Public Address | Cafe | Hard News: Where are all the polls at?

izogi

Tue, 26 Sept 2017 12:44:23 +1300

I think the Greens need to care what the media report

Yes and no. I'm not a Green Party insider, but especially after Kennedy Graham and David Clendon resigned, it seems to me like what happened to Metiria Turei went deeper than just media. For a moment that came from…

simon g

Tue, 26 Sept 2017 11:29:18 +1300

I think the Greens need to care what the media report, and since the standard "analysis" is usually to get some Nat-aligned commentator to give reckons (because free and easy) then, yes.

If that didn't matter then Metiria Turei would still be co-leader. The Greens can certainly say "don't care",…

linger

Tue, 26 Sept 2017 11:10:58 +1300

Do the Greens really need to care what National supporters think?
The only kind of deal the Greens could accept would be something that addresses everything National has failed to do on the environment or on social issues in the past 9 years. Not vague promises of studies for future…

izogi

Tue, 26 Sept 2017 10:57:54 +1300

If National offers a deal then I think it'd be largely so it can claim to its supporters that it tried, and that it was the Greens who were being unreasonable, the Greens' fault that NZ First is inflicted upon everyone, and yadiyadiyada.

simon g

Tue, 26 Sept 2017 10:57:40 +1300

But that's the narrative National shills want – we're so reasonable, it's only Shaw and his stubborn lefties who are stopping a green dream. It's BS, and he plays into it.

Call their bluff, I say. Do it with the same concern-trolling that they're doing to the Greens. ("I believe…

linger

Tue, 26 Sept 2017 10:17:48 +1300

Yeh, nah. National might be desperate enough to offer a deal, but Shaw is very clearly minded to suggest they investigate the invigorating possibilities of a hilltop ramble.

simon g

Tue, 26 Sept 2017 09:56:56 +1300

For balance – or to fill up a slow day while we wait for specials – here is the most detailed and sort-of plausible list of National-Green policies that I've seen so far, if the impossible coalition happened. Lance says that he voted/supports Greens, so it's not just Nats playing…

Bart Janssen

Tue, 26 Sept 2017 09:31:05 +1300

One of the weirdest things about the discussions of who will form a coalition with whom has been the idea that it's a bad thing for one party to have to compromise.

But compromise is good, we teach our kids to compromise to reach a consensus solution to a problem,…

David Bulog

Tue, 26 Sept 2017 07:17:59 +1300

News hub Reid Research poll *reputation intact* .Hats off to them for picking up on the early trends.

izogi

Mon, 25 Sept 2017 20:53:18 +1300

Isn't this whole perceived Winston dilemma a hangover from FPP days? As a population, we're still in a collective mindset of wanting big parties to run things, but that also means that we end up with giant blobs of parties that aren't allowed to mix.

If this is what those…

Dennis Frank

Mon, 25 Sept 2017 20:49:12 +1300

This is a great re-read;

http://www.nzfirst.org.nz/rt_hon_winston_peters_budget_speech_2017

Taken at face value it provides reasons to assume he'll be favourable to the Labour/Greens option. May seem a tad naive to assume he means what he says, but I'm inclined to regardless. I suspect he's now primarily motivated by the need to create…

Neil

Mon, 25 Sept 2017 19:07:40 +1300

The intricacies of Common Knowledge.

Everyone knows that everyone knows The Greens won't go with National.

Everyone knows that no one knows what Peters will do.

linger

Mon, 25 Sept 2017 18:52:08 +1300

The Greens have so far been fairly adept at maintaining their own independent voice (and James’ communique clearly shows they do recognise the potential problems). I don’t know if it’s “the electorate” punishing the minor parties though, so much as that the major parties still haven’t fully accepted that they…

Neil

Mon, 25 Sept 2017 17:51:15 +1300

I agree the Greens have a special character. But that does mean they lack leverage.

It seems to me there's an element of the electorate punishing small parties for trying to do the achievable and not hang out for the unlikely.

The Maori Party had a number of impressive achievements…

linger

Mon, 25 Sept 2017 17:36:36 +1300

That's taking a shortsighted view. The Greens have a political identity that can survive individual members' careers. Winston personally has a strong political identity, but NZF, not so much. You've previously mentioned the upcoming succession problem: Shane isn't Winston.

linger

Mon, 25 Sept 2017 17:28:28 +1300

Or in other words, any National deal's a killer, electorate gift or no.

