Tory lead down to 2 points, or is it.

Spartacus_Mills

The latest Yougov poll in the NOTW now shows a Tory lead of 2 points. Tories 37% and Labour 35% Lib Dems static on 17%.

However before these are taken at face value the raw stats are interesting.

http://www.timesonline.co.uk/multimedia/archive/00690/YouGov_survey_resul_690818a.pdf

In effect the Tories are weighted down by circa 10% and Labour up by 10%. The raw data shows the Tories on 41/2% and Labour 30/31%. So on raw data a lead in double digits. This is down on the 15% leads on raw data we saw a year ago from them.

The swings in some regions show massive movements either way.

I have copied this from a poster on pb.com

London: In Friday’s poll, 47% Con, 29% Lab - Con lead 18%
In today’s poll, 29% Con, 39% Lab - Lab Lead 10%

Con-Lab swing of 14%)

On the other hand:
Midlands: In Friday’s poll, 39% Con, 40% Lab - Lab lead 1%
In today’s poll, 43% Con, 32% Lab - Con Lead 11%

As the poster says this seems totally implausible.

I am taking Yougov with a pinch of salt (although this undoubtedly does show a narrowing based on their latest polling methods) until Peter Kellner has answered a Q&A session on pb.com explaining the methodology and the changes they have made to their methodology over the last 15 months (although I have had a punt on Labour to get the most seats in the next parliament at 6/1)

Using they previous methodology Yougov were very accurate in the European elections so it would be interesting to see why they changed their weightings and methodology.

Rochdale_Pioneers

Yes the Tory lead drops from 17 to 2. Must be bias in the pollster's methods.

peterg1965

I cannot believe that polling is a scientific art......

Select or ask 2000 people the same question - ' how will you vote in the election?', then, collate answers, come up with Poll!

Suspect that is 'politics' at play even in the murky world of polling!

Spartacus_Mills

Rochdale_Pioneers wrote: »

Yes the Tory lead drops from 17 to 2. Must be bias in the pollster's methods.

Good old unthinking Labour stooge. Deny something that has not been claimed.

Read this.

http://www2.politicalbetting.com/index.php/archives/2010/02/26/guest-slot-from-flockers-on-yougov/

The raw data has changed very little but the weighting methodology has changed. It is not unreasonable to question why that has happened and the basis behind it. On Tuesday we have the details from Peter Kellner. I am taking it with a pinch of salt until then.

Only a complete imbecile would think that this means people are claiming Yougov are biased.


To quote from the article.

When did YouGov’s weightings start causing the weighted result to diverge so dramatically from the unweighted result? Quite recently:

In 16 reported polls for which the fieldwork was completed in July, August or September the average unweighted Conservative lead was 14.4 points against an average reported lead of 12.8 points, indicating an average weighting of 1.6 points away from the Conservatives, far below the 2010 average weighting of 6.4 points.

The weighting moved in the Conservatives’ favour in four polls, against them in twelve. During October, November and early December, 15 polls gave the Conservatives an average unweighted lead of 15.5 points, against an average reported lead of 12.6 points, indicating an average weighting of 2.9 points away from the Conservatives.

In the twelve subsequent polls the average weighting against the Conservatives has been 6.3 points.

Every single poll in 2010 has seen the Tory share weighted downwards and the Labour share weighted upwards, with a net effect on each poll of between three and nine points. Ten of the eleven polls this year have seen weighting impact the Tory share by more than four points. Only five of the previous 39 polls was adjusted by the same amount.

Spartacus_Mills

peterg1965 wrote: »

I cannot believe that polling is a scientific art......

Select or ask 2000 people the same question - ' how will you vote in the election?', then, collate answers, come up with Poll!

Suspect that is 'politics' at play even in the murky world of polling!

I doubt that. Pollsters rely on commissions from the press, media and other outlets. If the polls are wildly out it could affect their business after the election.

It is more a case of understanding why the Yougov weighting against the Tory vote has moved in the last 12 months and what the reason for it is.

baileysbattlebus

peterg1965 wrote: »

I cannot believe that polling is a scientific art......

Select or ask 2000 people the same question - ' how will you vote in the election?', then, collate answers, come up with Poll!

Suspect that is 'politics' at play even in the murky world of polling!

Not quite that simple is it though?

One of the Conservatives biggest problem is this:

From what you have read and heard, do you feel that you know what the
Labour Party stands for on important issues, or not?
Yes, I do 47
No, I do not 53

From what you have read and heard, do you feel that you know what the

Conservative Party stands for on important issues, or not?

Yes, I do 38

No, I do not 62

They have changed their minds quite a bit lately. Maybe the forum this weekend might make a difference. If they were consistent and I knew what they had in mind it wouldn't be so bad, but they aren't and I don't.

If you look at the detail in the poll, the bullying issue seems to have made little difference.

Dr.Shoe_2

I bet they conducted the poll among delegates at a Labour Party conference...

Generali

Rochdale_Pioneers wrote: »

Yes the Tory lead drops from 17 to 2. Must be bias in the pollster's methods.

The way the data is treated has changed dramatically. The policies of the main parties, the leaders of the main parties and the prospective MPs standing for the main parties have remained broadly the same.

What do you think has caused the huge swing in this poll when other polls haven't shadowed it and haven't had the same big methodological change?

These methodological changes were introduced after the 1992 election when it seemed people were ashamed to admit they were planning to vote Tory. Given the state of the UK's economy, the general hatred of MPs and the near daily denigration of Gordon Brown in the British newspapers I would expect that the relative embarrassment amongst Brits to admit supporting Tory would have fallen substantially.

greytroot

Lies Lies Lies, never even met anyone who has taken part in one of these so called polls. Its really unbelieveable that so called professionals can say anything when they quote so called polls.

Think I will make one up - eh - 58% of people will buy items when they need them. Ding Dong!

baileysbattlebus

greytroot wrote: »

Lies Lies Lies, never even met anyone who has taken part in one of these so called polls. Its really unbelieveable that so called professionals can say anything when they quote so called polls.

Think I will make one up - eh - 58% of people will buy items when they need them. Ding Dong!

I've taken part in loads of UGov polls - anyone can - just register - you get paid a little bit as well.

If I remember they don't ask you anything about your political beliefs - they just email an invite to participate in a poll - you can take part if you want to - it's up to you.

drc

I can understand people not wanting to support Tory because they are not very clear about what they now stand for. However, I cannot understand how this could lead anyone to vote for Labour instead, surely one of the worst governments we have ever had. I suspect that the Lib Dem and marginal parties like UKIP are picking up a lot of Lab/Con votes rather than Tory votes moving to Labour.