It's Only A Poll, But Apparently The British Public Backs May

[Canary42]

40% of British people think that Mrs May should stay, compared to 34% who want her to go.

There are some interesting subsidiary stats in this article.

https://uk.news.yahoo.com/british-public-backs-theresa-may-stay-prime-minister-no-confidence-vote-looms-174022469.html

[vetuste_ennemi]

I can't see any details about this poll, like who conducted it, the questions asked, sample size and so on.

[Old_Geezer]

26% said, "Mrs. Who ?"

[Canary42]

v_e: I think it was Youguv but as regards size and representativeness I know not - which is why I put "... only a poll..."

[vetuste_ennemi]

Thanks, Canary.

[Peter Pedant]

on the you gov sige it looks like 4000

( so the figures and likely to be accurate to around =/- 2%)

[THECORBYLOON]

There were 3093 adults asked in Great Britain, they weren't interested in the views of folk in Ulster for some reason.

[vetuste_ennemi]

Does anybody know the questions?

PS: the margin of error in any poll is related to sample size, but most certainly not determined by it.

[THECORBYLOON]

https://yougov.co.uk/topics/politics/articles-reports/2018/12/12/may-should-stay-say-plurality-britons

[vetuste_ennemi]

Excellent. Thanks, CorbyLoon.

[cassa333]

Stay or go no one else can change this deal.

What someone else might have done, with the requisite guts and balls, was leave this atrocious deal in the gutter where it belongs and say proper deal or no deal.

However we have a remainer government who don’t want to leave so even a leader with the wherewithal couldn’t get that through.

Hopefully, lessons will have been learnt.... and she changes tac...

[Canary42]

Poll sample sizes here. Very small.

https://d25d2506sfb94s.cloudfront.net/cumulus_uploads/document/kz4dwrpsoe/NoConfidenceVote_Brexit_181212.pdf

[vetuste_ennemi]

Yes, that was in the Corby link, Canary.

Interestingly the 50+ age group was over-sampled.

[THECORBYLOON]

"Q. Why does sample size matter?

A. Because the risk of random sampling error is related to sample size: the smaller the sample, the greater the risk of such error. On a sample of 550, we can be sure that, 19 times out of 20, the true figure – that is, the figure that would have been obtained had the whole population been polled using the same methods – is within 4% of the published figure. Random error on a sample of 1,000 is up to 3%, on 1,500 up to 2.5% and on 2,000 up to 2%. Larger samples also allow the views of subgroups, such as women voters or Conservative supporters, to be measured more accurately."

 

[bednobs]

I'm a subgroup??? How very dare they :)

[vetuste_ennemi]

Size does[i matter.

But it is not the [i]only] determinant of a satisfactory outcome pollwise.