall lead of 800,000 votes over the whole 650 seats by the tories.
‘Despite a drop in the number of seats, the Conservatives actually saw a rise in vote share (up 5.5% points to 42.4%). Labour's vote share rose at an even greater rate (up 9.5% points) and now sits at 40.0%.'
https://data.london.gov.uk/blog/the-2017-general-election-the-numbers-behind-the-result/
https://www.bbc.co.uk/news/election/2017/results
THE DIFFERENCE BETWEEN THE TWO PARTIES WAS 2.4%.
Remember that percentage — 2.4%.
Now lets drill down into the Opinium poll.
1. They state ‘Source: Opinium poll: 2,003 UK adults surveyed from 20 to 22 November 2019' — that is 3 days over which the two thousand and three people were interviewed. Things were happening over these 3 days and doesn't include the Friday debate.
2. In their new presentation of the data — https://www.opinium.co.uk/wp-content/uploads/2019/11/VI-20-11-19-website.xlsx There are now multiple data sheets. The relevant sheet is 5a. It asks what the responders voted in 2017, of the number that are used to derive the headline ‘result'.
3. The actual number of responders who voted in 2017 is a total of 1,368.
4. Off these 46% (508) voted Tory and 36% (421) Labour in 2017 — a difference of 10% not the 2.4% of the actual result remember!
5. The actual 2017 Tory share was 42.4% not 46% as of the responders. The actual Labour share was 40% not 36% of the responders. Self selected responders, many who couldn't even ‘remember' how they voted 2 years ago btw (ahem!).
So the Tory share of responders is over represented by 7.6% (4)
6. Then let us look at sheet 3 & 3b which mutates the numbers even further. The first has tory 35% (558) , Lab 23% (372). The second has tory 37% (585) , 24% Lab (379) — both have a total respondents used as 1592.
So the magic trick is pulled! How does my point 6 compare to my point 4?
I put all that up there not expecting most to follow it but to show the ‘data'. It can be ignored and you can just take my opinion below or their opium from Opinium (a firm that should hang it's head in shame — i believe).
––––
So how many ways to skin this very thin cat?
The raw data adjusted for the 7.6% starting variance would give the Tories a current lead (to the 3 day period ending 22/11) of between 4.4% and 5.4%.
With undecideds of some 16%.
I am sticking to my prediction of a landslide based on how the numbers improved through the campaign last time.
Anyway the 19% HEADLINE current lead is balls!
Do we really need to wonder why such magical thinking is going on in the Obsessive Groaniad?
Thanks for reading this post.
You can share this post on social media of your choice by clicking these icons:
You can subscribe to this blog's daily email here.
And if you would like to support this blog you can, here:
This may well be a more accurate analysis but the damaging headlines are out. There are probably significantly more ‘undecideds’ this year. But under FPTP it’s where the votes are that count more than how many, isn’t it? Our elections are won and lost in just a handful of constituencies – some say as few as 30. My gut feel is that Labour will garner more support the closer we get to Dec 12th, but it will be too little too late – and probably not where they most need it, i.e. their traditional so-called ‘heartlands’ with a strong ‘Brexit’ orientation. However, I accept that playing amateur psephologist is a dodgy game. I know more about coffee!
I don’t understand. It reads as if he is saying 46 per cent of 1368 is 508
(Thanks Prof. – I am still waiting to see if there are any numbers on the Friday debate,)
In the meantime some instant reaction to the great mysteries expounded in Telford – Fermats last theorem …Shergar!
There we have it – a room mostly occupied by current mp’s and odds and sods, all seemingly outnumbered by the ‘colleagues in the media’!
Thanks Laura, thanks Robert, thanks Sky, Telegraph & Mail.. and err thanks Rowena for making me waffle and that local kid who I promised a lolly to.
The room cleared in 5 mins.
LBC lickspittle announces ‘bobo has won it’
They think it’s all over and done – the ‘COLLEAGUES IN THE MEDIA’!
So are you predicting a Labour landslide? As in an overall majority?
If you look at the first Survation poll released at the start of the campaign, they had labour 6 points down. Subsequent Yougov polls using the same methodology have shown the gap between Labour and Tory cut from 17 to 12 points. This was before the live debates of Friday. Survation were the only polling company that got it right last time. That would imply that the gap could be as close to 1 point, which would probably imply a labour minority/SNP coalition government. After Jo Swinsons mauling in the debate, I would predict at least a few percent of Libdems going over to Labour in the final few weeks, which could make them the biggest party.
Interesting times.
I am tempted to say two things:
1) The younger vote might very well be more crucial than realised.
2) The behaviour in the polls now up to election day could very well be affected by who drops the next biggest bollock during the ‘campaigning’ and their is certainly more of a propensity for a certain fellow from Eaton to do just that, given that too many of his cabinet are too reprehensible as human beings to be allowed into the spot light. The pressure he is bearing and the opportunity to put his foot in it will be too much to resist.
