American Research Group, Inc.

 

2017 United Kingdom General Election Pollster Ratings

 

The following table lists the accuracy of pollsters in the June 8, 2017 United Kingdom general election using the measure of polling accuracy proposed by Martin, Traugott, and Kennedy.

An accuracy measure of 0.00 indicates that the odds ratio of the survey results matches the odds ratio of the actual results (the closer to 0.00, the better).

 

2017 UK General Election
Conservative Labor Odds
Ratio
Accuracy
Survation
41% 40% 0.97 -0.04 
SurveyMonkey 39% 35% 0.05 0.05*
Kantar Public 43% 38% 1.07 0.06 
Qriously 39% 41% 0.90 -0.11*
YouGov 42% 35% 1.13 0.12*
Opinium 43% 36% 1.13 0.12*
Ipsos MORI 44% 36% 1.15 0.14*
Panelbase 44% 36% 1.15 0.14*
ComRes 44% 34% 1.22 0.20*
ICM 46% 34% 1.27 0.24*
BMG 46% 33% 1.31 0.27*
Actual 42.4% 40.0%

 

*The accuracy measures for nine of the eleven polls fall outside their respective 95% confidence intervals.

While the SurveyMonkey poll has an accuracy measure of 0.05, the accuracy measure is greater than what would be expected from sampling error with a sample size of 11,853.

The average absolute accuracy for all polls is 0.137.

As a comparison, the average absolute accuracy for all polls in 2016 EU referendum was 0.143 and the average absolute accuracy for all polls in the 2014 Scotland independence referendum was 0.126.

The average absolute accuracy for all polls in the 2016 US presidential election was 0.070 and the average absolute accuracy for all polls in the 2017 French presidential election was 0.194.


ARG Home