Jump to content

Polling: 2017 General Election, Council Elections and Independence


Recommended Posts

2 minutes ago, Baxter Parp said:

As a result of the end of the Brexit transition period on 31 December 2020, British people have lost their rights as EU citizens.  Do you think it should be a priority for the Scottish Government to regain these rights for the people of Scotland, such as being able to live and work in any EU country?  (Scot Goes Pop / Survation poll, 11th-13th January 2021):

Yes 52%
No 30%

At the end of the Brexit transition period on 31 December, the UK Government chose to withdraw from the Erasmus programme, which has given university students the opportunity to study in other European countries.  Do you think it should be a priority for the Scottish Government to regain access to the Erasmus programme for Scottish students?

Yes 52%
No 29%

https://scotgoespop.blogspot.com/

How do they weigh that with dont knows removed?

Link to comment
Share on other sites

4 minutes ago, Erih Shtrep said:

surely you can do that by yourself? 

No because I dont know what weighting is being used, i was shite at using SPSS and the likes at uni. I get the arithmetic of working it out from the 52% of 82% of the votes being yes, but wasnt sure if there was any form of weighting based on trends and the background dynamics of the don’t knows ie gender/age etc etc.  

Edited by Inanimate Carbon Rod
Link to comment
Share on other sites

29 minutes ago, GordonS said:

FWIW rolling averages have exactly the same margin of error as the individual polls within them. You can't add the polls together because they're taken at different times and using different methodologies, and even if you could you'd only reduce the margin of error to about 2.5% points by increasing the sample size to 5,000.

The benefit of rolling averages is that they knock the edges off outliers. But if pollsters are systematically off, as is normally the case, then averages just confirm the gap.

I'm all for making this a stats chat.

Are you sure about that 2.5%? I did a quick calculation and got 1.4%, which tallies with some other sources.

I do get that it's not quite a nice as saying well 1k is now 5k and so we drop from 3 to 1.4. However, it's definitely not the case that margins of error just don't reduce. For example, polls that were taken years apart would have a much higher margin of error than polls taken on consecutive days. I certainly don't know what the formula to work that out would be there must be some kind of error calculation inverse to how long ago the poll was taken.

For example, polls are reported as being taken over a number of days. We don't say that the MoE for a 1000 person poll is the same as for a 1 person poll because the 1000 responders didn't answer simultaneously.

Edited by Gordon EF
Link to comment
Share on other sites

4 minutes ago, Inanimate Carbon Rod said:

No because I dont know what weighting is being used, i was shite at using SPSS and the likes at uni. I get the arithmetic of working it out from the 52% of 82% of the votes being yes, but wasnt sure if there was any form of weighting based on trends and the background dynamics of the don’t knows ie gender/age etc etc.  

weighting begins earlier in the process.   The 52% will be a weighted adjustment using social class, previous vote etc.  

Link to comment
Share on other sites

37 minutes ago, Inanimate Carbon Rod said:

Oh absolutely no one came out of that covered in glory, the person i feel sorry for is the child who was targetted, thats the only person. 

I respectfully disagree, a 16 year old is considered a child in Scotland, Mackay(?) knew this because he voted for the legislation that framed it that way in the Children and Young People act 2014. Ferrier was a grade A fuckwit also, I suppose on reflection its a difficult one to say which is worse, Im biased because of my experiences with victims of grooming. 

The Children and Young People (Scotland) Act 2014 makes no reference to sexual offences, or indeed any offences against children and young people.

Depending on the purpose, a 16 year old is both an adult and a child in Scotland. They can have sex, get married and form contracts. FWIW we're the only country in Europe to have 16 as the age of majority. 

As I'm guessing you know, it's only an offence for a person over 17 to engage in sexual activity with a person under the age of 18 if they are in a position of trust. That's defined reasonably narrowly in s.43 of the Sexual Offences (Scotland) Act 2009 and it wouldn't have covered Mackay. In any case, there was no sexual activity.

Grooming is covered in the Protection of Children and Prevention of Sexual Offences (Scotland) Act 2005, which you probably know too. It only applies to under 16s, except for indecent images which apply to under 18s.

In any case, I don't think the messages that Mackay sent crossed the lines for those offences, and presumably the police didn't either. 

I totally respect your moral judgement of Mackay of course, and if you think it's worse than Ferrier's behaviour that's every bit as good an opinion as mine.

Link to comment
Share on other sites

4 minutes ago, GordonS said:

The Children and Young People (Scotland) Act 2014 makes no reference to sexual offences, or indeed any offences against children and young people.

Depending on the purpose, a 16 year old is both an adult and a child in Scotland. They can have sex, get married and form contracts. FWIW we're the only country in Europe to have 16 as the age of majority. 

As I'm guessing you know, it's only an offence for a person over 17 to engage in sexual activity with a person under the age of 18 if they are in a position of trust. That's defined reasonably narrowly in s.43 of the Sexual Offences (Scotland) Act 2009 and it wouldn't have covered Mackay. In any case, there was no sexual activity.

Grooming is covered in the Protection of Children and Prevention of Sexual Offences (Scotland) Act 2005, which you probably know too. It only applies to under 16s, except for indecent images which apply to under 18s.

In any case, I don't think the messages that Mackay sent crossed the lines for those offences, and presumably the police didn't either. 

I totally respect your moral judgement of Mackay of course, and if you think it's worse than Ferrier's behaviour that's every bit as good an opinion as mine.

