Boards.ie uses cookies. By continuing to browse this site you are agreeing to our use of cookies. Click here to find out more x
Post Reply  
 
 
Thread Tools Search this Thread
15-09-2018, 16:25   #1501
FrancieBrady
Registered User
 
Join Date: Aug 2010
Posts: 25,731
Quote:
Originally Posted by jmcc View Post
Traditionally, younger voters don't vote as reliably as older voters. So while there may be some support there, it may not translate into votes. And SF is very strong in younger demographics.

Regards...jmcc
Depends what you call young. I would be talking about up to 35.

Too early to be speculating on this. When we see the first volleys of the campaign fired and the first opinion poll we will know better.
FrancieBrady is offline  
Advertisement
15-09-2018, 16:29   #1502
jmcc
Hackwatch
 
jmcc's Avatar
 
Join Date: May 1999
Posts: 4,056
Quote:
Originally Posted by A Tyrant Named Miltiades! View Post
You're perhaps overlooking the age profile of the electorate, and fact that there are a hell of a lot 20-somethings in this country than there are 70-somethings and 80-somethings combined.
Younger demographics are those below 30.

Quote:
It was precisely this kind of demographic which caused so many people to be surprised by the outcome of the 8th Amendment referendum -- I don't suppose you had a detailed prediction about that? You haven't said...
Wasn't at all surprised due to the fact that some of the pollsters made a complete mess of things by relying on telephone polling when there were supposed to have been at least 100K new voters added in the run-up to the vote. The telephone polling methodology was seriously flawed because of the low probability of these new voters having a fixed telephone line rather than a mobile phone. This meant that the mobile phone half of the survey was not properly representative and that undue emphasis was placed on the fixed line part of the survey.

Regards...jmcc

Last edited by jmcc; 15-09-2018 at 16:36.
jmcc is offline  
15-09-2018, 16:30   #1503
jmcc
Hackwatch
 
jmcc's Avatar
 
Join Date: May 1999
Posts: 4,056
Quote:
Originally Posted by FrancieBrady View Post
Too early to be speculating on this. When we see the first volleys of the campaign fired and the first opinion poll we will know better.
Yep. The polling methodology will be important (telephone polling versus face to face questioning).

Regards...jmcc
jmcc is offline  
15-09-2018, 16:40   #1504
A Tyrant Named Miltiades!
Alexa, Play Liveline
 
A Tyrant Named Miltiades!'s Avatar
 
Join Date: Feb 2015
Posts: 11,116
Mod: Radio, ZTest
Quote:
Originally Posted by jmcc View Post
Wasn't at all surprised due to the fact that some of the pollsters made a complete mess of things by relying on telephone polling when there were supposed to have been at least 100K new voters added in the run-up to the vote. The telephone polling methodology was seriously flawed because of the low probability of these new voters having a fixed telephone line rather than a mobile phone. This meant that the mobile phone half of the survey was not properly representative and that undue emphasis was placed on the fixed line part of the survey.

Regards...jmcc
I find it difficult to believe that pollsters haven't thought of this, given that this phenomenon has been in play for well over a decade.

It isn't as though pollsters just disregard age when they're conducting polls, they're supposed to capture a sample that represents recent electoral demographics (or, failing that, the age pyramid of the general adult population).

They don't just gather random samples, not if they have the most elementary notion of how to do their job.
A Tyrant Named Miltiades! is offline  
15-09-2018, 17:08   #1505
jmcc
Hackwatch
 
jmcc's Avatar
 
Join Date: May 1999
Posts: 4,056
Quote:
Originally Posted by A Tyrant Named Miltiades! View Post
I find it difficult to believe that pollsters haven't thought of this, given that this phenomenon has been in play for well over a decade.
Opinion polling is closer to Astrology than Statistics.

The telephone polling is largely a US import but the problem is that the Irish phone system is not laid out along US geographical zones where the area code is more accurate. The mobile phones don't have any geographical indicators. The phone numbers are supposed to be randomly generated but there are some anecdotal reports of people who had cooperated in one poll being repolled again.

The response rate (those who when concated are not willing to be polled) is also important but it rarely seems to be published. This means that rather than it being the poll of 1,000 people, it may actually be a poll of more than 1,000.

The pollsters also apply their own "secret sauce" adjustments to some of these polls to derive other indications. The problem is that it can lead to complete bolloxology like the "Burton Bounce" which had to remove SF voters along with other voters from the poll to get the "bounce".

There's also a cyclical effect in the main Irish polls in that each poll seems to favour specific party. Thus a party might do well in one poll but will not do well in the other polls that month. It is visible in the poll of poll type graphs. This kind of cyclical effect is very unusual and odd for supposedly random samples from the electorate.

Quote:
They don't just gather random samples, not if they have the most elementary notion of how to do their job.
That changes a poll from being a random sample to something completely different.

Regards...jmcc
jmcc is offline  
Advertisement
15-09-2018, 17:20   #1506
Water John
Registered User
 
Join Date: May 2014
Posts: 13,218
Did somebody put Trump and sophisticated in the one sentence???
Water John is offline  
15-09-2018, 17:27   #1507
alaimacerc
Registered User
 
Join Date: Apr 2012
Posts: 7,003
Quote:
Originally Posted by jmcc View Post
That changes a poll from being a random sample to something completely different.
Any guesses in the class for what weighting turns a random sample into?

