Recent State Election Polling Does Not Skew To Labor

Advance Summary

1. A major polling failure in the 2019 Australian federal election has been attributed to unrepresentative sampling, coupled with inadequate reweighting, that produced a large skew in primary vote and 2PP estimates in Labor's favour.   

2. A recent report argues that a skew in federal 2PP polling was present throughout the period 2010-2019 and was not specific to 2019.  

3. If this was the case, and was so for the same reason, then a skew to the ALP should also be expected from the much larger sample of state-level final polls taken over the same period.

4. However, state level polls in Australia from 2010-2020 do not display any overall two-party skew to the ALP.

5. Also, while federal polling for 2010 overestimated Labor, final 2PP polling at the 2013 and 2016 federal elections was mostly very accurate.

6. While federal polls overall (not all specific polls) do have a record through recent decades of on average overestimating the Labor 2PP, this record is much inflated by a single pollster (Morgan).

--------------------------------------------------------------------------------

2019 Federal Election: Pollster Performance Review

Welcome (belatedly) to another of my regular pieces that I do after all the election results are finalised and, um, we can't really give this one its usual title this year.  Normally it's called "Best and Worst Pollsters" (see the comparable articles for 2013 and 2016) but this year that title isn't really appropriate.  This year was the year of the great Poll Fail, and when it came to final voting intention polls at least, they all went down together.  The story for seat polling turns out to be a little less clearcut, but not that much.

For all the complaints about "too many polls", the frequency and diversity of Australian polls had been declining at state and federal level in the four years leading up to this election.  At this election there were only five poll series conducting national polls, and of these two were conducted by the same pollster (YouGov-Galaxy conducts both Galaxy and Newspoll polls).

I usually include three categories but this time I'm not going to take tracking too seriously.  As usual the first cab off the rank is ...

Least Worst Final Poll

I usually say the final poll should be the easiest one for the less accurate pollsters to get right, because pollsters can look over each others' shoulders and consider corrections if everybody else is getting something vastly different.  Thus there have been some prior cases where polls that differed from Newspoll for some time have jumped into line with it in their final poll.  This year unfortunately it seems that some pollsters may have taken this concept a little too far - either that or multiple pollsters got to around the same 2PP coincidentally and then decided to self-herd from that point.

The Miracle Is Over: The 2019 Australian Federal Election Poll Fail

Nice 2PP.  Shame it's for the other side ...

"I have always believed in miracles" said re-elected Prime Minister Scott Morrison very late on Saturday night.  But many (not all) of us who study national Australian polls and use them to try to forecast elections have believed in a miracle for one election too many.  The reason we believed in this miracle was that it kept delivering.  While polls failed to forecast Brexit, Trump and two UK elections in a row (among other high profile failures) Australian national polls continued to churn out highly accurate final results.  The two-party preferred results in final Newspolls from 2007 to 2016 are an example of this: 52 (result 52.7), 50.2 (result 50.1), 54 (result 53.5), 50.5 (result 50.4).  

Predicting federal elections pretty accurately has long been as simple as aggregating the polls, adjusting for obvious house effects and personal votes, applying probability models (not just the simple pendulum) and off you go; you generally won't be more than 5-6 seats wrong on the totals.  While overseas observers like Nate Silver pour scorn on our little polling failure as a modest example of the genre and blast our media for failing to anticipate it, they do so apparently unfamiliar with just how good our national polling has been since the mid-1980s compared to polling overseas.  As a predictor of final results, the aggregation of at least the final polls has survived the decline of landlines, volatile campaigns following leadership changes or major events, suspected preferencing shifts that frequently barely appeared, herding with the finish line in sight, and come up trumps many elections in a row.  This has been put down to many things, not least that compulsory voting makes polling easier by removing the problem of trying to work out who will actually vote (another possibility is the quality of our public demographic data).  But perhaps it was just lucky.

Rolling Poll Roundup And Seat Betting Watch: The Final Days

2PP Aggregate 51.5 to Labor (by last-election preferences) (-0.3 since last week)
51.1 with One Nation adjustment
Current seat projection approx Labor 79 Coalition 66 others 6 assuming polls accurate.