Neil

Mon, 25 Sept 2017 17:27:00 +1300

The Greens didn't need to align with National in order to recently bring them to the point of extinction.

That was with an MOU with Labour.

With MMP it's just that smaller parties have been at the mercy of the larger ones.

Although Peters has been with both National and…

Paul Campbell

Mon, 25 Sept 2017 17:20:21 +1300

James Shaw has made this release to members:

https://pbs.twimg.com/media/DKhga5mUIAIiJjX.jpg

linger

Mon, 25 Sept 2017 16:41:06 +1300

True that; I could countenance voting for 1970s Labour.
(And you can draw a fairly direct line from 1980s National to NZF, in fact that’s probably what most NZF voters think they’re actually supporting.)

tussock

Mon, 25 Sept 2017 16:01:26 +1300

The National party ain't much like it was in the 70's either, and Labour even further away. They just never changed their names, even though a few in National used to fly other colours.

simon g

Mon, 25 Sept 2017 15:46:36 +1300

Meanwhile we can enjoy the Blue-Green coalition fantasies being circulated on social media. Possible motivations include blatant mischief-making, genuine fear of Winston destroying the Nats yet again, the prospect of Ron Mark ("Go back to Korea!") sitting next to Melissa Lee with 3 years of the government saying "we're not…

linger

Mon, 25 Sept 2017 13:32:43 +1300

Yeah, kind of, via the somewhat misnamed Alliance. And it has continued to evolve since. As of last term there was as much ex-Macgillicuddys as ex-Values in the Green genome.
Actually, not sure steady genetic inheritance is the best image for it: the progress of the core personnel and ideas…

Ian Dalziel

Mon, 25 Sept 2017 13:24:18 +1300

Values (1972-1990) never won a single seat in any election. Their best showing was in 1975
Didn't they metamorphose into The Greens?
That has to be a plus!

simon g

Mon, 25 Sept 2017 13:20:55 +1300

Even If Labour and the Greens had been given a mandate to govern without NZ first, that’s not change. That’s more or less the same government we already had, but with much more capable professionalism.

Steven, that really isn't true. A Labour-Green government would have been (will be next time?)…

izogi

Mon, 25 Sept 2017 11:17:18 +1300

The reactions to the review in this article really highlight that attitude.

Labour "backs the changes", but only makes a deal of getting rid of coat-tailing (something that National's been taking lots of advantage of lately to foster coalition partners).

National opposes lowering the threshold (no reason given).

ACT opposes…

Bart Janssen

Mon, 25 Sept 2017 10:43:44 +1300

If he threshold was 1% more people would vote for those minor parties BECAUSE their vote would count.

Same applies to a transferable vote system.

But it won't happen because those votes would come from National and Labour and they won't allow such a change to be made.

izogi

Mon, 25 Sept 2017 10:36:33 +1300

So real outsiders breaking in: none. Have I missed any?

The 5% threshold seems, to me, like a statement that we don't want to risk any weirdos whom we don't know getting in. Only the people entitled enough to be there, thanks.

The likes of TOP and Conservative have demonstrated…

Joe Wylie

Mon, 25 Sept 2017 08:54:32 +1300

…and Epsom – what’s wrong with you people?
(is there something in the water?)

They where told how to vote.

True, though for whatever it might be worth, Barry Humphries in a 1980s interview was moved to mention how he'd been struck by an overwhelming sense of sadness while driving…

linger

Mon, 25 Sept 2017 01:48:09 +1300

Values (1972-1990) never won a single seat in any election. Their best showing was in 1975 (5.2%, which under FPP still got them nothing).

tussock

Mon, 25 Sept 2017 01:31:54 +1300

Mana party got in under a sitting Māori party MP, though he won a by-election first when he switched to Mana.

