EU demands more money

[Bean]

See if you can work out how you have muddled things up around statistical significance and causation.

I don't believe I have. In fact, its worse.


Low sample size (of 11205), relating to a target group of 34000000 referendum voters, actually means the sample was 0.03% representative.


I said this was therefore a statistically insignificant study and therefore YOU shouldn't ascribe causation from any correlation the study has shown.
(and the fact it's not even formalised yet)


Now - what did I do wrong?
(and you must show your working, rather than saying 'let's see if you can see XYZ')

[Bean]

I come from a working class area in the midlands. On facebook I am still connected to a lot of people from that area. Almost to a man (and woman) they were sharing these and many more headlines during the whole of the campaign. I would consider them pretty representative of the blue collar, working class, none SE in our society. They were all influenced by these headlines and to a man (and woman) voted out.

FWIW I was so disgusted by a lot of what I saw on read on their FB pages that after 40+ years of knowing these people I had to defriend them. Not because they voted out, but the racist and xenophobic posts.

So yes I do have evidence and yes I do believe these headlines influenced voting.

Next.......

By all means, I would unfriend racist 'friends' on facebook too - but I didn't see anything like that.


Ok, let's see how we can show you that what you experienced was anecdotal evidence:

How many facebook friends do you have? - This will be 'A'
From this number, how many were leavers? - This will be 'B'
From this number, how many posted those headlines? - This will be 'C'

Now do the following calcs and tell us the % outcomes for 'D', 'E' & 'F':

(A / 17000000) * 100 = 'D'
(B / 17000000) * 100 = 'E'
(C / 17000000) * 100 = 'F'

[WTFH]

no we just can't believe you all fell for Project Fear.

Us Brexiters are wondering when everyone is going home because there aren't any jobs. Or when we need to take our wheelbarrow down the bakers due to inflation.

Its all just you wait, you will be sorry when your dad gets home/ you finally leave/ when the sky falls in.....

https://www.farminguk.com/News/Cornw...ds-_47882.html

[BlasterBates]

https://www.farminguk.com/News/Cornw...ds-_47882.html

Should be plenty of Labour available after they move the 4 trillion Euro Derivatives clearing market to the EU.

A bit of fresh air will do these pasty faced financial services workers a lot of good.

[Bean]

See if you can work out how you have muddled things up around statistical significance and causation.

Ah I see what you were angling towards, pedanticism. (around how 'most people' would use causation vs a statistician)

Yes, you are technically correct (but the point is moot by the end of this post) with regards to causation and StatSig, but I doubt, for example, many people would like a wording change to 'smoking causes cancer' on cigarette packets...due to this same technicality....
"Many other reasons were suggested for the link between lung cancer and smoking, including sleep deprivation or alcoholism. In layman’s terms, it’s now known that smoking causes lung cancer. But in scientific (or statistical) terms, you can’t really say “cause” as that would mean every single person who smoked even just one cigarette would get lung cancer. As statisticians, we say that there is a very strong correlation between smoking and lung cancer."


However, plug in the study figures to the link below and you will arrive at a confidence interval of 4.6-5.4% - NOT really statistically significant is it.....so not even a correlation has been found
https://select-statistics.co.uk/calc...on-proportion/


But you don't really need to use the calculator to work that out, when the sample (11205) is so low (0.03%) compared to the target group (34000000)


So to sum up;
1. Low sample size compared to population size
2. Low confidence interval
3. No correlation can be derived due to 1 & 2
4. Extremely unlikely (but not impossible) to be causation without any correlation
5. Study is yet to be formally presented (and therefore not yet peer-reviewed)


But thanks for linking it anyway, made me chuckle with all those 'remainer' symptoms