{"id":680,"date":"2017-07-02T14:19:12","date_gmt":"2017-07-02T13:19:12","guid":{"rendered":"https:\/\/marriott-stats.com\/nigels-blog\/?p=680"},"modified":"2017-07-02T18:05:09","modified_gmt":"2017-07-02T17:05:09","slug":"uk-general-elections-2-how-accurate-are-the-opinion-poll-updated-with-ge17","status":"publish","type":"post","link":"https:\/\/marriott-stats.com\/nigels-blog\/uk-general-elections-2-how-accurate-are-the-opinion-poll-updated-with-ge17\/","title":{"rendered":"UK General Elections #2 – How accurate are the opinion polls? – updated with GE17"},"content":{"rendered":"

Ahead of the 2017 general election, I\u00a0predicted that the\u00a0opinion polls would be wrong again and that the Conservatives lead over Labour would be underestimated by 2.6%<\/a>.\u00a0 \u00a0I\u00a0based this on\u00a0data provided\u00a0by Mark Pack who has systematically recorded every opinion poll published since 1945<\/a>.\u00a0 In the event, I was right that the polls would be wrong but instead of an error favouring the Conservatives, the polls recorded the largest ever underestimate of the Labour vote.\u00a0 As a result, election forecasters were\u00a0blindsided yet again and the result was a hung parliament which few saw coming.<\/p>\n

<\/p>\n

This post analyses only the polls that\u00a0took place in the week before every general election between 1950 & 2017.\u00a0 Note this is based on the fieldwork dates, not the publication date which can be a few days later.\u00a0 For the elections in the 1950’s, Gallup were the only pollster so instead of using the week before, I used the month before.<\/p>\n

For each election, I calculated the average vote share recorded across all pollsters for the Conservatives, Labour and Liberal Democrats (Liberals 1950 to 1979, Alliance 1983 & 1987).\u00a0 The polling error for each party can then be calculated as the actual election result for Great Britain minus the average vote share from the polls.\u00a0 I use the figures for Great Britain rather than the United Kingdom since nearly all polls do not survey in Northern Ireland.<\/p>\n

The results can be seen in the chart below.\u00a0 The black line is the number of polling companies that polled in the run up to the election.<\/p>\n

\"\"<\/p>\n

The 2017 general election saw the highest ever underestimate of the Labour vote.\u00a0 At 4.5% this exceeded the 4.3% underestimate in the 1951 general election when Gallup was effectively the only pollster.\u00a0 The Conservative and Liberal Democrat vote shares were spot on.\u00a0 Unlike 2015 when all pollsters got it wrong, some pollsters did get Labour right in 2017 notably Survation.<\/p>\n

Looking back, I am particularly struck by what has happened in the last 3 general elections, specifically –<\/p>\n