I agree with Richard about the age of media manipulation but I would also add that what we are still seeing is the lasting success of the Thatcherite model of politics in that rather than being about compromise and win/win, British politics is about winning at ALL costs and destroying the opposition once and for all.
We are country where – if we are honest and with some exceptions such as the late Speaker and some of the Tory BREXIT Refuseniks – democracy exists now in name only.
By late speaker, you don’t mean Bercow, do you? He is the former speaker. Of course, you could have had another speaker in mind.
Larry
This is a blog. It’s not a perfect English course.
So when dungroanin says they are sticking to their prediction of a landslide do they mean a Labour or Tory landslide?
I’m assuming Labour ( also hoping ) but I can’t yet see any evidence to suggest how that can be.
I don’t for one minute think there will be a Tory majority either. My cautious optimistic view is that there will be a hung Parliament and likely a Labour coalition government.
I’ve probably beat this drum before but the print media as we know is owned by off-shored billionaires but the BBC is supposed to be an impartial reporter of facts. We all **must** pay a licence fee if we watch any live transmission but time and again the BBC’s current affairs/news department has shown blatant bias favouring the Tory party.
The reason being two prime ministers back the controlling board was changed such the government of the day appoints the majority of the board. Allied to that, the news department is ‘stuffed’ with editors with previous right-wing news editors.
I can sort of live with the newspaper side of things, the Daily Mail is now so disrespected it no longer counts as a source of reliable information. The BBC however, is held up as a beacon of objectivity when it has in fact been infiltrated by entryists. It has been argued that ‘New Labour’ was a similar example of this takeover.
I have had to look deep into the interweb to find ANY indications of how the Friday debate was polled – remember the first debate of a significant number of polled (30k people) was unanimous for Corbyn – so hasn’t it been a surprise that 48 hours later the big pollsters have not pipped a squeak yet ?
So seat back and grab some popcorn here is what Wales on Line has to report ( i have no underlying data or how many were involved). READY ?
1. Rate the performance of the four leaders
Jeremy Corbyn – you rated him nearly eight out of ten
Nicola Sturgeon – you rated her six out of ten
Boris Johnson – you rated him five out of ten
Jo Swinson – you rated her nearly five out of ten
2. Who won the debate?
The debate was chaired by Fiona Bruce(Image: Jeff Overs/PA Wire)
Jeremy Corbyn topped our poll with 60% of the vote.
Boris Johnson came in with 22%, Nicola Sturgeon with 12% , Jo Swinson with 2% and 6% of you claiming you didn’t know.
3. Has the debate changed your mind about who to vote for?
A small 17% of you said yes , while 76% said no .
Meanwhile, a 7% said they weren’t sure further said they weren’t sure.
4. Who appeared to have the best ideas?
Once again Jeremy Corbyn takes the lead of the vote with 61% .
Boris Johnson came in at 20% , while Nicola Sturgeon had 9% of the vote and Jo Swinson had 4% .
A further 6% said they didn’t know.
5. Who would make the best leader?
Jeremy Corbyn was deemed to be the best leader with 52% of the vote.
Boris Johnson had 25% and Nicola Sturgeon had 15% .
Jo Swinson had only 3% of the vote, while 5% claimed they weren’t sure.
6. Who do you trust the most?
Jeremy Corbyn came out on top with 55% of the vote, with Boris Johnson behind with 18% .
Nicola Sturgeon had 15% , Jo Swinson had 4% and 7% claimed they didn’t know.
7. Whose priorities best match what you think is important?
More good news for Jeremy Corbyn as he came out with 62% of the vote.
Boris Johnson was quite behind with 23% , and Nicola Sturgeon took 8% .
Jo Swinson had 4% , with a further 3% claiming they weren’t sure
https://www.walesonline.co.uk/news/politics/corbyn-johnson-question-time-leaders-17303868.amp ‘
Thanks
I certainly hope that the polls are inaccurate and badly so. However, I should mention that my neighbouring constituency is Grimsby which recently had a startling poll result showing that the Tories were heading for a landslide to unseat the current Labour MP. In this case, I can quite well believe that enough turkeys in Grimsby will vote for Christmas as they are so Brexity that they seriously believe a Tory MP and government is the way to guarantee leaving the EU. I’ve had discussions with few people who sincerely believe that the loss of our fishing industry was the fault of the EU and we’ll somehow suddenly become a wealthy and vibrant fishing port once we’ve left. For others, it has become such an object of faith that they are desperate to leave even though they have no logical explanation as to how it will improve things.
It would be pretty shameful to see a Tory MP in Grimsby, given how they’ve left the town to rot since the 1970s.
It is a staggering idea tha5 this might happen
Grimsby is indication of Tory neglect
I’ve posted my take on the polling methodology elsewhere, but it is relevant here too.