... waiting... waiting...
alaimacerc is offline  
15-09-2018, 17:29   #1508
alaimacerc
Registered User
 
Join Date: Apr 2012
Posts: 7,003
Quote:
Originally Posted by Water John View Post
Did somebody put Trump and sophisticated in the one sentence???
Dictator chic type of "sophisticated".

Solid gold toilets, mass disinformation, that type of "classy" stuff.
alaimacerc is offline  
Thanks from:
15-09-2018, 17:40   #1509
jmcc
Hackwatch
 
jmcc's Avatar
 
Join Date: May 1999
Posts: 4,056
Quote:
Originally Posted by Water John View Post
Did somebody put Trump and sophisticated in the one sentence???
Trump's Data operation was far more sophisticated than HRC's. It got him to campaign in areas where he could have picked up votes. HRC didn't even bother going there because the Democrats thought that they had the areas. Those areas were crucial to winning some of the Electoral College votes.

Regards...jmcc
jmcc is offline  
Advertisement
15-09-2018, 17:46   #1510
A Tyrant Named Miltiades!
Alexa, Play Liveline
 
A Tyrant Named Miltiades!'s Avatar
 
Join Date: Feb 2015
Posts: 11,116
Mod: Radio, ZTest
Quote:
Originally Posted by jmcc View Post
The pollsters also apply their own "secret sauce" adjustments to some of these polls to derive other indications.
JMCC... if you don't know the methodology that pollsters are employing, how can you claim that the telephone polls are problematic?

I see no reason to believe that the polling companies have not realised possible limitations with things like fixed-line telephone connections, it isn't exactly rocket science, and it should be fairly easy to overcome.
A Tyrant Named Miltiades! is offline  
15-09-2018, 17:47   #1511
An Ciarraioch
Registered User
 
Join Date: Aug 2014
Posts: 3,778
Now that we have a Red C GE poll tonight, the presidential poll is presumably being saved for the print edition.
An Ciarraioch is offline  
15-09-2018, 17:56   #1512
jmcc
Hackwatch
 
jmcc's Avatar
 
Join Date: May 1999
Posts: 4,056
Quote:
Originally Posted by A Tyrant Named Miltiades! View Post
JMCC... if you don't know the methodology that pollsters are employing, how can you claim that the telephone polls are problematic?
Because they publish their basic methodology of using samples of 500 fixed line subscribers and 500 mobile phone subscribers but don't generally publish the response rate.

https://en.wikipedia.org/wiki/Response_rate_(survey)

Quote:
I see no reason to believe that the polling companies have not realised possible limitations with things like fixed-line telephone connections, it isn't exactly rocket science, and it should be fairly easy to overcome.
People who say something is not rocket science aren't typically rocket scientists. Fixed line subscribers have different demographics to mobile phone subscribers. There is also an overlap. Fixed line subscribers are likely to be older than many mobile phone subscribers. This caused problems with the Repeal referendum where they underestimated the support for Repeal and thought that it would be much closer. It was no surprise because most of the 100K new voters would have been underestimated because the sample wasn't a single sample but really two distinct samples of 500 with some possible overlap.

Regards...jmcc

Last edited by jmcc; 15-09-2018 at 18:04.
jmcc is offline  
15-09-2018, 18:49   #1513
A Tyrant Named Miltiades!
Alexa, Play Liveline
 
A Tyrant Named Miltiades!'s Avatar
 
Join Date: Feb 2015
Posts: 11,116
Mod: Radio, ZTest
Quote:
Originally Posted by jmcc View Post
Because they publish their basic methodology of using samples of 500 fixed line subscribers and 500 mobile phone subscribers but don't generally publish the response rate.
Are you telling me you're assuming that polling companies do not apportion weights to their sampling in order to reflect the age and gender profile of voters at all? That it's all random?

It's not really obvious why we should assume that the polling companies operate in a way that anyone with a basic grasp of statistics would not.
A Tyrant Named Miltiades! is offline  
15-09-2018, 18:57   #1514
jmcc
Hackwatch
 
jmcc's Avatar
 
Join Date: May 1999
Posts: 4,056
Quote:
Originally Posted by A Tyrant Named Miltiades! View Post
Are you telling me you're assuming that polling companies do not apportion weights to their sampling in order to reflect the age and gender profile of voters at all? That it's all random?
I added the link to Wikipedia on response rates. Go read it.

Regards...jmcc
jmcc is offline  
15-09-2018, 19:14   #1515
A Tyrant Named Miltiades!
Alexa, Play Liveline
 
A Tyrant Named Miltiades!'s Avatar
 
Join Date: Feb 2015
Posts: 11,116
Mod: Radio, ZTest
Quote:
Originally Posted by jmcc View Post
I added the link to Wikipedia on response rates. Go read it.

Regards...jmcc
I know what a response rate is, but it doesn't answer why you've chosen to make the assumptions you have about Irish polling companies, i.e. that they are apparently not weighting their samples to reflect the electorate, that it's all random.

A leaving cert maths student wouldn't have applied a methodology of the type you seem to be assuming.
A Tyrant Named Miltiades! is offline  
Post Reply

Quick Reply
Message:
Remove Text Formatting
Bold
Italic
Underline

Insert Image
Wrap [QUOTE] tags around selected text
 
Decrease Size
Increase Size
Please sign up or log in to join the discussion

Thread Tools Search this Thread
Search this Thread:

Advanced Search



Share Tweet