Army Rumour Service

Register a free account today to join our community
Once signed in, you'll be able to participate on this site, connect with other members through your own private inbox and will receive smaller adverts!

Latest snowflake outrage

The BBC News is almost on a continuous loop reporting this. I’ve lost count of the number of times they’ve shown ‘highlights’ of speeches from Sir Vince Cable and Caroline Lucas. If that’s the best they can do, I’m still happy with my decision.
They accuse those on the Brexit side of lying and yet their* latest wheeze is to suggest a majority (53%) of the country now wants to stay in the EU! HTF do they know that? Has there been another referendum and I missed it?

*Eloise Todd, CEO of Best for Britain states “what we absolutely need is a people’s vote”. Sorry, what was that a couple of years back then. :?
Has anyone bothered to work out, I dare to say the back of a fag packet, what the political, social, moral and constitutional fall out will be if Brexit is derailed and destroyed? Can anyone think out what the political fallout will be?
 
. . . which, like the vast majority of polls, tells us one thing and one thing only: the intentions or perceptions of those polled.

To extrapolate a National view from such a miniscule data set is risible.

No sorry it's not.

It depends on two things:

1. Accepting there's a margin of error

2. Being REALLY good at getting a truly random sample.

If you're happy to accept 95% confidence level, for example, your sample size (for a population over about 100,00 (IIRC)) need only be 385.
 
Has anyone bothered to work out, I dare to say the back of a fag packet, what the political, social, moral and constitutional fall out will be if Brexit is derailed and destroyed? Can anyone think out what the political fallout will be?

Painful for those who made it happen.

Very painful.
 
No sorry it's not.

It depends on two things:

1. Accepting there's a margin of error

2. Being REALLY good at getting a truly random sample.

If you're happy to accept 95% confidence level, for example, your sample size (for a population over about 100,00 (IIRC)) need only be 385.

So if it's 385 from a population of 100,000 that extrapolates to a tad over 250,000 for the current (admitted to) population.

Ain't no bugger going to spend the time & effort polling that many, so it's back to being a guesstimate.
 
Their best of late is the BBC insinuating that the Windrush generation was 'those that built Britain' This was mentioned a few times on phone-ins and the program commentator; I almost started to think that it was the Windrush folk that had stormed the Normandy beaches, and not Brits and our allies.

It's been covered on the radio a lot but it was more about them being invited to help rebuild Britain and how many of the early Windrush generation migrants from the Caribbean were returning to Britain having volunteered to serve during the war in spite of having a one in five chance of being torpedoed en route. They may not have stormed the beaches at Normandy but many of them kept Bomber Command in the air and the convoys sailing.
 
So if it's 385 from a population of 100,000 that extrapolates to a tad over 250,000 for the current (admitted to) population.

Ain't no bugger going to spend the time & effort polling that many, so it's back to being a guesstimate.
Not quite, the figure was for a population over 100,000. The sample bobmentioned would give you 95% accuracy.
 
No sorry it's not.

It depends on two things:

1. Accepting there's a margin of error

2. Being REALLY good at getting a truly random sample.

If you're happy to accept 95% confidence level, for example, your sample size (for a population over about 100,00 (IIRC)) need only be 385.

Sorry, Bob, but to my cynical eyes those two observations support my view. A sampling size of slightly over 1000 people from a population of ca 70m cannot be viewed with any accuracy.
 
. . . which, like the vast majority of polls, tells us one thing and one thing only: the intentions or perceptions of those polled.

To extrapolate a National view from such a miniscule data set is risible.

Indeed it is. A similar situation with a Fox hunting poll in 2014. Mori polled adults in great Britain: "should the hunting ban be made legal again?"
No - it should not be made legal again = 80%
Yes - it should be made legal again = 17%
Don’t know = 3%

The anti's took this figure and ran with it, trumpeting as the view of the entire UK population.And citing the figure a conclusive proof of their point of view.
The poll was from a sample of 1,971 people.
 
No sorry it's not.

It depends on two things:

1. Accepting there's a margin of error

2. Being REALLY good at getting a truly random sample.

If you're happy to accept 95% confidence level, for example, your sample size (for a population over about 100,00 (IIRC)) need only be 385.

I know not who said it but I do remember:
there are lies,
there are damned lies,
and then there are statistics.
 
there are lies,
there are damned lies,
and then there are statistics.

The term was popularised in United States by Mark Twain (among others), who attributed it to the British Prime Minister Benjamin Disraeli: "There are three kinds of lies: lies, damned lies, and statistics." However, the phrase is not found in any of Disraeli's works and the earliest known appearances were years after his death. Several other people have been listed as originators of the quote, and it is often erroneously attributed to Twain himself.[1]
Wikipedia.
 
No sorry it's not.

It depends on two things:

1. Accepting there's a margin of error

2. Being REALLY good at getting a truly random sample.

If you're happy to accept 95% confidence level, for example, your sample size (for a population over about 100,00 (IIRC)) need only be 385.

Have you got a source for that? I am interested in how the statistics work - is there a nice formula for sample size and confidence level? My understanding of Statistics is a bit sketchy.

It's been covered on the radio a lot but it was more about them being invited to help rebuild Britain and how many of the early Windrush generation migrants from the Caribbean were returning to Britain having volunteered to serve during the war in spite of having a one in five chance of being torpedoed en route. They may not have stormed the beaches at Normandy but many of them kept Bomber Command in the air and the convoys sailing.

We had Caribbean troops in both World Wars.
 
The term was popularised in United States by Mark Twain (among others), who attributed it to the British Prime Minister Benjamin Disraeli: "There are three kinds of lies: lies, damned lies, and statistics." However, the phrase is not found in any of Disraeli's works and the earliest known appearances were years after his death. Several other people have been listed as originators of the quote, and it is often erroneously attributed to Twain himself.[1]
Wikipedia.
Does that count as a lie, a damned lie or a statistic?
 
Have you got a source for that? I am interested in how the statistics work - is there a nice formula for sample size and confidence level? My understanding of Statistics is a bit sketchy.

The YouGov site tries to explain it.
In the small print of opinion polls you'll often find a ‘margin of error’ quoted, normally of plus or minus 3%. This means that 19 times out of 20, the figures in the opinion poll will be within 3% of the ‘true’ answer you'd get if you interviewed the entire population.
YouGov | Understanding margin of error
 

New posts

Top