GE 2017 #10: Predictions & Opinion Polls: a Hung Parliament, Why Not?

Well, I suppose I can always delete this post at 10pm tonight when the result of the exit poll is published!

There are no good reasons for assuming that the Tory’s will win with a comfortable majority.  Opinion polls are a better guide to the likely outcome of the election than feelings and “anecdotal evidence”.  Of course, opinion polls may be wrong (and given that they are producing very different projections), a lot of them will be wrong.  But just because Joe Bloggs down the pub guesses right (and the opinion pollster gets it wrong) does not mean that we should have relied on Joe Bloggs all along.

Insofar as criticisms of the polls are based on a sense of what’s going on in the country or on how we would expect people to react to Corbyn’s chequered past or to Mrs May’s facile campaigning, those criticisms should be discounted. Such feelings or such “analysis” is wholly speculative.

Polls/projections are based on something tangible, people’s stated opinions, and use defensible methods of arriving at headline figures from those actual experimental results.  If they’ve got their models right, then, all those factors that seem significant  to us should already be factored in (and factored in to the appropriate extent).

As far as I can tell, betting markets and the prevailing wisdom (a comfortable Tory majority, albeit not a landslide), are based on a “sense” of what is happening rather than a wholly objective view of the most objective data.

The truth is that the pollsters are simply not sure, and are not agreed, about the correct methodology they should use this time and this explains the divergence in polls.  [They are hearing broadly the same things from voters;  they are just not sure of the best way to process the raw data.]  And certain things cannot be reliably known in advance.  Will today’s bad weather reduce turnout differentially?  Will Conservative voters stay at home after all because of Mrs May’s uninspiring campaign?  Will young people turn out in unusually high numbers because, perhaps, Labour has promised to abolish tuition fees in England?

So, we really cannot tell whether the Tory lead will be 1% [well and truly a hung parliament] or 12% [something approaching a Tory landslide] or somewhere in between.  There remains a not insignificant chance that we are heading for a hung parliament.


Leave a Reply

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

You are commenting using your 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