Greens had sitting MPs from the Alliance, and won a seat their first time on their own, though only just on special votes. They also trace back to the…

linger

Mon, 25 Sept 2017 01:06:27 +1300

Social Democrats pre-MMP, maybe. The Bob Jones vanity project got to double-digit support back in the day, too, but again, rich man's hobby, and guess which two digits I'm raising to that.
Anybody starting without a representative already sitting has a huge disadvantage. Maybe someone with a massive media profile…

simon g

Sun, 24 Sept 2017 21:53:34 +1300

Too true. History of minor parties getting into Parliament under MMP (some predated the change of voting system), and how they first got there:

NZF – sitting Nat MP. Alliance – sitting Lab MP. United(Future) – sitting Nat and Lab MPs. ACT – recycled Lab MP (Prebble) who was quasi-gifted…

linger

Sun, 24 Sept 2017 21:37:29 +1300

For all practical purposes, unless the threshold is reduced to <1%, that better option would have to involve a locally popular sitting electorate MP forming their own party. Any takers?

simon g

Sun, 24 Sept 2017 21:24:04 +1300

I think the Metiria story makes any broader conclusions about the Greens pretty shaky, really. It was a double self-inflicted wound (the original story, but more so, weeks of the not resigning/then resigning follow-up, which was more or less the worst way to handle it).

More generally, we've had a…

Caleb D'Anvers

Sun, 24 Sept 2017 21:06:17 +1300

What I'm seeing suggests that the Greens are in fact electoral poison with the non-Left bloc. "Centrists" might consider voting for a right-dominated Labour Party if the other options have lost all credibility, but they won't countenance voting for a Labour Party that would go into any form of coalition…

Katharine Moody

Sun, 24 Sept 2017 20:41:53 +1300

If Winston really sides with those who aren’t getting the trickle-down, since he now has the opportunity to help shape a genuinely-progressive new government his negotiating strategy ought to prioritise that design.

This is a great re-read;

http://www.nzfirst.org.nz/rt_hon_winston_peters_budget_speech_2017

Katharine Moody

Sun, 24 Sept 2017 20:31:26 +1300

I guess there are a million ways to frame the outcome, but to me there are just a heap of people don’t want things to change.

And they very much in the main live in Auckland;

https://www.stuff.co.nz/national/politics/97191224/election-2017-auckland-tips-the-balance-in-nationals-favour

Despite all the talk of unaffordable housing, unchecked immigration and gridlocked roads, their…

Neil

Sun, 24 Sept 2017 20:10:40 +1300

Peters will have plenty of considerations but perhaps an important one will be setting up heir apparent Shane Jones.

Thinking that through I'm not sure which major party is favoured.

linger

Sun, 24 Sept 2017 20:00:29 +1300

Nah, just a less than brilliant opposition (with a surge coming too little, too late).
Want to look back at the "lessons to be learned for Labour" comments after the 2014 election? Things like:
(i) Labour should adopt a more collegial leadership structure, with co-leaders.
(ii) Labour should visibly, consistently,…

Neil

Sun, 24 Sept 2017 19:35:43 +1300

If National do indeed get a 4th term then Key's resignation will turn out to be one of the more brilliant manoeuvres in NZ politics.

simon g

Sun, 24 Sept 2017 17:15:57 +1300

A reminder of the Herald poll on page 4 of this thread.

Relevant today as misinformation and misunderstanding of MMP abounds. Don't read Stuff comments – or a bunch of other outlets – if you'd like to believe that NZ voters understand their own democracy, and the system they chose in…

Trevor Nicholls

Sun, 24 Sept 2017 16:37:11 +1300

The congenital inability of leftists to comprehend that swing-voters are centrists who control the outcome of our elections is sociopathic.

Would you like some fish with that chip on your shoulder?

linger

Sun, 24 Sept 2017 11:37:01 +1300

1.2 millionReckon they multiplied the % of votes for National by the total number of registered voters, rather than the number of actual voters. Muppets.

Dennis Frank

Sun, 24 Sept 2017 11:12:38 +1300

We're likely to get our first ever refugee into parliament due to the usual boost to the Greens from special votes. Golriz is a specialist in human rights law, so will add considerable value. Her bio describes her as Kurdish/Persian (Iranian).

As James Shaw has been pointing out, the three…

Ian Dalziel

Sun, 24 Sept 2017 09:59:01 +1300

I don't understand where the Sunday Star Times gets it's figure of 1.2 million votes for National (or the idea of 'victory'?
New Zealand’s biggest-ever election turnout delivered National’s highest ever vote: 1.2 million. Last night, reports Adam Dudding, was a landslide.
National’s Bill English has blown away the stardust…

izogi

Sun, 24 Sept 2017 08:59:07 +1300

I see Joyce tweeted "I stand by the way we campaigned" – which says it all really – what loathsome lying lowlifes.

