Polls, youth, and experimental weighting

There seem to be very widely different predictions from the various polling companies in the run-up to the 2017 General Election, with some much closer than others.

I was curious as to which polls I should put more trust in as the general Election approaches, and remembered how in the aftermath of the 2015 election, some polling companies had been more accurate than others in predicting the final result.

So I went on DuckDuckGo to search for whose poll was closest.

I didn’t really get back a useful answer to that question in terms of which polls to trust. But I did find a fascinating piece from YouGov published today about why the results seem so widely varied, and what’s going on in those companies.

Two points stuck out for me strongly: the first is that, as the title of that piece says, this election is being treated as a testing ground for different fixes made in response to the opinion polls’ 2015 failure (although many polls there were within margin of error). Different companies are using different methods to weight their samples and try to model the outcome based on their answers.

The other was this observation:

The reason the polls got the 2015 election wrong was down to sampling, particularly among young people. The sort of young people who took part in polls were too engaged and too likely to vote, meaning polls ended up with too many young people voting. Polling companies have taken different approaches to solving this, but they broadly fall into two categories. Some have tried to improve their samples to reduce the number of people who are very interested in politics. Others have changed their turnout models so that they assume the same low level of turnout among young people as happened in 2015.

Generally speaking, the polls that continue to show a large Conservative lead are those who are basing their turnout models on the pattern of turnout in 2015. Those that show smaller leads are basing turnout on how likely people say they are to vote.

The author concludes that there are two possibilities on election day: either the younger voters turn out, and Labour do well; or turnout by age matches 2015 and the Tories have a strong win.

My conclusion is that, perhaps more than ever, young voters are the key to this election and have a real chance to shape the world they want to live in.

Incidentally, YouGov’s most recent poll showed a 42-39 split (which is a statistical tie – it’s in the margin of error) and this was based on a weighting “recruiting more people who are less interested in politics and weighting by political interest and education” and also “we weight down people who didn’t vote in 2015.”

I refuse to have hope. The closest I will come to “hope” is to imagine that May will have a smaller majority in Parliament. I don’t want to jinx things by for even a second imagining that Corbyn could win; I don’t want to risk the utter dashing of that hope if I do start to believe it’s possible.

But please: vote. Vote Labour. Let me hope again!


About ValeryNorth

I overthink everything.
This entry was posted in Politics, Uncategorized and tagged . Bookmark the permalink.

One Response to Polls, youth, and experimental weighting

  1. Pingback: Digging into the pollsters (GE2017) | Valery North – Writer

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s