Plus the Veterans’ Support Bill
Although this Bill is better than the !954(?) Act, can we at least recognize the efforts these people have made without insisting they be disabled to receive full recognition. Their time left here is short and to…

Not to mention that apparently Bridges has returned from an alternate reality where Russel Norman has been a Minister in Government!

Just how much time does he spend there?

Philip K Dick eat yer heart out...

Plus I only saw one article in Herald about the PM's view on it. He thinks its fine of course.TV3 seem to be covering it. Weird.

Treasury, then

It's as if a bunch of…

Going into caucus this morning Key said: "He's a colourful character. We've enjoyed having him in caucus but it makes sense for him at this time to step down."
Pushed? Much?

That does make sense, since until an election they don't have any information upon which to judge their house bias for any methodological change. I'd hope they'd want to stick to a methodology throughout…

No, not consistent over a long time period (multiple election cycles). The polling firms are always trying to improve their methods, so we wouldn't expect them to be.

They look reasonable consistent over shorter periods (an election…

Golden Bay – Mon April 14
Nelson – Tues April 15
(This is The 2013 Roger Award Presentation Event – not the talk)…

that’s what I’ve seen mentioned.

Just a partially formed thought:

Could “other stuff” include a different model which postulates that people move in or out of main party support (lumped together – although not in voter’s minds!) versus minor party support (lumped together) depending on what they…

I might have missed discussion of this, but are there any references…

Turns out that when you take this into account, the movement of Labour/National is unsurprising, but some of the others are (e.g. Green/National is higher than you'd expect). If the…

Not really, I don't have a lot in common with Winston or NZF and I think some of their views are a little extreme, but I'm starting to see how extreme gets one noticed in Politics and that in itself seems to be a strategy.
What I…

It's hard to be sure if that story is true. Greens are not strongly correlated to Labour, but they are to National, negatively.

I see a bunch of possible explanations:
1. The…

Labour and the Greens approaching him and negotiating in good faith, I'd think. It's the only thing that would convince me that it would be a good idea. Essentially they give a blueprint of their bottom line…

They are correlated, but that actually makes their voters different to each other. When the vote of one goes up, so does the vote of the other – that's because their vote reflects either National or Labour weakness,…

Interesting idea Sofie.

I would never had thought to write to Winston Peters (I’m not what you would call his core constituency).

He and I might not share many common values, but we do agree on the detrimental influence foreign investment is…

As I facilitated the donation in question, I can report – for the first time – that Peters was in fact telling the strict truth.

Bingo. I’d call it a longitudinal study, market research companies call…

So get on ya horse and tell him. Or, by your lovely gravatar, maybe not the horse. Their Website is easy to find and email is even easier. Power to the peoples. We are not sheeples!

He says he is not the Party. He is the leader of NZFirst and would like others to treat him as that rather than the only one in the Party. He stressed that he…

The updated one has constant scales (same patterns, just a bit easier to see the impact).…

Winston can be a minister, in or out of cabinet, in any post that does not affect…

I doubt he likes Key, but that would make it all the sweeter to have him on his knees, begging for forgiveness. He could also be in…

Good point. Or there could be movements in and out of non-voting between choices. I can imagine that's not that uncommon. You stop being a tribal Labour voter, but have…

@dpfdpf Apr 2 "I have all the public poll data back to 1974. I should point out I didn't start collecting them in 1974 though, as I was just 7 :-)"

Some are having…

In reality what might be happening is…

I suspect that various folk that collect polls (e.g.…

What this is showing in the middle (the black smudgy bit) is the number of seats (scales are seats) that the left or right achieve in simulated elections. i.e. it shows that as the number of seats on the left increase, the seats…

Now I'm hitting total guesswork: I think the light blue band is an outright…

I can tell you what they are, but I'm only guessing how to use them. They're scatterplots, each plotting one party against one other party. The dots are individual polls and the x val is one of the parties, the y val…

We're looking for pattern in those, right? To my eye, I see Labour/National negatively correlated. Labour/Green barely correlated. Labour/NZF hardly correlated. National/Green negatively correlated. National/NZF negatively correlated. And then the really strange one: Green/NZF positively correlated.…

I believe the text always appears beneath the attachment. And that you can Edit your post and attach another couple of images in the same comment.