I find the tactics disgusting yet cannot help but think it still works. As long as people are content to respond to this stuff, it's always going to…

Ian Dalziel

Sun, 24 Sept 2017 07:57:28 +1300

I see Joyce tweeted "I stand by the way we campaigned" – which says it all really – what loathsome lying lowlifes.

If National was really paying attention to 'the will (and mood) of the people' English would have announced they were seeking to form a government with The Greens,…

izogi

Sun, 24 Sept 2017 05:21:16 +1300

More of the same, I guess, but I’ll be interested to see what’s happened after specials.

It’s a shame they take so long to come in because a government forming deal may well be done and dusted by that time. How does 16% of advanced votes being specials compare with…

tussock

Sun, 24 Sept 2017 00:55:52 +1200

And because there's no better place for it, my tri-annual, stop stealing people's seats and giving them to the big parties, you bastards, post.

First divisor 1.4, no threshold, from the night's results.

National 56 (-2)
Labour 44 (-1)
NZF 9
Greens 7
TOP 3 (+3)
Māori 1 (+1)
ACT…

tussock

Sun, 24 Sept 2017 00:16:44 +1200

Polling averages made it Winston's choice, almost certainly so, and late polls were pretty much on the spot for what he'd be looking at for a choice, give or take the specials (go go magic late enrolment swing!).

Well done the pollsters again. Good old math and sampling doing it's…

Ian Dalziel

Sat, 23 Sept 2017 22:35:11 +1200

Bugger!
(provisionally....)

Joe Wylie

Sat, 23 Sept 2017 12:15:50 +1200

Some problems with Australia's postal yes/no 'referendum'...

The unfailingly excellent David Rowe.

Ian Dalziel

Sat, 23 Sept 2017 10:50:22 +1200

Some problems with Australia's postal yes/no 'referendum'...
https://www.stuff.co.nz/world/australia/97163982/australias-samesex-marriage-survey-corrupted-another-haul-of-votes-dumped

FletcherB

Sat, 23 Sept 2017 09:58:49 +1200

Also, if I were running the process efficiently I’d expect my counting team to report their tallies at the end of each voting day

If you do that, the tallies could get leaked and influence people who haven't voted yet...

I don't like that idea... I don't even like the…

linger

Sat, 23 Sept 2017 09:20:24 +1200

Absolutely not. As of 2pm today we will know (roughly) how many advance votes have been cast but we will not know anything about how they have been cast. Processing the advance votes does start early – but given the number, will not be completed before the final day’s votes…

Dennis Frank

Sat, 23 Sept 2017 08:46:43 +1200

The previous day's advance votes are not tallied until 2pm on polling day – but the actual results are not scrutinized and therefore are not released until after close of polls.

Okay, but I was commenting on the basis of seeing a couple of political reporters telling us that the…

linger

Sat, 23 Sept 2017 00:44:46 +1200

That’s not quite how it’s supposed to work. The previous day's advance votes are not tallied until 2pm on polling day – but the actual results are not scrutinized and therefore are not released until after close of polls. Special votes (including some proportion of the advance votes) take even…

Russell Brown

Fri, 22 Sept 2017 22:38:20 +1200

Kia ora koutou.

Just a reminder that the provisions of the Electoral Act are about to come into force, till 7pm tomorrow, so if you could please confine yourselves to electoral and poll geekery and no indulge in anything referring to the parties contesting the election, still less what you…

Ben Austin

Fri, 22 Sept 2017 21:04:21 +1200

If it's possible to vote in person I usually do, but it's a bit of a hassle to get to the High Commission at present.

izogi

Fri, 22 Sept 2017 18:19:30 +1200

I'd have voted early but, after seeing how many are doing so and the discussions about outdated electoral laws, I've held off. It's occurred that this might be the final election where I get an opportunity to vote on a day when nobody's allowed to scream at me about how…

Sacha

Fri, 22 Sept 2017 15:29:55 +1200

Bernard Hickey reckons the polls might be wrong.

