The curious thing about election polls is that they can be wrong by miles, but so long as the candidate with the predicted lead still wins, no one much cares. For example, a survey suggesting Candidate A has a 20-point advantage over Candidate B in an election where A only ends up winning by five points is much less accurate than one which predicts that Candidate A has a three point lead, but goes on to lose to B by one point.
Predicting the wrong winner in a tight contest is simply much more memorable than misjudging the size of victory in a landslide race. So we all have post-traumatic stress disorder following the polling error in the 2016 US presidential election which Hillary Clinton lost (despite winning the popular vote) but forget the even bigger polling error in favour of Joe Biden in 2020, because, well, Biden won anyway.
So where does this leave Sadiq Khan? The Labour candidate – and recipient of the Standard's endorsement in today's paper – is either enjoying a vast 22-point lead (if you ask YouGov) or a more modest 10-point lead (according to Savanta). This is annoying for voters and commentators alike but deeply unsettling for pollsters because clearly, someone's sample isn't quite right. But whose?
A look back at history is instructive. In the weeks before the 2021 mayoral election, Khan was racking up 20+ point polls leads over then Tory rival, Shaun Bailey. But, in the final days, two polls gave Khan a much-reduced 12-point lead. And on election day itself, the mayor eked out a five-point first round advantage. Might history be repeating itself?
There are reasons to think so. Khan is a more polarising figure today, thanks in large part to his decision to extend London's ultra-low emission zone. He is perceived as being weak on crime, with knife and gun crime in London leaping by 20 per cent last year while there has been a 38 per cent rise since Khan came to power in 2016. Finally, there is the basic fact that running for a historicTM third term is difficult. Voters get bored after a while.
On the flip side, his opponent, Susan Hall, has not had a great campaign. Writing in yesterday's paper, Anna van Praagh's description of the Conservative candidate's performance as "unpolished" demonstrated once again that understatement is often more devastating than hyperbole. But Hall is not yet out of it. Key will be turnout – a low one is thought to favour her given the depth of feeling surrounding opposition to Ulez and antipathy in some quarters towards Khan.
Ultimately, the mayor is heavy favourite to win tomorrow (votes will be counted on Saturday). And the result matters far more than the margin. Still, it is notable that in a heavily Labour city, amid an exceptionally anti-Tory political environment and against a fairly weak opponent, Khan cannot be sure of victory. Given all those advantages, he really ought to be.