“They polled 385 people who identify as Conservative voters, and 311 who identified as Labour voters. After weighting they retained 71% and 62% of the sample respectively. So they over sampled Tory voters, and then retained a higher sample of those voters after weighting; justified by what? Why after sampling 23.7% more Tory voters, did then keep a higher percentage after weighting than they did for Labour with a much smaller sample?”
And then onto demographic weighting, which is wildly at odds with census data
https://en.wikipedia.org/wiki/Demography_of_the_United_Kingdom#Age_structure
The only opinions these polls measure, is the wealthy businessmen who run them, and those desperate to curry favour with them.
Really good analysis by DunGroanin. FWIW I think that Opinium is as close to pure “fake news” as polling gets. Their polling is done very cheaply (they provide regular polls to the Observer for free because the Observer can’t afford to pay; the Guardian dropped ICM polling after the 2017 election as they were too expensive). They don’t reweight properly for how people say they voted in the 2017 election (as DunGroanin shows). They might as well be just making up the data without spending the money to phone people, for all the good it’s worth. What’s the purpose of Opinium? It’s not to provide robust polling on the outcome of the general election, it’s to provide a fig leaf behind which the Observer journalists – most of whom are rabidly anti-Corbyn – can hide, so that they can say “the Labour campaign is imploding with Labour now 19% behind the Tories”, etc. They are hoping that it will demoralise activists and become a self-fulfilling prophecy. I think the real gap between the parties is probably only a few percentage points and if we were to reallocate don’t knows and undecided voters in line with the split from the debate last Tuesday – where Corbyn was about 40 points ahead of Johnson with undecided voters – Labour might actually be ahead on vote share. My prediction for Dec 12th is a small overall lead for Labour in vote share – maybe 2%? And probably Labour just ahead of the Tories in terms of seats. The latter is very hard to call though as so much depends on the geographical distribution of the vote. I think there will be a lot of seats changing hands in both directions – with Labour losing some to the Tories in the Midlands and North, but Labour also gaining some from the Tories in the East, South and London. Also some high profile Lib Dem gains from the Tories although I think the Lib Dem vote share will be not much more than 10%. SNP to do well in Scotland, although not a complete clean sweep – maybe 50 seats? But it’s going to be an exciting night on the 12th, that’s for sure…
I had a quick look at polling for the 2017 election – https://en.wikipedia.org/wiki/Opinion_polling_for_the_2017_United_Kingdom_general_election
Of the polls that did fieldwork up to the day before the election the largest Conservative lead reported was by BMG – 13% One is left with the conclusion that for some reason polls are of virtually no use in the current political climate!
I also remember some of the regional polls that were done before the 2017 election, especially Wales where it was trumpeted that Labour were going to lose big. It didn’t happen.
I wonder if there could be “shy Labour” voters that don’t reveal themselves to pollsters because of the mainstream media narrative that Corbyn/Labour are crazy Marxists?
It may be that the Conservatives do win a big majority, but the uncertainty is at least prolonging the period when I can try and keep optimistic!
Richard
I don’t see how Labour can lose.
Bang the drum of free prescriptions….free tv licenses….free tuition plus maintenance grants…payments of thousands of pounds to female pensioners…(sure I have left something out) all to be paid for by someone else.
Forget politics just a one pager on the freebies and Labour can’t lose.
Even if the Observer poll is wrong, all other poll data has given consistently large leads to the Tories and a Tory win seems inevitable. To suggest otherwise is to refute the mathematical basis of the sampling methodology. You can certainly have rogue polls, but to have 50 or more pointing in the same direction with large leads and try to refute the likely outcome is to engage in denialism. I am upset that the Tories are going to win but that is what is very likely going to happen. I suspect this all comes down to Corbyn’s Brexit ambivalence, and now stated neutrality, because many working-class voters are flipping for the first time in their lives.
This happened in 2017 too…
For completeness sake i’ll post this link here having put a fuller post on RM’s next post on the issue.
https://blogs.lse.ac.uk/brexit/2019/10/29/long-read-are-opinion-polls-pro-leave-biased/
Further as the terrible news filters through the brexiteers and they try and divert attention to Foreign issues (Uighars, today), Peter Kellner (polling expert?!!) tries to wish away the latest numbers coming from a pollster – desperate to avoid their reputation being trashed – on LBC.
I will say that if IDS doesn’t prove to be one of many ‘Portillo’ moments on Friday the 13th – i’ll eat my hat!
Duncan i think your point is interesting that labour will get a landslide, but based on one poll being out by a big margin. Surel that is not scientific!
I know polls can be wrong and i mean a lot of them. I read an article if polls start to say the same thing, it does not mean they are right it just means they are amplifying their wrong methodology. It is so bad – all the polls are doing what is termed “herding”. So could the polls being herding in this manner or could it be that theyare right in their own context?