Two big changes in the forecast

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.

Finally, some movement in the polling

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?

Labour, Greens and Māori edge up

The latest One News Colmar Brunton poll has been released, I’ve updated my model accordingly.

The updated predicted outcome is exactly the same, in that each party would still get the same number of seats as they did before this poll was released. However, some movement has been observed.

Labour is now up 0.5 per centage points, so they must be very close to getting a 35th seat. Also, both the Greens and Māori Party are also observing an increasing trend in support with both of them increasing 0.4 percentage points and also being close to pickup an additonal seat.

I think this result shows the value in a model like this – significant new movement will still be observed, but will only end up showing in the results if it eventually forms part of a trend. In essence, we’re doing what we can to nullify “rogue polls”.

2017 Election Forecast released

There are few things that annoy me more than how blogs and Twitter light up after the release of a single political poll.

Pundits will make the huge inferences from statistically insignificant changes, or attribute meaning to an event that occurred after polling finished.

Today I’m proud to release something I’ve been working on for a while, a forecast model for the 2017 New Zealand General Election. It is a mathematical model for analysing polling and determining what Parliament would look like if an election were held today.

Check it out here or via the permalink at the menu on the top of this page.

It takes all available public polling, adjusts for historical data (for instance, known bias’ that individual pollsters have), produces a weighted average based on recency and sample size.

It then produces an estimate of each party’s seat count in the Parliament.

No doubt people will have a ton of questions, hopefully the following will answer them. If you have any further questions, or ideas or suggestions, please either leave them on here, or email me directly on

Lastly, my thanks to the many people on both sides of the Tasman (you know who you are) who have helped me with the coding, maths, and design. Hopefully you’ll find it useful!


Continue reading “2017 Election Forecast released”

The Māori seats

One of the pecularities of MMP is that because of the proportional representation provided by the party vote, there is virtually no electoral benefit to winning electorate seats (there are other political benefits, which I’ve touched on previously). So even though it looks like a few seats like Napier and Christchurch Central might come down to the wire, the outcome isn’t going to change who forms government.

The one exception to that is of course parties that use the “coat-tailing” rule – that is, they get less than 5% of the party vote but still get an electorate MP and possibly some list MPs due to winning an electorate seat.

Given the survival of the Māori and Internet Mana parties both rely on winning a Māori electorate seat (as they are both polling consistently below 5%), these seven seats can actually have a very important impact on the makeup of Parliament.

One of the other unique things about the Maori seats is that they are the only electorate seats that regularly get polled. Māori TV have commissioned a series of polls from Reid Research (and TVNZ’s Marae used to also poll). I’ve compiled this years poll results, plus the results from the 2011 election and the 2011 poll results (where I can find them – if anyone has any of the missing numbers please send them through!).

It’s worth taking these results with a grain of salt – the sample sizes are very small (normally 400) and that, combined with poor turnout in the Māori seats make for lots of inaccuracies.

That said, today’s Te Tai Tokerau poll is the tightest yet – with Hone Harawira polling only one point ahead of Labour’s Kelvin Davis. If Kelvin manages to win the seat (and a good turnout operation could certainly help close that gap), then the Hone Harawira/Kim Dotcom farce is over.

Interesting times indeed.

Note: All numbers are candidate, not party vote.

Electorate Candidate 2011 poll 2011 result 2014 poll
Te Tai Tokerau Labour 35 35 37
Māori Party 20 16 9
Mana 42 41 38
Tāmaki Makaurau Labour 23 35 27
Māori Party 58 40 28
Mana 14 16 14
Greens 3 8 7
Waiariki Labour 22 25 17
Māori Party 56 43 50
Mana 22 32 21
Greens 2
Hauraki-Waikato Labour ? 54 57
Māori Party ? 16 14
Mana ? 21 10.4
Ikaroa Rāwhiti Labour ? 41 37
Māori Party ? 20 18
Mana ? 26 21
Greens ? 11 6
Te Tai Hauāuru Labour ? 30 29
Māori Party ? 48 32
Mana ? 9 10
Greens ? 11 11
Te Tai Tonga Labour 35 41 48
Māori Party 46 32 17
Mana 9 8 9
Greens 10 15 9

Good news for Bill Shorten


Unlike the recent volatility we’ve been seeing in the polls in New Zealand (and I highly recommend Rob Salmond’s piece on the latest Herald poll), here in Australia we’re seeing a very strong trend emerging, with the Labor opposition under Bill Shorten rapidly taking over from the Government in popularity stakes. This morning’s Age reports

In a double blow to the Prime Minister, it found the only honeymoon is actually being enjoyed by his direct opponent, Opposition Leader, Bill Shorten.