The end, it seems, is nigh.  If the (ludicrously herded) national polls are right, the Morrison government would need a huge amount of luck to survive a swing of somewhere around 1.3-2.3%, at an election at which it can afford perhaps two net seat losses.  If the polls on the whole are just modestly wrong in one direction, the Government's chances of survival improve greatly, but the other direction leads to a decisive loss.  The most likely path to survival is a Donald Trump style path - a combination of a modest national polling error and a fair amount of luck with the local breakdowns, but if it happens in this case, after everything, it will be very surreal.

Poll Roundup: Well-Received Budget Yields A Kitten-Sized Bounce (Maybe)

2PP Aggregate: 52.5 to Labor (2016 preferences) (-0.5 in a week)
(51.9 with One Nation adjustment)
Labor would win election "held now", with seat tally around the low 80s

Equal best polling position for Coalition under Morrison so far
Budget reception among the best ever in some regards, but not all
Weak evidence that there may have been a "Budget bounce" of around half a point, but impossible to confirm

----------------------------------------------------------------

The 2019 Budget has been delivered with the election expected to be called sometime in the next week.  This year's budget was in most ways well-received, although the voters have not bought the Government's attacks on the ability of the Opposition to deliver the same thing.  There was remarkably little polling in the leadup to the Budget, so it's hard to say for sure if we have seen that rare creature the Budget bounce or not, but if we have seen it, it's probably only a little one.  We can't yet reliably conclude that the modest move to the government this week is caused by the Budget at all as opposed to other factors.  As it isn't statistically significant, it may even just be random noise.

2019 NSW Election Live Comments

Summary

Coalition has won the election - probably with a small majority 

Apparent wins Coalition 45 Labor 35 Green 3 Ind 3 SF+F 3, 4 in doubt
(Apparent wins are not necessarily all confirmed)

Apparent seat changes:

Barwon (Nat to SF+F) - but need to wait for Broken Hill booths
Murray (Nat to SF+F)
Coogee (Liberal to Labor)

In serious doubt:

Lismore (Nat vs Green vs ALP - long postcount ahead)
Dubbo (Nat vs IND - close)

In some doubt:

East Hills (Liberal leading Labor)
Upper Hunter (Liberal leading Labor)

Assumed won but at low doubt levels: 
Wollondilly (Liberal vs IND - no 2CP count available)
Penrith (Liberal leading Labor)

Commentary appears below the double line with latest comments scrolling to the top - refresh frequently for new comments once count starts.  Comment clearance during commentary will be slow and comments may not be replied to until very late.

2018 Victorian Final Polls

Galaxy 53-47 to Labor, ReachTEL 54-46 to Labor

Current primary vote aggregate ALP 40.7 L-NP 39.4 Green 11.0 Other 8.9

Polls could be underestimating Labor 2PP vote slightly and may be overstating Greens primary

Seat projection estimate ALP 48 L-NP 36 Green 3 IND 1

This post will update all polling news in the final 24 hours of the Victorian campaign.

If the latest polls are right, yesterday's token post about Lower House modelling might not be quite so token after all. What we've seen in the Herald Sun's YouGov-Galaxy (53-47 to Labor) and Fairfax's ReachTEL (54-46 to Labor) suggests that the net effect of the last few weeks of campaigning has been more or less zero.  The polling would not have to be wildly wrong for an unlucky distribution of seats to leave Labor short of a majority, but it would have to be very wrong indeed for the Coalition to win the election in any way.

2018 Victorian State Election Intro

It's very close to the 2018 Victorian state election for me not to have written a thing yet about it!  Largely this has been because my analysis model needs polling to work, and (in common with other recent state elections) there's hardly been any of it.  Anyway, this is an opening offering on some general issues in trying to forecast this election

Let's start with the important bit.  If voting in the Legislative Council (upper house) in Victoria, vote below the line for candidates, not above the line for parties.  You only have to choose five candidates for a valid vote, though you will make your vote a lot more powerful if you number a lot more.  If you vote above the line, your vote will be at the mercy of your party's decisions about where to send your preferences, and they may well choose to send it to a party who you'd be totally opposed to.  Unfortunately, Victoria is one of the two remaining states that has not got rid of the Group Ticket voting system.  Keep control of your own vote and say no to preference-harvesting which can lead to unknown parties electing unaccountable candidates off tiny percentages of the vote.

How Did The Super Saturday Seat Polls Go?

