DEBUG: https://d3n8a8pro7vhmx.cloudfront.net/london4eu/pages/5/features/original/heart_photo.png?1501497680
DEBUG:
DEBUG: blog_post
Polls into seats
04 May, 2019

Opinium - 12-15 March 2019 (Note the date - published out of sequence)

London4Europe Committee Member Michael Romberg works out what the opinion poll findings for the European Elections in London mean for seats. Remember: it’s just a poll – a snapshot that comes with a significant margin of error. The margin is bigger than usual because London respondents are just a small subset of the overall sample.

 

Data Source:  Opinium - fieldwork 12-15 March 2019   -  199 replies in London, not weighted by likelihood to vote, excluding don't know/ won't say/ won't vote (24% of unadjusted London sample).

 

Note: this poll was conducted in March 2019.  It is being published by London4Europe way out of sequence. it was carried out before the Brexit Party and Change UK had been formed.

 

TABLE 1: This table takes the opinion poll findings and turns them into seats using the D’Hondt method (read more about that here). Seats won in each round are shown in bold. Poll numbers are then adjusted for subsequent rounds of seat allocation.

  

 

UKIP

Con

Labour

Green

LD

Other

Poll

8 29 39 6 15 3

1

8 29 39 6 15 3

2

8 29 19.5 6 15 3

3

8 14.5 19.5 6 15 3

4

8 14.5 13 6 15 3

5

8 14.5 13 6 7.5 3

6

8 9.7 13 6 7.5 3

7

8 9.7 9.75 6 7.5 3

8

8 9.7 7.8 6 7.5 3

Total

0 3 4 0 1 0

 

Notes

LD = Liberal Democrats

 

CAVEATS

  • It’s a poll. A snapshot in time. People’s views change. If “don’t know/ won’t say” is large, then their views could swamp small differences between parties once they decide.
  • European elections normally have low turnout. Differential turnout amongst supporters of different parties could affect the result compared with a poll. Different polling companies have different methodologies for adjusting for turnout.
  • The definition of “London” in the poll may not match the London constituency for the election.
  • Polls come with a margin of error. On the highest level figures asking a question of the whole sample a rule of thumb is that polls come with a margin of +/- 3 percentage points (so 45% think this might be anything in the range 42%-48%). London figures are normally a small subset of the poll so the margin of error is larger. A good overall sample size for a poll is 2,000 or so.
  • My calculations are on rounded numbers and that might introduce an error when results are close.

 

TABLE 2: this table works out a counterfactual allocation of seats if the Remain parties had joined on a single platform. The calculation assumes that the vote for the platform would be the sum of the votes for the individual parties. That would not be the case in real life – there are arguments for saying that a platform might do better or that it would do worse than the sum of the parties.

In the case of this poll a common Remain Platform would have obtained one more seat than if the parties had stood separately.

 

 

UKIP

Con

Labour

Remain

Other

Poll

8 29 39 21 3

1

8 29 39 21 3

2

8 29 19.5 21 3

3

8 14.5 19.5 21 3

4

8 14.5 19.5 10.5 3

5

8 14.5 13 10.5 3

6

8 9.7 13 10.5 3

7

8 9.7 9.75 10.5 3

8

8 9.7 9.75 7 3

Total

0 2 4 2 0

 

Remain = sum of poll results for  Green and Liberal Democrats