Currently, the two major published polls put National ahead of Labour by eight or nine percentage points, but those polls have assumed that turnout rates among the young will be the same as for previous elections.
...
If the young have voted…

Alfie

Fri, 22 Sept 2017 15:15:34 +1200

due to most traditionalists voting tomorrow

I wouldn't call myself a traditionalist and I was inclined to vote early. The reason I've held off voting until Saturday is because I like being able to drill down in the ElectionNZ site, right down to my local voting booth. For the last…

simon g

Fri, 22 Sept 2017 13:52:47 +1200

I'd say there's almost no chance of Labour/Greens having 62 on election night, and even L/G plus Maori Party is a long shot.

But the real concern is that there will be negotiations based on incomplete numbers, and specials will change the picture (i.e. give the only correct picture) after…

Dennis Frank

Fri, 22 Sept 2017 13:46:11 +1200

If the skewing effect on the polls since advance voting started is real, highly-motivated voters who are quick off the mark will already have been tallied prior to the polls closing tomorrow and the first media reports thereafter will be of their tally.

If they mostly want a change of…

John Farrell

Fri, 22 Sept 2017 08:38:59 +1200

Interesting, Tom. My pick – Labour/Greens 62 seats, National 56, Maori Party 2. No seats for anyone else.

Trevor Nicholls

Thu, 21 Sept 2017 23:29:53 +1200

I am going to make my call – A Labour-Green 62 seat win on the back of a late swing to Labour.

Here's hoping.

Tom Semmens

Thu, 21 Sept 2017 21:14:42 +1200

Politik say they have seen National's internal polling which indicate a 1% lead to the left bloc and softening of the National vote.

My bones tell me the National scare campaign worked right up until Bill English jumped the shark on the whole slaughter the dairy herd thing and the…

linger

Thu, 21 Sept 2017 19:47:43 +1200

Differences of less than the margin of error should not be called a swing.
Basically, we won’t know the result until after Saturday (and that’s all that poll says). Time to stop speculating and start voting if you haven’t already done so.

David Bulog

Thu, 21 Sept 2017 19:01:38 +1200

If TV3 Reid Research Poll sampling is correct
What we are seeing is a new late swing to the minor parties -Greens up 2.2% and NZF up 1.1%
decline for National since last week poll -1.1% , slighter decline for Labour – 0.5%
Greens and NZF are getting some votes…

Trevor Nicholls

Thu, 21 Sept 2017 18:27:51 +1200

Do we know if CB changed their "modelling"? I know they've said they didn't change their "sampling" before their last poll. But if they kept to the same electorate model then there really has been a big shift since the tax bullshit hit the fan, and Reid picked it up…

John Farrell

Thu, 21 Sept 2017 18:19:14 +1200

Nope.

David Bulog

Thu, 21 Sept 2017 17:56:31 +1200

TV3 Reid Research poll *6pm tonight* might show a new late swing**- stay tuned

izogi

Thu, 21 Sept 2017 17:49:39 +1200

For example, if (as we're told) Labour voters are particularly fired up now, then isn't it possible that their keeness means they're voting early in higher numbers than supporters of other parties. Because these early Labour voters would then be excluded from opinion polls, then the polls would record this…

Rob Stowell

Thu, 21 Sept 2017 17:19:42 +1200

“Do you intend voting in the New Zealand general election on Sept 23?”
I was polled by curia last night, and they didn't ask anything of the sort.
And it being Curia – polling privately, I assume, for National's strategists/Stephen Joyce – I lied my face off. 5 or 6…

linger

Thu, 21 Sept 2017 16:04:52 +1200

That might also be asked, but doesn't exclude the advance voters.

Trevor Nicholls

Thu, 21 Sept 2017 16:01:59 +1200

Or even, are you enrolled to vote this year?

linger

Thu, 21 Sept 2017 15:33:58 +1200

If I were writing the initial screening question, it would be something like
“Do you intend voting in the New Zealand general election on Sept 23?”
which excludes at one stroke those who have already voted, and those who won’t be voting at all.
Can anybody who has been polled…

Dennis Frank

Thu, 21 Sept 2017 13:13:52 +1200

early Labour voters would then be excluded from opinion polls, then the polls would record this as a *drop* in Labour support (since the remaining pool of voters available for polling would be skewed disproportionately away from Labour)

Both of you are onto something with this. I bet the polling…

simon g

Thu, 21 Sept 2017 11:18:06 +1200

I would have liked Jacinda to put him on the spot, to counter-attack from left field (sic).

e.g. on the inevitable which-way-Winston questions, she could say:

"As Prime Minister, I want to bring people together, not drive them apart. So I can tell you now: there will be no referendum…

linger

Thu, 21 Sept 2017 10:59:05 +1200

Bill had a reputation for integrityIn a double-Dipton “within the letter of the law we rewrote to make it legal” kind of way. And relative to other National ministers, which sets a low bar for comparison.

