Attitudinal Polling

 Preferred Prime Minister

Aggregated Attitudinal Polling

I am now applying the same Bayesian aggregation techniques I use to the opinion polling. I wrote extensively about those techniques here. The results are as follows:

Albanese - preferred leader

Mid-March 2025 Update

Since Donald Trump was sworn in as the President of the United States of America, the Australian polls have been trending away from the Coalition. Now Labor is is ahead on all of my aggregation models of the two-party preferred vote. If an election was held now, the sizeable "third party" vote would see either Labor or the Coalition form minority government. 

Poll Update No. 2

The release of Newspoll in today's Australian caught me a little by surprise, arriving just after I had completed yesterday's aggregation. I was expecting Newspoll to be released next week to coincide with the next Parliamentary sitting week (a typical Newspoll practice). Anyway it's out and it is unchanged on a fortnight ago (50/50). Dropping the result into the aggregation yields a national two-party preferred voting estimate of 52.3 per cent for the Coalition and 47.7 per cent for Labor.

It is worth noting that we are tracking the new Newspoll as being 1.3 percentage points biased towards Labor (in comparison with the other opinion polls, and assuming the house effects of all polling houses sum to zero). Much of that house-effect bias has been evident in the poll results since the elevation of Malcolm Turnbull (where Newspoll-2 has been consistently towards the bottom of the pile).

Turning to the primary voting intention model, again assuming that house effects sum to zero, we can see the following.

The other thing of note in today's Newspoll is the continuing decline in the attitudinal polling for Malcolm Turnbull. Let's start with the raw data before moving the attitudinal aggregation. Of note in the negative PM polling, whereas the former Newspoll tracked closely to the other pollsters, the new Newspoll is significantly more negative than its competitors.

Moving to the comparative results for both the Prime Minister and the Leader of the Opposition, we can see a small improvement in the net-happiness position of the Leader of the Opposition, a more significant decline for the Prime Minister, in the context where the Prime Minister is still well ahead overall.

Technical information on the polling aggregation process can be found here.

Off the boil

There have been three key polls since the start of February. All suggest the public has cooled on Turnbull government; although there is some disagreement on the extent of that cooling.

• The Morgan poll of 30 January to 7 February had the government on 52.5; down from 56 in early December last year (using preference distributions from the last election).
• The ReachTEL poll of 11 February has the government on 54; down from 55 in the third week of January (and late November last year).
• The Ipsos poll of 11 to 13 February had the government on 52; down from 56 in mid November last year.

Collectively, this is showing up as a post-Christmas decline in Coalition two-party preferred (TPP) voting intention in my aggregation models.

Across all the models I run, the results are.

Update

Turning to the primary votes:

Like Kevin Bonham, I have some doubts about the high end Green vote results from some polling houses.

On the attitudinal front, looking at how "happy" the punters are with the performance of the Prime Minister and the Leader of the Opposition, we can see some changes.

Aggregated polling chart bonanza

The headline for today's Newspoll is unchanged on the previous fortnight: 53 to 47 per cent two-party preferred in the Coalition's favour. The big change today was in the attitudinal polling, with both leaders taking a hit.

Malcolm Turnbull: Satisfied 52 (-8), Dissatisfied 30 (+8)
Bill Shorten: Satisfied 23 (-3), Dissatisfied 61 (+4)

The Bayesian aggregation has flat-lined with this latest data point from Newspoll. We are estimating that the Coalition has 54.5 per cent of the two-party preferred vote. 

Across all of our models, we have similar message of plateauing in the TPP support levels for the Coalition.

In terms of the primary votes, our estimates (assuming that house effects across pollsters sum to zero) are as follows. Both the Coalition and Labor have flat-lined. The Greens are much as they have been since Turnbull's ascension (about 1.5 points down than where they were in the latter Abbott months).

The Other model above includes the Palmer United Party. Given Clive Palmer's recent financial troubles, a quick look at the stand-alone Palmer model follows.The "Beta" in the title of this chart is a reference to the beta-distribution, which the model uses.

At the height of its influence, Palmer was more than half of the Other party vote. Now, at 0.5 per cent of the primary vote share, my guess is that the Palmer United Party would not win a seat in either House at the next Election, should these polling figures persist.

Moving to the aggregated attitudinal polling.

Attitudinals

I have not looked at the attitudinal polling for some time. But before we do that, let's catch up on the impact of the latest ReachTEL poll, which came in at 53 to 47 in the Coalition's favour. The aggregation now stands at 52.8 per cent for the Coalition.

As with my other models, I have introduced a discontinuity into the attitudinal polling models I use for data fusion/aggregation. I applied the discontinuity to both the Coalition and Labor series. First, however, let's look at the raw poll results. In these charts, we can see a dramatic change in the Coalition's attitudinal polling, and little change in the Labor polling.

And on to the aggregation.

And placing the results from the two Hierarchical Dirichlet Processes side by side, we get.