Peter, I accidentally left my font on the free internet available "lovedbytheking" font so when I started making the diagram in Inkscape it was the…

If we look back at the polls (rather than use the output from the simulator from poll of polls, as we know they’re independent with the exception of National due to the way it predicts) then…

That being said the current polls don't give National a 99.5% chance of governing – the…

I ask because it obviously isn't going to be held now, so…

I think you've gone wrong somewhere in that the labour clear win chance was 0.005. If Winston is absolutely certain to go with National then when you combine the National clear win and…

In the scenario analysis that I've done from the poll of polls, it indicates that the Nats have a 23% chance of going it alone* without Winston…

That would be an awesome conditional probability to be able to get. Then we could work out the overall probability of National-led govt.

Just for fun since I'm swotting this stuff right now:

P(N) = P(N|W)P(W)…

Answers from those who gave their party vote to NZF in 2011 (n=230): Labour 73%, National 27%

And on the subject of graphs…how did you put your…

It is either a Labour or National Government- it is defined by the difference between the two blocks (sans Winston) is not greater than the seats NZF have. It makes no judgement about what Winton would…

I'd like to think that with NZ Firsts state assets policy alone, that they can find room to compromise with Labour and Greens to change the govt and or a mix with Mana and Internet if…

Labour-led meaning "not requiring (but possibly including) Winston" here? I ask because "Winston decides" surely includes an unknown chance of Labour led government?

We'll see on…

With Colmar Brunton the fixed result…

http://www.statschat.org.nz/2014/04/05/oh-what-a-difference-a-bit-of-formatting-makes/

I liked your graph with ranges Sacha. You get my vote (and assistance if you want it). I'm way behind in my R and nice graphs skills, but I've always…

FiveThirtyEight's prediction that the Republicans will take the Senate in 2014 really shows how emphasising certain elements of the status quo can put you in a conservative, even defensive, mindset.

Given that positive change is a definitional goal of progressive politics, persuasion has to…

Thank you Russell. I want someone to post an expert analysis of every poll, and for other people to refer to it. And for journalists to understand poll analysis. Discussion is good.

I think unless something major happens between now and the election once again Winston will be deciding…

Maybe closer to the election there could be a weekly post with updated graphs as David says:
Well, we can probably get it making pretty graphs of the result for inclusion in posts…

I would start making other assumptions in that case. Firstly, that National would take a hit of a few percent, made disproportionately from young women and ‘aspirational liberals’, and that the Conservative Party would gain votes, some…

What happens if you plug in CCCP with an electorate and whatever their current share is of the party vote?

or must have code :)

This is a way to explain it.

I suspect it’s actually more that most New Zealanders have been conditioned by the polls and reportage thereof to believe that…

I suspect it's actually more that most New Zealanders have been conditioned by the polls and reportage thereof to believe that National's victory on the day is assured.

Well, we can probably get it making pretty graphs of the result for inclusion in posts about election things. Beyond that I can't think of much as it is really just reinterpreting the…

Most New Zealanders want Labour to form a coalition government

But most New Zealanders expect Labour to do something so utterly compellingly stupid before the election that they will fail to win

Quite happy to help if for any reason things are difficult (95% of the time it's as easy as pie, but sometimes it isn't).

You do indeed need to install something- the language R, from
http://cran.r-project.org
Where in theory you could open this as a source file and run it. However if dead keen to give it a go, your life would probably be much easier if…

Go to http://www.r-project.org/‎ and install R. This is pretty easy, and can be done in about ten to fifteen minutes without specialist knowledge. I'd also go…

The other figures show that National supporters are very confident of their side winning, Labour and Greens supporters are much less so. Bolstering those…

__"The survey starkly illustrates the difference between perceptions over which party might win and what electors would prefer,…

I think that's called poll jumping.

Or should that be OneTwentyOne in the NZ context?

The Libz definitely won't. They disbanded and threw in their lot with ACT (or what's left of it).

I'm an electoral-vote.com user. It got me through the 2008 election and I like the simplicity of it.

I'd be really interested to know more about how the parties go about trying to persuade voters to change their minds.

They only get lumped into "other" when they don't have an electorate seat and they're < 1%. ALCP, Libz, etc, they're never going to get enough votes to matter. UF, Act, Mana, they only break the rule because they have sitting MPs so every votes for them does count.

Since I was going to add it to github, but you have done a lot of work on making it actually work, I was going to mark the project…

We could call it FiveThirtyEight.co.nz ...

I think as long as you emphasise and discuss the mean (or effect size) and the CI rather than the P-value you're doing fine, but agreed in many contexts the Bayes approach tends to be more natural.

