Trump and Polling Error

There is little to say on different perceptions in the UK and new Zealand to Donald Trump’s victory. Overwhelmingly there is a consensus, that his was “a primal scream against Washington” (Rupert Cornwell, Independent in the UK). Tracey Watkins, writing for Stuff in New Zealand, concludes that “The forces that propelled Donald Trump into the presidency are the same forces that drove Britain out of the European Union”. That the people of the UK and now the USA wish to take back control of their futures; and, specifically, to have a less divided society, must surely be good.

Some people are concerned that this is a nationalist, right-wing, thing. Looking after the interests of the nation that elected him would be one thing. Bigoted xenophobia would be quite another. Time will tell.

On the polling, the excellent Anthony Wells writes:

“the final polls were clustered around a 4 point lead for Clinton, when in reality it looks about 1 point. More importantly, the state polls were often way out, polls had Ohio as a tight race when Trump stomped it by 8 points. All the polls in Wisconsin had Clinton clearly ahead; Trump won. Polls in Minnesota were showing Clinton leads of 5-10 points, it ended up on a knife edge. ”

There is already a narrative about “shy” Trump supporters appearing in the media. Evidence for this is apocryphal to non-existent. It is too early to know the reasons that the US pollsters got it so wrong, but we do know why the UK pollsters got the last UK general election wrong. The British Polling Council conducted an in depth review, and “shy Tories” was an urban myth not a cause. They concluded that “The main cause of the error was unrepresentative samples”. Anthony Wells’ excellent summary, with a link through to that full report is here.

The US and UK electorates understood that “if you keep doing what you’ve always done, you’ll keep getting what you’ve always gotten” and voted for something different – anything different. The pollsters techniques were incapable of identifying and correctly analysing that change.

Leave a Reply

Your email address will not be published. Required fields are marked *