Appreciate the polite discourse! 
Yes I know it didnt cross the boundaries of criminality because the threshold is of that of the age of consent, I suppose again thats a debate for another place! 

Link to comment
Share on other sites

39 minutes ago, Gordon EF said:

I'm all for making this a stats chat.

Are you sure about that 2.5%? I did a quick calculation and got 1.4%, which tallies with some other sources.

I do get that it's not quite a nice as saying well 1k is now 5k and so we drop from 3 to 1.4. However, it's definitely not the case that margins of error just don't reduce. For example, polls that were taken years apart would have a much higher margin of error than polls taken on consecutive days. I certainly don't know what the formula to work that out would be there must be some kind of error calculation inverse to how long ago the poll was taken.

For example, polls are reported as being taken over a number of days. We don't say that the MoE for a 1000 person poll is the same as for a 1 person poll because the 1000 responders didn't answer simultaneously.

Well, this thread is supposed to be about polls!

I was guessing about 2.5% because I'm sure I saw a big poll sample of about 6,000 pull an error margin down to 2.3%. But I checked too and obviously you're right, it's 1.4%.

Scottish opinion polls are usually weeks apart. A 5 poll average just now would take you back to 11 November last year, with only one since 15 December. It would also cover four different companies. You can't just add those together for a super poll.

Link to comment
Share on other sites

6 minutes ago, GordonS said:

Well, this thread is supposed to be about polls!

I was guessing about 2.5% because I'm sure I saw a big poll sample of about 6,000 pull an error margin down to 2.3%. But I checked too and obviously you're right, it's 1.4%.

Scottish opinion polls are usually weeks apart. A 5 poll average just now would take you back to 11 November last year, with only one since 15 December. It would also cover four different companies. You can't just add those together for a super poll.

Yeah, I'm not saying you could add them up into one super poll but the margin of error would still be less than with one individual poll one fifth of the size. Also, I'd imagine that diversity in the wording would actually increase the confidence in the result. One poll with misleading wording could throw up an anomaly. 5 different wordings / methodologies giving similar results would essentially be a form of corroboration.

Also, you've got the slight complication that looking at a trend of 5-rolling average polls actually isn't just 5 polls contributing. If we looked at the previous 10 5-rolling average polls, there's actually 14 polls contributing to that so you'd have to weight their margins of error.

I'm sure there's some standard way of of doing it but I suspect trying to figure out if that trend is significant is fiendishly difficult.

Edited by Gordon EF
Link to comment
Share on other sites

3 minutes ago, Inanimate Carbon Rod said:

Appreciate the polite discourse! 
Yes I know it didnt cross the boundaries of criminality because the threshold is of that of the age of consent, I suppose again thats a debate for another place! 

There are a lot of things that aren't illegal that are thoroughly repugnant. And thankfully we'll never know how far Mackay might have taken it.

On a tangent, I've often wondered why very religious people get so angry about abortion, on which the Bible is ambiguous and the Gospels silent, but they never want to criminalise adultery which is against the Ten Commandments 🤔

Link to comment
Share on other sites

7 minutes ago, GordonS said:

There are a lot of things that aren't illegal that are thoroughly repugnant. And thankfully we'll never know how far Mackay might have taken it.

On a tangent, I've often wondered why very religious people get so angry about abortion, on which the Bible is ambiguous and the Gospels silent, but they never want to criminalise adultery which is against the Ten Commandments 🤔

Agreed on all counts.

Link to comment
Share on other sites

The Children and Young People (Scotland) Act 2014 makes no reference to sexual offences, or indeed any offences against children and young people.
Depending on the purpose, a 16 year old is both an adult and a child in Scotland. They can have sex, get married and form contracts. FWIW we're the only country in Europe to have 16 as the age of majority. 
As I'm guessing you know, it's only an offence for a person over 17 to engage in sexual activity with a person under the age of 18 if they are in a position of trust. That's defined reasonably narrowly in s.43 of the Sexual Offences (Scotland) Act 2009 and it wouldn't have covered Mackay. In any case, there was no sexual activity.
Grooming is covered in the Protection of Children and Prevention of Sexual Offences (Scotland) Act 2005, which you probably know too. It only applies to under 16s, except for indecent images which apply to under 18s.
In any case, I don't think the messages that Mackay sent crossed the lines for those offences, and presumably the police didn't either. 
I totally respect your moral judgement of Mackay of course, and if you think it's worse than Ferrier's behaviour that's every bit as good an opinion as mine.
In a way no different from Salmond.

Nothing illegal but the behaviour was completely inappropriate.
Link to comment
Share on other sites

4 hours ago, DeeTillEhDeh said:

In a way no different from Salmond.

Nothing illegal but the behaviour was completely inappropriate.

Assuming you agree with the jury and don't believe the prosecution witnesses, of course. There are differences of opinion on that but with Mackay the facts aren't disputed.

Link to comment
Share on other sites

Assuming you agree with the jury and don't believe the prosecution witnesses, of course. There are differences of opinion on that but with Mackay the facts aren't disputed.
Even if it's the other way it does not matter - Salmond was found not guilty on all charges bar one which was not proven. He faced the charges and was cleared.

It does not mean that his behaviour was acceptable.

If I think he's a creepy old lech who was lucky is irrelevant
Link to comment
Share on other sites

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

Loading...
  • Recently Browsing   0 members

    • No registered users viewing this page.
×
×
  • Create New...