With final results for the Super Saturday by-elections now available, including preference flows, it is worthwhile reviewing the accuracy of the seat polling for these by-elections.  Recently I have posted a few times here about seat polling - see Is Seat Polling Utterly Useless? and Why Is Seat Polling So Inaccurate?  The preferencing results of the Longman by-election are also of special interest to the debate about Newspoll preferences, as the first test of Newspoll's changed methods at any federal election.

We can put that one to bed right away: the preference flow from One Nation to the Coalition in Longman was a massive 67.74%.  This should not be taken as a sign of quite how strongly One Nation preferences would flow nationally, since they did preference the LNP in this seat but would not necessarily do so in every seat, and since LNP preferences flowed strongly to One Nation in the area at the Queensland election even in the seat where the party preferenced Labor.  But it does show that it is entirely reasonable for pollsters to assume that 2016-election preferences can't be trusted in the case of One Nation.

Is Seat Polling Utterly Useless?

Advance Summary

1. Seat polls have received bad publicity because of poor results at the 2013 and 2016 federal elections, and in some other recent elections such as the WA Darling Range state by-election.

2. Because it is clear that seat polls are not very accurate, it is common for posters on social media to dismiss them out of hand as useless or so misleading as to be worse than useless.

3. Indeed, seat polls at the 2016 federal election shows they were so inaccurate that they had greater average 2PP errors than simple models based on uniform swing and national polling.

4. However, in 2016 hybrid models combining seat polling and uniform swing would have been more accurate than either seat polling or a uniform swing model alone.

5. The correct use of publicly available seat polling seems to be not to ignore it entirely, but rather to aggregate it with other sources of information including national modelling.

6. Seat polling should be most useful for races that are difficult to predict by normal means, but seat polls may be unusually inaccurate in those races too.

7. The biggest problem with seat polling is the reporting that treats unreliable seat polls as definitive verdicts that one side or the other is "winning".  In fact they are weak indicators and need to be reported in the context of other evidence.

Poll Roundup: What Is Going On With Newspoll Preferences?

2PP Aggregate (Last-election preferences): 52.4 to Labor (-0.4 since last week,  -1.2 points in five weeks)
With One Nation adjustment, 51.8 to Labor 
Closest position since May last year
Labor would very probably win election held "right now", but would probably have a small to moderate majority

[Updated on 26 April at bottom of post]

------------------------

Normally I issue Poll Roundups every second Newspoll. Since the last one there's been the slight distraction of the Coalition's 30th consecutive 2PP Newspoll loss. This week's Newspoll was number 31 in a row, just two shy of equalling the longest losing streak held by Labor under Julia Gillard, but it was more significant for the discussion it has sparked about (i) Newspoll's preferencing methods (ii) the prospect of a Coalition recovery.  So firstly, a detailed discussion of the preferencing issue, and then a slightly shorter discussion of where things now stand in federal polling.

Newspoll as a brand name linked to a standard set of questions has a 33-year history in Australia.  However, in 2015 the company previously doing Newspoll for the Australian was wound up.  The Australian retained control over the brand, but its operation was contracted out to Galaxy Research (which in turn was recently acquired by YouGov).  While the questions didn't change when Galaxy took over, the methods did, with a mixture of robopolling and online polling replacing the old Newspoll's landline-only live phone polling, and an increase in average sample size.

2018 SA Election Late Polls And Other Comments

SA: Newspoll and ReachTEL 34-31 on primary votes to Liberal
No predicted winner - too close to call

On Saturday night I will be attempting to live-comment the SA state election and the federal Batman by-election at the same time starting from 6:30.  Really this shouldn't be too hard, since Batman is just one seat, so I hope it will be useful.  They will be on separate threads and I will be trying to give each about equal attention to start with, though if Batman can be called quickly I will wind it down and switch to focusing purely on South Australia.

Queensland 2017: Final Results And Polling Accuracy

Queensland: ALP 48 LNP 39 KAP 3 PHON 1 GREEN 1 IND 1
2PP Estimate 51.2 to Labor (+0.1 from 2015)

It's taken a while but I've finally found some time to put up something about the final results of the 2017 Queensland state election.  I try to always put something out on Christmas Day, though last year nasty weather interfered with that plan.

