An assessment of the causes of the errors in the 2015 UK General Election opinion polls
An assessment of the causes of the errors in the 2015 UK General Election opinion polls
The opinion polls undertaken prior to the 2015 UK General Election under-estimated the Conservative lead over Labour by an average of 7 percentage points. This collective failure led politicians and commentators to question the validity and utility of political polling and raised concerns regarding a broader public loss of confidence in survey research. In this paper, we assess the likely causes of the 2015 polling errors. We begin by setting out a formal account of the statistical methodology and assumptions required for valid estimation of party vote shares using quota sampling. We then describe the current approach of polling organisations for estimating sampling variability and suggest a new method based on bootstrap re-sampling. Next, we use poll micro-data to assess the plausibility of different explanations of the polling errors. Our conclusion is that the primary cause of the polling errors in 2015 was unrepresentative sampling.
757-781
Sturgis, Patrick
b9f6b40c-50d2-4117-805a-577b501d0b3c
Kuha, Jouni
9e9cab44-4ae7-42cf-8bfe-a4690df3c31b
Baker, Nick
17adb74f-1b7b-44de-b200-51bf5cb81ec2
Callegaro, Mario
b8479f2e-2d1f-4332-824f-2351d2c6d1f6
Fisher, Stephen
d7555867-484c-40da-977d-24b5e5fcdafd
Green, Jane
f70aa78c-6492-4a37-82ef-19d3abc72d6a
Jennings, Will
2ab3f11c-eb7f-44c6-9ef2-3180c1a954f7
Lauderdale, Benjamin E.
0b8e0746-8b5e-4954-9690-005a861678f5
Smith, Patten
4d1bd10f-ca2a-4c3a-a784-06f9f74b28ff
1 June 2018
Sturgis, Patrick
b9f6b40c-50d2-4117-805a-577b501d0b3c
Kuha, Jouni
9e9cab44-4ae7-42cf-8bfe-a4690df3c31b
Baker, Nick
17adb74f-1b7b-44de-b200-51bf5cb81ec2
Callegaro, Mario
b8479f2e-2d1f-4332-824f-2351d2c6d1f6
Fisher, Stephen
d7555867-484c-40da-977d-24b5e5fcdafd
Green, Jane
f70aa78c-6492-4a37-82ef-19d3abc72d6a
Jennings, Will
2ab3f11c-eb7f-44c6-9ef2-3180c1a954f7
Lauderdale, Benjamin E.
0b8e0746-8b5e-4954-9690-005a861678f5
Smith, Patten
4d1bd10f-ca2a-4c3a-a784-06f9f74b28ff
Sturgis, Patrick, Kuha, Jouni, Baker, Nick, Callegaro, Mario, Fisher, Stephen, Green, Jane, Jennings, Will, Lauderdale, Benjamin E. and Smith, Patten
(2018)
An assessment of the causes of the errors in the 2015 UK General Election opinion polls.
Journal of the Royal Statistical Society: Series A (Statistics in Society), 181 (3), .
(doi:10.1111/rssa.12329).
Abstract
The opinion polls undertaken prior to the 2015 UK General Election under-estimated the Conservative lead over Labour by an average of 7 percentage points. This collective failure led politicians and commentators to question the validity and utility of political polling and raised concerns regarding a broader public loss of confidence in survey research. In this paper, we assess the likely causes of the 2015 polling errors. We begin by setting out a formal account of the statistical methodology and assumptions required for valid estimation of party vote shares using quota sampling. We then describe the current approach of polling organisations for estimating sampling variability and suggest a new method based on bootstrap re-sampling. Next, we use poll micro-data to assess the plausibility of different explanations of the polling errors. Our conclusion is that the primary cause of the polling errors in 2015 was unrepresentative sampling.
Text
JRSSA_revision_9August17.2
- Accepted Manuscript
More information
Accepted/In Press date: 31 August 2017
e-pub ahead of print date: 25 October 2017
Published date: 1 June 2018
Identifiers
Local EPrints ID: 415357
URI: http://eprints.soton.ac.uk/id/eprint/415357
ISSN: 0964-1998
PURE UUID: 75455dde-fd99-4c5b-9838-ee56f06ec570
Catalogue record
Date deposited: 07 Nov 2017 17:31
Last modified: 16 Mar 2024 04:10
Export record
Altmetrics
Contributors
Author:
Patrick Sturgis
Author:
Jouni Kuha
Author:
Nick Baker
Author:
Mario Callegaro
Author:
Stephen Fisher
Author:
Jane Green
Author:
Benjamin E. Lauderdale
Author:
Patten Smith
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics