Question on Statistics and Polls

[albion]

See ons data.
Also has data on vaping. Not sure ex smokers are switching to vapes, more those who have never smoked taking up vaping.
Why do you assume it’s easier to do surveys? Cheaper probably yes, not necessarily easier

More now maybe. But certainly a majority of smokers I know moved to Vapes. The pub smoking ban played a major part.

 

[presta]

Clearly many aren't done in a statistically rigorous manner, as the bulk called the last two general elections wrong

If you tell me that I'm more likely to get run over if I cross the road without looking, and I then shut my eyes, cross the road, and survive, have I proved you wrong? If I tell you that the probability of heads or tails is 50/50, and you get 6H/4T am I wrong?

 

[Electric_Andy]

12% sounds high

It sounds about right to me but it depends where you look. If for example you look around a deprived suburb, it might look like 40% of people smoke. Whereas in leafy middle England you might not see any smokers all day

 

[ebikeerwidnes]

The problem witha lot of surveys and polls is that they are biased towards people who are willing to bother answering the poll questions

obviously

which is why people do surveys that show that everyone thinks xxxxx - when you are pretty certain that a load of people don;t think that - it is just that most people saw the poll coming and swerved it
like Party workers on a High Street coming up to an election

My wife used to do surveys and stuff for a local hospital and could bore you for hours on the ways and means of doing it properly and the mistakes she has seen
Actually I find it really interesting
but she gets annoyed with me because I see it from a different viewpoint to her

 

[ebikeerwidnes]

On another point
WHen I was training to be a teacher we had to do a "dissertation" at the end which had to include "Primary Research" - which was interpreted as having to be a survey.
We were just trainee teacher - so although we had a degree it did not necessarily have any stats included in it so most of use had no knowledge or experience of getting data in this way.
One person had a degree in IT and PE (I know - I don;t understand either!) and as part of it ha had done an extra course on statistics and surveys

He knew the stuff about psycology and how people react to surveys and how to ......
etc etc - it was far more complicated that you would think

Our "training" was a 5 minute talk about how to do it

And this was from a proper university who should have known better


There are a lot of carp surveys out there - and a lot of people using surveys to "prove" their point by knowing how to distort the results - e.g. by biasing only certain people to respond

 

[vickster]

More now maybe. But certainly a majority of smokers I know moved to Vapes. The pub smoking ban played a major part.

Smoking ban was over 15 years ago. They’re all still vaping?

 

[albion]

Smoking ban was over 15 years ago. They’re all still vaping?

A mix of stopped and vaping.

 

[MontyVeda]

Man, this brings me back to dim and distant memories of A-Level Sociology

Oh blimey that reminds me... I probably filled in around 80% of the questionnaires for my project survey

 

[presta]

a lot of people using surveys to "prove" their point by knowing how to distort the results

There was the Brexiter's survey about returning to imperial units in which keeping metric wasn't one of the options on the list.