Our very own great polling disaster
Tuesday 4 June 2019
- Opinion piece for The Canberra Times by Peter Brent, Adjunct Research Fellow, Swinburne University of Technology
Step aside Brexit, move out of the way Donald Trump. The plucky country is once again punching above its weight. Yes, Australia has had its very own spectacular opinion poll flop.
The headline fail was the fact that all pollsters reported Labor's two-party-preferred support rounded to 51 to 52 per cent in the campaign's final days. When the counting is over, it will be close to 48 per cent. So, 3 to 4 per cent off. (That's about how wrong they were in Victoria in November last year, but the difference between a big win and a landslide doesn't generate the same headlines.)
The primary figures were way out too. Leaving aside idiosyncratic Ipsos, which always overstates the Greens (mostly at the expense of Labor), the pollsters exaggerated Labor support by 2 or 3 percentage points and understated the Coalition by 3 or 4.
We'll never know for sure why that happened, but here are a few clues about the great 2019 polling disaster.
The Queensland factor
The northern state has a long tradition of excess enthusiasm for Labor in the polls, which then corrects as election day approaches. In 2019, the trajectory was extra steep. Just six months ago, the polls were suggesting a two-party-preferred swing to Labor of about 7 or 8 per cent in Queensland. The current estimate is 4.2 per cent - in the other direction.
Overstating minor parties, understating the Coalition
Entirely predictably, the polls also overstated support for the biggest right-wing minor parties, One Nation and the United Australia Party. One reason is the decision to include them on the initial "which of these will you vote for?" list read out to respondents. All the pollsters included One Nation in the opening question, while only Galaxy and Newspoll (which happens to be run by Galaxy) included the UAP.
It seems likely that the vast bulk of the people who told pollsters they would vote for these two parties, but didn't, put a "1" next to the Coalition instead.
This is part of the same minor-party problem. Not only did pollsters overstate their support but, by using flows from 2016 (One Nation) and 2013 (PUP, Clive Palmer's previous party), they understated preferences for the Coalition.
Only Galaxy and Newspoll seem to have assumed a relatively high 60 per cent flow to the Coalition from both minor parties, but even that looks likely to be too low.
The ingredients came together in a particularly combustible fashion in Queensland, where support for those minor parties was highest. Still, even allowing for these minor-party and preference errors, we're left with a big polling miss.
Statistically skilled commentators tend to be dismissive of "late swings", seeing them as excuse-making by the pollsters. I'm not so sure.
Voting-intention polls aim to measure how the voting population would answer the "how will you vote?" question, not how the respondent actually would vote. As election day approaches, the voting scenario becomes less hypothetical and the two concepts should converge.
To an extent, all elections involve scare campaigns with potential effects on polling day. The desire to kick the government out is tempered by a fear of the alternative. At this election, this dynamic was dialled up to the red zone.
So a late swing could happen, even after Newspoll stopped surveying at noon on Friday. All it takes is for undecideds to break predominantly one way.
A counter-argument is that the YouGov/Galaxy exit poll had Labor on 52 per cent after preferences. But polls like these, conducted across a selection of unidentified electorates, have always been rough.
What about the internal party polls? Journalists' reporting suggests Labor was delivering mixed messages. One, based on the tracking polls (conducted for the first time by YouGov/Galaxy), had them easily winning.
But there was also hand-wringing in the final week, seemingly based on Labor's individual seat polls. Expectations had dipped into minority government territory. Then, by Friday evening, Labor insiders evidently had a spring back in their step and were briefing journalists on a seat haul in the high 70s to low 80s. (Labor has ended up with 67 or 68.)
The Coalition, meanwhile, was happy to confide doom and gloom. The polling was generally pessimistic, with the odd ray of light.
Many brainy people, including Nobel laureate Brian Schmidt, detect something fishy in the pollsters' two-party-preferred numbers across the campaign: they're all so similar, sitting at about 51 and 52 per cent. They calculate, to varying degrees, the chances of the campaign polls being so close together as astronomically remote.
My humble reservations about these points will need to wait for another article. (Mostly, they're to do with the fact the pollsters measure primary support and estimate two-party-preferred, and the primary numbers didn't obviously herd.)
My two cents
To overcome the minor-party problem, the pollsters might like to try surveying twice as many people, and naming the minor parties they deem worthy of inclusion for only half the respondents. The differences between the two sets of results over time could be illuminating, at least giving an indication of the softness of major-party support vis a vis minor parties.
And they should keep a very, very close eye on Queensland. But they'll no doubt be doing that anyway.
Peter Brent is an Adjunct Research Fellow at Swinburne University of Technology. Read his opinion piece originally published in The Canberra Times.