I’ve updated my Election Forecast with the results of two recently released polls – one from UMR which ended three days ago, and one from Roy Morgan which ended on the seven days ago.
Neither of these polls taken individually offer much interesting new information – they both show a closing of the gap between Labour and National as swing voters start moving towards Jacinda Ardern’s Labour Party.
However, what is interesting is that adding these two new data points has tipped my election model substantially.
It’s designed so that individual polls can’t have considerable impact, but the sheer weight of support now behind Labour has meant that with these two new polls my forecast for Labour seats has sky rocketed from 36 to 44 – with them coming from National, NZ First and the Greens.
On these numbers, Jacinda Ardern could form a government with the backing of NZ First and the Greens, and Bill English could form a five-headed hydra of a government with ACT, the Maori Party, United Future AND NZ First.
I would be very worried if I was a National back bencher.
I’ve updated my Election Forecast with the results of today’s Colmar Brunton poll. It’s good news for Labour, and bad news for National and the Greens.
You may have noticed that Colmar Brunton have also done an electorate-level poll in Ohariu which puts United Future’s Peter Dunne 14 points behind Labour’s Greg O’Connor. It’s only one poll with a small sample, but it does not surprise me. If there is any further polling in that seat showing similar results, I’m going to update my forecast to give the seat to Labour, meaning United Future and their over-hang seat will be gone from Parliament.
I’ve made two changes to my Election Forecast.
Firstly, I’ve managed to import all the UMR polling data that has been released into the public domain, going back to January this year (though polls older than 90 days will have no impact on the forecast). Given they are polling at least fortnightly I’m really hoping their results continue to be released.
Note that UMR polls don’t release numbers for ACT, Maori Party, United Future or any other minor parties.
I’ve also fixed a bug that was impacting the weightings. The impact of this will be that the forecast will be more heavily impacted by newer, bigger polls. Older and smaller polls won’t have as much of a factor in the result. While it wasn’t my intention, this means the forecast will start to show the impacts of the Jacinda Ardern affect sooner.
Bring on more polls!
I’ve updated my Election Forecast with the results of today’s astonishing Newshub / Reid Research poll.
Because of the nature of my forecast, polls as old as 90 days will factor into the result. Which means a significant sudden changes won’t be as noticable as they are in raw numbers.
So while Labour is up 9% and Jacinda’s preferred PM ratings will have Bill English very worried, my forecast is very conservative and only shows one seat changing hands from National to Labour (which is still a very good movement).
As the campaign progresses and polling becomes more regular I may look at doing a version of my forecast with a much shorter half-life, so giving significantly more importance to more recent polls.
Let’s do this.
I’ve updated my Election Forecast with the results of today’s Newshub / Reid Research poll. It changes the party vote results a little bit, but not enough to change the projected seats.
54 days to go.
One News have released the latest Colmar Brunton poll, to be frank it’s a terrible result for Labour. Astonishingly, Andrew Little has even admitted that he has considered resigning as leader. Funnily enough, we’re now 54 days until the election, one day longer than Mike Moore served as Prime Minister.
Anyway, I’ve updated my election forecast and it holds an important lesson – don’t loose your marbles over one poll result. Despite Labour’s 24% result in today’s Colmar Brunton, they’re still holding at over 28% in the forecast. True, if the previous Roy Morgan poll was in fact a rogue, then the future results will be very different. We’ve got 54 days to wait and see.
I’ve updated my polling forecast with yesterday’s Roy Morgan poll, which offers significant respite for Labour. The poll has Labour and the Greens combined on 44%, one point ahead of National who are on 43%.
This works well for Labour in my forecast. As the most recent poll it is weighted pretty heavily, keeping them very close to the 30% mark. They’d have 35 MPs and assuming no electorates changed hands then Priyanca Radhakrishnan, Jan Tanetti, Willow-Jean Prime, Kiri Allan and Willie Jackson would make it into Parliament off the list.
If Labour’s substantial field effort continues it’s not hard to see how they could chip another couple of percent off National – which could mean game over for Bill English. If you want to see a change of government in NZ: go out and knock on some doors.
I’ve also toyed with the possibility of including yesterday’s leaked UMR poll into my forecast. I’m keen to do so, it being a reliable poll, but the sticking point is the way they don’t have numbers for the minor parties. This means I need to change my code to ensure that they are not included as zero values thus bringing down the weighted averages for those parties. Watch this space.
I’ve updated my polling forecast with the latest Colmar Brunton poll.
NZ First are cementing their place as the 3rd party, and seem to be drawing their support from National and Labour.
Okay, so I messed up.
Basically, I made some mistakes with the code behind my election forecast that adjusted for pollsters’ performance. Thanks to Nigel for the email pointing out my mistake.
So, today there are effectively two updates to the forecast. One is a fundimental change the model I’m using to predict the outcome of the election, and the other is a new data point, yesterday’s Colmar Brunton poll.
The overall result is Greens lose a huge amount of support, and National, Labour and NZ First all gain. To the point where NZ First would eclipse the Greens as the third largest party in Parliament.
On my new numbers the only new Green MPs would be Chloe Swarbrick and Golriz Ghahraman, while Denise Roche and David Clendon would lose their seats.
Marama Fox would lose her seat – the Māori Party would be reduced to a single MP.
Labour would be almost 17 points behind National, but that would be a decent improvement on their crushing defeat under David Cunliffe.
Their new list MPs would be Priyanca Radhakrishnan, Jan Tanetti, Willow-Jean Prime, Kiri Allan, Willie Jackson, Jo Luxton and Liz Craig. Their caucus would be 48.6% female – less than the required 50%.
Apologies for the change in my model, if anyone is interested I can rerun previous predictions with my new performance numbers.
I’ve updated my polling forecast with the latest data from the only NZ public poll released in April so far (seriously, we’re less than 150 days out from a general election and there has only been one poll this month).
We’re finally starting to see some movement in the forecast, although it is still fairly minor. While NZ First are moving up in their party vote, it’s not yet enough to net them another List MP.
The Greens however have just nudged high enough to grab another List MP, at the expense of National.
This won’t have a significant impact. To form Government on the numbers predicted before this poll was released, Bill English would have had to rely on support from NZ First, that does not change).
Can we just have some more polls, please?