In a nutshell, the 2017 Queensland election was one where a great many dramatic things could have happened, but virtually none of them did, as the following sections explain:

Hardly any seats changed hands

You don't turn 89 seats into 93 without breaking a few eggs, but the level of seat transfer between the parties at this election was remarkably low.  On a notional basis and ignoring retirements and mid-term defections, just nine seats changed hands at this election, most of them marginal anyway.  The Liberal National Party lost Redlands (1.2%), Gaven (2.8%) and Aspley (3.2%) to Labor, and would have lost Maiwar (3.0%) to Labor as well but the Greens snatched it instead.  Labor lost Bundaberg (0.5% and which was a freak win last time anyway) and Burdekin (notionally theirs by 1.4% but LNP-occupied) to the LNP, and might have lost Mirani (3.8) to the LNP had not One Nation helped itself to its only win.  The LNP also dropped Noosa (6.6) to independent Sandy Bolton, and Hinchinbrook (3.4) to KAP's Nick Dametto.  In Hinchinbrook, Dametto (who according to his party had only been campaigning for four weeks) pulled off a duplicate of Andrew Wilkie's Denison 2010 winning method of coming third and getting everyone's preferences.

Poll Roundup: 2017 Year In Review

2PP Aggregate: 53.4 to Labor (-0.4 since last week, -0.8 in three weeks)
Labor would easily win election "held now"
Average for 2017 53.3 to Labor
By last-election preferences, Labor won all 93 polls this year

The polling year has just about come to an end so it's time for the annual roundup.  Should any further national polls appear I will edit in any necessary changes.

Since the last roundup things have improved slightly for the Turnbull federal government.  Following a brace of 55-ish results to Labor around mid-November, we've had two 53s from Newspoll, a run of 54-54-55-54-53 from Essential, 53s from ReachTEL four weeks back and Ipsos two weeks back (but the ReachTEL 53 came out at 54.7 by last-election preferences), and results from YouGov that came out to 53.1 and 54 by last-election preferences from YouGov.  (As noted further below, YouGov's 2PPs are wacky, so let's ignore them.)  The two 53s from Newspoll and today's 53 from Essential all looked like they were probably rounded down, and so my aggregate now sits at 53.4 to Labor.  Here's the (slightly) smoothed tracking graph:

New England Washup and Bennelong By-Election Preview

I've decided to combine some post-result comments about New England with an overdue preview of the Bennelong by-election, which will be updated for any further polls that are published.  It's really not possible to talk about Bennelong now without talking about the former and whether anything seen in New England does or does not apply.

New England: Barnaby Bolts Back In

While Barnaby Joyce's re-election was always extremely likely given the lack of serious opposition, the scale of it surprised me.  Currently Joyce has 64.6% of the primary vote, a 12.3% swing to him, and a 73.6% two-party vote against Labor, a 7.2% swing to Joyce.  It seems that Labor are second, although in theory independent Rob Taber might overhaul the 4.4-point gap on the 17.2% of minor-candidate preferences.  Even if he does, his two-candidate result against Joyce won't be much better than Labor's.

My pre-election expectation was that Labor would not get much 2PP swing and that there would probably be a modest 2CP swing away from the result achieved by Tony Windsor in 2016, but that the gaggle of candidates running against Joyce might be able to take him to preferences and delay the result.  Instead Joyce has picked up a primary vote swing compared even to his 2013 result, when Tony Windsor wasn't on the ballot paper.

2017 Queensland Election Postcount (Main Thread)

Labor has won the election

Final result ALP 48 LNP 39 KAP 3 ONP 1 IND 1 GREEN 1 

Pumicestone won by LNP
Cook assumed won by ALP
Rockhampton won by ALP
Gaven won by ALP
Maiwar won by Greens
Hinchinbrook won by KAP
Macalister won by ALP
Burdekin won by LNP
Townsville won by Labor

This thread will follow the 2017 Queensland election post-election-day count in those seats that remain up in the air.

I'm in no real doubt now that Labor has won the election, in some form or other, but that form (majority or not, and if not with what numbers) remains to be clear.  They have 44 wins that I am regarding with some trepidation as solid, and one more ( Gaven) that I think they have probably won.  There are two more that appear to be going to "the left" in some form (Maiwar and Rockhampton), a close one in Townsville, and it is also worth noting that the indie who appears to be winning Noosa preferenced Labor. A vast amount has to go wrong from there before an LNP-ONP-KAP-indie government could be seriously considered, and even then it's not clear which way KAP would go.