David Haywood

Thu, 21 Sept 2017 10:56:32 +1200

I've been wondering along a variant of the same lines as Izogi. With a massive amount of early voting (voters who then, as I understand it, can't legally be polled) wouldn't that have the potential to massively skew the opinion polls if this early voting was inclined disproportionately to one…

Trevor Nicholls

Thu, 21 Sept 2017 10:49:59 +1200

And this is why they lie.

There were at least three blatant lies (all repeated when challenged) in last night's leaders debate: Labour raising income tax (they aren't, and under Bill's logic if the Nats need Winston in government the Nats will be raising income taxes too), Labour's $11.7B fiscal…

Neil

Thu, 21 Sept 2017 10:42:49 +1200

I’m not sure why neither National or Labour aren’t looking at an enquiry into the building industry.

It’s all very well to make promises about building more houses and blame foreign students and speculators – the easily targeted faceless enemy – but the reality is of a building industry that…

izogi

Thu, 21 Sept 2017 10:20:05 +1200

Undecideds are back up to 14% apparently

Is this possibly just an effect of polling companies only polling people who haven't already voted? ie. There might be the same number of undecideds as there were before, but decided voters have been puling out of the sample population whereas undecideds probably…

simon g

Thu, 21 Sept 2017 10:08:22 +1200

My take is that publicising the Labour `make it up as you go along' tax policy has worked for the Nats big time. Labour has not offered any excuse to the public to explain why nine years of opposition isn't ample time to design a credible economic policy – they…

Dennis Frank

Thu, 21 Sept 2017 09:24:12 +1200

Looks like the latest Colmar Brunton poll has confirmed the prior Reid Research poll: a lead reversal back to National by a large margin and partial deflation of the Ardern effect bubble. My take is that publicising the Labour `make it up as you go along' tax policy has worked…

Caleb D'Anvers

Wed, 20 Sept 2017 05:14:24 +1200

I have to say, I’m not that convinced by elements of Danyl’s analysis there. I don’t think it’s actually the case that NZ and UK Labour’s tertiary fees policies are “very similar.” Corbyn offered current students the concrete material benefit of not paying any fees for the coming academic year,…

Emma Hart

Tue, 19 Sept 2017 16:46:31 +1200

I'd not been aware that advance voting stations doubled as enrolment stations. Is it meant to be all of them?

The article is also quite vague on detail and lacking conviction about how serious it is or isn't considered to be, but Labour seems to be saying that some unenrolled…

simon g

Tue, 19 Sept 2017 12:41:56 +1200

Policy proposal for next election (any party welcome to adopt it):

"We will make tertiary education completely free, but only if 90% of under-30s enrol."

I mean, 68%, come on, put down your Walkman (check this reference – Ed) and get cracking.

*shakes zimmer frame at passing young person*

linger

Tue, 19 Sept 2017 11:07:33 +1200

Are these recent immigrants and expats all young people?Nah, though both groups will skew younger than the average; the important thing is they outnumber the unregistered youth, which we need to bear in mind when considering who's not voting. Danyl’s argument specifically about age was that youth participation is generally…

izogi

Tue, 19 Sept 2017 09:08:49 +1200

I read that article closer to when he wrote it and it makes some sense. Australia snagged me when I lived there for a couple of years and signed up to a power company. I've been a dual citizen most of my life, so they forced me to vote. I…

linger

Tue, 19 Sept 2017 04:36:25 +1200

Could something similar [to Corbyn bringing out the youth vote] happen in NZ?
Danyl Mclauchlan’s analysis suggests we are unlikely to see any similarly strong effect, because the “missing” voters in the last few NZ elections were largely (i) recent immigrants, and (ii) NZ expats (mostly in Australia), rather than…

Ben Austin

Tue, 19 Sept 2017 01:11:22 +1200

Well I guess we'll see if my friend is a reliable source / analyst in a week!