It'd be great…

I suspect (know) that it would (seriously) annoy quite a few people to not have ‘their party’ in the graph – I get calls/emails from people expressing such for parties that are grouped in ‘other’. They feel as though we are disadvantaging their party by…

I'd have thought there'd be at least some interest in a well-thought out election polling blog. It would involve analysing the data provided by the main news organisations, providing a rolling average, commenting on broad trends, critiquing poor coverage and providing insight…

I've taken the liberty of updating it to…

Also, there is a time factor. The methodological…

Minor correction to the above post- with the Colmar results, in…

Labour/ Greens (45%) regain lead over National (43%) for first time since January

Quite a lot of nil or marginal change, but National dipping 2.5% and NZ First rising 2% and the Conservatives 1% might be significant.

Labour rose but Lab/Green vote fell slightly.

Internet Party in…

It's not the polls which are flawed. They are what they are. It is the analysis and…

Thanks for that. A link lets everybody else see it too, not just me with my shelf of reference books. Much obliged.

@ Peter Calder: yes you are quite right, but it is more subtle (yeah, whatever dude maths geek stuff coming) because at very low or high…

Hi Steve, I've been really enjoying your contribution. This is the reference I use in relation to 1.41(4) in relation to comparing between polls.

I did wonder at the negative 0.1% values.

ta – hence my comment about not having the right tools. :)

You can do…

Why Mr Gower insists on doing them the way he and his peers do frustrates me as…

And it's +/-1.34 at 4.9% which is the example I gave…

I’d only give the new code a bare…

Unfortunately this kind of graphic may be misleading and bogus for the reasons I mentioned before, although that was more in the context of the C-B methodology.

Now let’s consider what is happening with retirement of sitting members. The most dramatic effect is likely to be…

Yeah, if you were going to make this question – and presumably the Orivida one as well – properly robust you'd make it…

Whether it helps to create a definitive yes/no meaning or not, I don't understand the point in asking questions that need such a lead-in to make sense. If regular voters aren't going to have a controlled introduction towards forming an opinion, isn't a poll which does exactly…

There is one thing they could, and should, be doing which is incredibly simple: include the undecided/don't know/wouldn't say vote. Making it disappear isn't "dealing with…

great opportunity for tv to differentiate themselves from print media, you’d think

But TV is not a static medium, you aren't limited to a graph that is fixed. You could have some seats fixed red blue green or purple and some that flick between colours slowly or rapidly depending on uncertainty or something much…

I for one happen to believe that Rebekah Brooks will never be involved in phone hacking again ... .

If Winston polls 4.9% then I would pick NZF to be in, based on how many people I heard last time saying they might throw him a vote to…

To be fair the Survey could have said: " Mr…

I have it at 46% :-)

And yet that is exactly the story New Zealand needs to hear to understand that MMP is actually working as intended and not just being steamrolled by National.

It IS a balanced situation where your vote counts – NOT what is being…

I agree a) that non-response is a far, far bigger issue than non-coverage in telephone surveys, and b) survey reports should include the response rate.

The problem is though, I've seen some very dodgy response rate formulas used in New Zealand by reputable companies. What…

Yes, well illustrated.

It also brings us back to Monday's point about the folly of drawing up virtual houses of Parliament at this point. But that's a hard sell.

The underpants gnomes will not permit it.

who makes those decisions?
and who benefits?

No. They aren't doing any such thing. I explained the whole thing here: http://www.pundit.co.nz/content/one-of-these-things-actually-isnt-quite-like-the-other

As an example, the big to do over Cunliffe’s…

Not much is happening in these polls (statistically). But it never seems to slow down the narratives. This cartoon nails it:

https://xkcd.com/904/

Hover over that and it adds "and also all financial analysis..." and they should add "and all political polls when the methodology section gives margins of…

And of course Russell had to break that embargo — happy birthday PG.

Correct, but I think you could present "which combinations of parties could form government" reasonably enough. A Monte Carlo simulation of the seat distribution from the poll…

That's possibly where the likes of Campbell live could do some legwork to help themselves Patrick and the public have a better understanding."We, the public are not in Kindergarten…

Worth a crack. Data source for one of these recent polls, anybody?

Mainly wanting to make the point that providing seat ranges would require many more assumptions than just 'all electorate seats are held' – the potential number of party seat…

I actually don't think you could do it that easily, because seats are distributed proportionally to parties over 5% or with electorate seats. For example if NZ First's range put them under OR over the 5% threshold, that would influence how all the other seats are distributed, so…

"Our poll shows National is (highly) likely to have 56 to 58 MPs."

Not hard.

Easy enough to show on a graph. Most people don't have trouble with a range if it's shown visually.

Surely a link to a pdf wouldn't be too difficult?