This thread will follow the seats that I consider to be in significant doubt.  Where time permits and a seat greatly interests me, it may be given a breakout thread.  Seats appear in alphabetical order but when a seat is no longer considered of interest it will be moved to the bottom of the thread.  It will take me some time today to add all the seats.  Updates on specific seats will be added as time allows, but because of work commitments this is only likely to happen in the evenings, and probably not all of them.

Queensland: The Election Polls Forgot

Queensland Aggregate: Labor 35.9 LNP 33.9 One Nation 13.3 Green 9.6 Other 7.3
2PP off this aggregate: 52.5 to Labor
Seat projection off this aggregate: Labor 51 LNP 37 PHON 3 KAP 2 
(Greens may win 1-2 seats instead, but not enough reliable evidence re Greens' chances)
Uncertainties: limited polling dominated by a single pollster, change in preferencing method and likely preferencing behaviour

Nearly three years ago an incumbent Queensland government was leading about 52-48 in the polls and polling analysts generally though that it might lose but would probably be returned.  We were wrong; it did very narrowly lose, mainly because of a radical shift in preferencing behaviour by voters for minor parties.

Three years later, some of the problems are the same.  A radical shift in preferencing behaviour is possible in theory, because Pauline Hanson's One Nation was just a minor presence last election but is now gathering a double-digit vote.  Moreover, some polls have showed One Nation voters as much more likely to preference the conservative side of politics than they used to be - a situation consistent with the party attracting a lot of ex-Coalition supporters.

How Accurate Was The Same-Sex Marriage Polling?

The abrogation of responsibility and waste of resources that was the Marriage Law Postal Survey has now concluded with a Yes vote of 61.6%, based on a very high turnout of 79.5%.  Every Australian poll on same-sex marriage in the last ten years has shown more voters supporting same-sex marriage than opposed, with the exception of a single fledgling ReachTEL in 2011, so this has been seen initially as another good result for Australian polls.  In contrast, non-polling "big-data" approaches based on social media analytics failed completely, with the EqualityPulse site mostly favouring the No vote until after the polls had closed and a Griffith University study bombing embarrassingly.  (Be wary of anyone who claims their methods predicted Trump would win - most who predicted him to win did so because they wrongly expected him to win the popular vote.)

This is being taken as another strong result for Australian polling, but the reality is not so snazzy, and more consistent with experience elsewhere.  Below are all the final poll results by each pollster that I could find.  (Some pollsters conducted several polls, typically finding little variation through the survey period.) The polls vary in methods - some asked about results based on those who had voted, some asked about the votes of those who intended to vote and some just asked a basic question about support or opposition to same-sex marriage.  One (Ipsos) appears to have asked about voting intention among those certain to vote only.  In many cases, inadequate public documentation means that it is not entirely clear what the pollster did.

All Polling On The Plebiscite Has Problems

In the last few weeks we've seen some new polling results concerning the Coalition's proposed plebiscite on legalising same-sex marriage (or as it is more accurately described, marriage equality).  It is extremely well-established in polling that a clear majority of voters support legalising same-sex marriage, but whether voters support deciding the matter by plebiscite or parliamentary vote has been less obvious.  The very inconsistent results from various polls on this subject are causing a fair degree of interest and confusion.

In this article I suggest that the range of results we are seeing on the question of a plebiscite vs a parliamentary vote is largely a result of differences in design between different polls.  Which poll is right and which poll is wrong?  My view is that all of them are suspect.   The question is a difficult one to poll and none of the polls offered thus far have even got close to a design that accurately reflects the choices the parliament, voters and activists face.

Queensland: One Nation Have Peaked, So Now What?

I last looked at Queensland state polling back in February, when a rampant One Nation were polling 23% in state voting intention and threatening to win something like 15 seats at the next state election.  A lot has happened in the few months since.  In the Western Australian state election, both the party itself and the Liberals' preference deal with it got found out in the heat of the campaign. What benefit on preferences accrued from the deal was drowned out by its distraction factor and damage to primary vote support for all involved.

As One Nation 2.0 comes under further scrutiny, it is under attack on two major fronts.  Firstly there's the suggestion that the party is simply corrupt, as seen in the current scandals surrounding the undeclared provision of a plane by a property developer and the recording of a meeting in which James Ashby seems to have seriously suggested a blatant electoral expenses rort.  Secondly, the party sends mixed messages about whether it is a purist party of revolt against existing politics, or an active inside player that wants to supplant the Nationals on the Coalition side.  This is making it harder for it to take votes away from Labor.