In fact, Mr Shorten’s personal approval continues to climb with fully two-thirds of voters viewing his performance as either satisfactory (41.5%) good (15.9%) or very good (9.2%).

The ReachTEL/Seven News survey of more than 3500 voters was taken on Sunday afternoon, the eve of the 100-day milestone.

It confirmed the findings of the most recent Fairfax-Nielsen and Newspoll surveys revealing that Mr Shorten’s ALP Opposition already leads by 4 percentage points at 52/48 over the Coalition.

Even on primary votes, Labor is virtually level pegging with the combined Liberal and Nationals parties at 40.4 per cent to the Coalition on 41.4.

Bad news for Colin Craig

Despite having endless media coverage since Louisa Wall’s marriage equality members bill was drawn a few weeks ago, the latest Roy Morgan poll has bad news for Colin Craig.

His Conservative Party have dropped 1.5%, down to a total of 1.5%.

He’ll be deeply disappointed by this result. I’ve heard many people predict that Louisa’s bill might just be the catalyst that Colin Craig needs to get into Parliament, but he simply doesn’t seem to be getting any traction.

Also, from Gary Morgan, on the result of the poll:

A potential Labour/Greens alliance (46%, up 5%) now holds a significant advantage over National (44%) and means if a New Zealand Election were held now it would be ‘too close to call’ and depend on the voting results of minor parties and whether they crossed the 5% threshold to win list seats.

Good trends

As you may have noticed, Labour have been doing rather well in recent polls. Tony Milne has written a useful piece pointing out the trend that is emerging, which he has since updated to cover last week’s One News poll, and this evening’s 3 News poll.

(Side point: tonight’s poll has National on 45.8% and John Key’s personal popularity plunging to 40.5% – not good for Mr Key)

Of course, I’m quite satisfied with how this trend is emerging. There is one minor issue though which hasn’t had much (if any?) coverage.

Both Tariana Turia and Pita Sharples are on record saying that they won’t contest the next election. Fair enough, and all the best to them.

This does however create problems for pollsters who traditionally calculate how many seats there would be in Parliament by assuming the number of electorate seats each party holds will stay static, and then extrapolating their poll results out for the party vote.

In a situation where two electorate MPs are going to retire, this does create an interesting situation.

Being the partisan hack I am, I re-ran the numbers from tonight’s poll, using the scenario whereby Turia and Sharples retire in 2014 and Labour retakes those electorate seats. I realise that is a very subjective assumption, and might be something I write about in future, and I certainly hope Morgan Godfery writes about.

Anyway. Here are the numbers according to tonight’s 3 News poll:

Party Poll % Electorate Seats Total Seats
ACT 0.5 1 1
Greens 14.4 0 18
Labour 33.2 22 42
Mana 0.3 1 1
Maori 1.4 3 3
National 45.8 42 57
United Future 0 1 1

As Duncan Garner pointed out and David Farrar was happy to re-iterate, on these numbers, the Maori Party would have the balance of power. National + ACT + UF + Maori would have 63 seats (the exact number needed to govern in a 123 seat Parliament), on the other side, Labour + Greens + Maori would also have 63 seats, and they could possibly also get Hone on side. We could speculate until the cows come home who would get to form the government, but lets take another look, assuming that Labour pick up Tamaki Makaurau and Te Tai Hauauru.

Party Poll % Electorate Seats Total Seats
ACT 0.5 1 1
Greens 14.4 0 18
Labour 33.2 24 42
Mana 0.3 1 1
Maori 1.4 1 2
National 45.8 42 57
United Future 0 1 1

With the Maori Party reduced to one electorate seat, their 1.4% of the party vote is just enough for them to bring in a list MP (I’d assume that Te Ururoa Flavell would be joined by Rahui Katene). Labour’s total number of seats of course does not change, but the size of Parliament reduces by one seat, meaning you could pass a budget with 62 votes rather than 63.

This dramatically changes things. National + ACT + UF + Maori would now only muster 61 seats, and simply would not be able to form a government. Labour + Green + Maori would have their requisite 62 seats, and as before could take that to 63.

It does show quite clearly just how close things are at the moment. If National lose just a few more percentage points to Labour, then John Key would have absolutely no way of forming a government.

One final thing: never write Winston off.