Hilary Stace

Mon, 18 Sept 2017 08:20:23 +1200

Some useful analysis of that landlords' poll by Thomas Lumley https://www.statschat.org.nz/2017/09/17/polls-that-arent-any-use/?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+StatsChat+%28Stats+Chat%29

linger

Sun, 17 Sept 2017 20:49:31 +1200

From Emma’s post on advance voting: Do I have to be enrolled?
No. We can enrol you in the advance voting booth and you can cast your vote at the same time. The only time you can’t enrol is on Election Day.Yes, that should be true at every advance venue.…

izogi

Sun, 17 Sept 2017 19:27:57 +1200

linger:
you can register at the same time as casting an advance vote (though not on the final polling day)

Does anyone know much about what Labour is talking about here?

The Labour Party is concerned voters who aren't enrolled are being turned away from advance voting booths.

I'd not…

izogi

Sun, 17 Sept 2017 17:14:05 +1200

If that's the case then I'm most likely wrong. Ah well.

linger

Sun, 17 Sept 2017 11:23:59 +1200

Some (very small) subset of the advance votes may also be last-minute registrations, because you can register at the same time as casting an advance vote (though not on the final polling day). But that data is not immediately available.

Tom Semmens

Sun, 17 Sept 2017 09:25:49 +1200

97% of the olds, but only 67% of the youngs. That makes any "youthquake" a fairly mild tremor ... so far.

Has anyone reported the late enrolment pattern from last election?

simon g

Sat, 16 Sept 2017 12:13:49 +1200

There's been a lot of coverage of advance voting but less coverage of people not enrolling at all.

97% of the olds, but only 67% of the youngs. That makes any "youthquake" a fairly mild tremor ... so far. It's the difference between Labour having to accommodate Winston or the…

linger

Sat, 16 Sept 2017 11:20:56 +1200

On current trend, more than 1 million advance votes will be cast before final election date (despite a shorter timeframe for advance voting!) — in which case the polls (which legally can't ask anyone how they have already voted) can all bugger off.

simon g

Sat, 16 Sept 2017 11:15:11 +1200

Horizon polls have come up with some ridiculous numbers in the past, so I would treat this with a truckload of caution, but their latest poll in the NBR is not far off the general picture.

Except for the prospect of a second ACT MP. Oh the horror, the horror…

David Bulog

Sat, 16 Sept 2017 10:58:39 +1200

look out for next weeks news hub Reid Research poll —99% sure it will be
so far out of whack with last nights Roy Morgon Poll and NBR Horizon poll.
Either Reid Research is right on the money or they are 100% wrong and will end up being the laughing…

Alfie

Sat, 16 Sept 2017 10:43:44 +1200

A new Roy Morgan poll predicts a Labour/Green/Maori coalition as follows:

Labour (49 seats); Greens (11 seats) & Maori Party (2 seats): Total 62 seats

National (50 seats); NZ First (7 seats) & Act NZ (1 seat): Total 58 seats

Sample size: 866
Conducted: Aug 28 to Sept 10

Ben Austin

Sat, 16 Sept 2017 03:53:23 +1200

I've been told by a friend that the phonebanking reception for Labour is still very positive for O-Belmont, fwiw

Caleb D'Anvers

Sat, 16 Sept 2017 03:01:39 +1200

I think it's worth pointing out that one of the reasons practically all the polls before the 2017 UK general election were wrong was because they systematically under-represented the youth vote. That was deliberate: after the polling debacles of 2015, the pollsters made adjustments to their sampling to reflect what…

Paul Campbell

Fri, 15 Sept 2017 20:49:03 +1200

With those numbers I think the Maori party is the likely 'kingmaker'

simon g

Fri, 15 Sept 2017 20:39:26 +1200

For Friday night poll junkies (let's get lives, people!) here's Roy Morgan latest:

NAT 40% LAB 39.5% GRN 9% NZF 6% MAO 2% ... rest irrelevant.

Least reliable of the pollsters, traditionally. But as a very rough guide, confirms the "all to play for" narrative rather than the TV3 Newshub…

Bart Janssen

Fri, 15 Sept 2017 17:00:59 +1200

myth of scientific objectivity

There have been studies that show pretty compellingly that people who believe themselves to be objective (eg scientists) are more subject to confirmation bias than average.

