A task force of polling experts found surveys notably understated support for Donald Trump, both nationally and at the state level. Here’s what may have gone wrong, according to a polling historian.
Whether you are predicting the outcome of an election or studying how effective a new drug is, there will always be some uncertainty. A margin of error is how statisticians measure that uncertainty.
People know a lot about their friends and neighbors – and pollsters can learn from that information, if they ask.
Polling shows Joe Biden with a large lead over Donald Trump nationally in the presidential race. But there are many ways that presidential race polling has gone wrong in the past, and could do so now.
Members of Congress factor what the public thinks into their decisions. But it’s difficult to measure what the public is really thinking.
Approval ratings are usually a good way to predict the winner of the next presidential election. But Trump’s numbers fall far outside any historical trends.
You could compare election opinion polls to penalty shoot-outs at a World Cup final: there’s huge pressure to get it right and we remember the big misses most of all.
The Tasmanian seats of Bass and Braddon were always going to be key elements of a Coalition victory – and so it proved to be.
More than 1,000 Nebraskans were asked about laws that protect business owners who refuse to serve gays or lesbians. People on either side of the issue made appeals to rights, freedom and capitalism.
Hitting a moving target is hard, and young people don’t always do what’s expected.
Polling is difficult – and everyone except pollsters overestimates how accurate polls are.
Pollsters must be as accurate as possible. How will they address the challenges revealed in the 2016 election, and other changes in the coming years?
From undetected late swings, to pollster ‘herding’.
Swinburne political scientist Bryan Cranton looks at why so many experts got the US Election so wrong
By tracking emotive tweets in the three weeks prior to polling day, these researchers called the election better than most pollsters.
Given the failure of British polls to predict the outcome of Brexit, is it possible Donald Trump could produce a surprise result of even greater proportions?
Elected officials and the media are in cahoots. Both have succumbed to a two-party system that treats voters not as independent thinkers, but as blind partisans.
The polling industry struggled to predict the last British election, and referendums are even harder.
When public opinion is as split as it is on the EU referendum, pollsters struggle to get it right.
Sorry Boris, those with a bet at stake think we’re staying put.