However, when making comments on the meaning of data there is a difference between comments made from knowledge and comments…

Dennis Frank

Fri, 15 Sept 2017 16:54:08 +1200

Scientists are generally aware of the difference between reporting facts and offering interpretation, and scientists generally seek to test their interpretations by constructing experiments which will either convert interpretation into fact or dismiss it as erroneous speculation.

Yes, this general practice is a laudable mental discipline. I was referring to…

linger

Fri, 15 Sept 2017 09:43:00 +1200

And then there's the media phone-in/online audience opinion polls, with no attempt at random or representative sampling. Those would be "entertainment only" ... if they were entertaining rather than just infuriating.

Ian Dalziel

Fri, 15 Sept 2017 09:31:19 +1200

I guess all we have left now then is
the Wisdom of Crowds and
the Kindness of Strangers...

Bart Janssen

Fri, 15 Sept 2017 09:19:10 +1200

Just a comment about margins of error. At risk of 'splaining, most folks assume that the margin of error means the "real" result will be the stated number plus or minus the margin of error.

But these errors have a bunch of assumptions and what they really mean is the…

David Bulog

Fri, 15 Sept 2017 07:29:55 +1200

https://twitter.com/search?q=Reid+Research+poll&ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5Esearch

Trevor Nicholls

Thu, 14 Sept 2017 20:36:20 +1200

Interpretation of scientific results is inherently subjective – despite most scientists being addicted to their denial of this fact.

This isn't true. Scientists are generally aware of the difference between reporting facts and offering interpretation, and scientists generally seek to test their interpretations by constructing experiments which will either convert…

David Bulog

Thu, 14 Sept 2017 20:29:33 +1200

Tuesdays Newshub Reid Research poll = *sampling error of biblical proportions.*
But.....look at this
http://www.bbc.co.uk/news/uk-politics-32751993

Trevor Nicholls

Thu, 14 Sept 2017 18:45:23 +1200

Every polling company has to decide how representative their sample is of the wider electorate. This is usually done with a few questions where the responses can be tested against known big statistics – race, gender, age, etc. Then they have to make assumptions as to how likely various subgroups…

Dennis Frank

Thu, 14 Sept 2017 18:36:46 +1200

Yes it does rather incline one to doubt the methodology used by polling companies. Corin Dann commented that Colmar Brunton is being consistent in putting Labour ahead three polls in a row. The margin in tonight's is four points – greater than the margin of error.

Yet the National lead…

stephen walker

Thu, 14 Sept 2017 18:24:34 +1200

https://www.tvnz.co.nz/one-news/new-zealand/new-1-news-colmar-brunton-poll-labour-maintains-four-point-lead-over-national-could-govern-greens

Trevor Nicholls

Thu, 14 Sept 2017 18:04:18 +1200

Well the disparities in these polls are unnerving...

David Bulog

Thu, 14 Sept 2017 17:07:47 +1200

Reid Research poll *reputation on line tonight* --- stay tuned for Colmar Brunton poll at 6pm TV One.

linger

Thu, 14 Sept 2017 09:21:29 +1200

The percentages are just for the first-ranked issue for each respondent, hence the 100% total. That's a very blunt-instrument metric, because of course for most respondents many of the other listed issues would also have been "important", and in some cases combinations of second- and third-ranked issues might actually have…

izogi

Thu, 14 Sept 2017 08:30:29 +1200

If you're somebody who is concerned about how the country has been coping with those three issues, why vote for more of the same?

I can't look into people's heads and there could be a million individual reasons, but my simplistic guess would be that just because someone might think…

David Bulog

Thu, 14 Sept 2017 07:17:45 +1200

Tonights Colmar Brunton poll is the one to watch. Reid Research poll 25% internet panel -possible sampling error!!. Lets see at 6pm.

Trevor Nicholls

Wed, 13 Sept 2017 23:33:13 +1200

This result?

Yes. Somehow between screen and brain and keyboard housing became switched with education. I don't think it changes the point I was making though; health, housing and the environment is still a good combination for the left.
If you're somebody who is concerned about how the country has…

David Bulog

Wed, 13 Sept 2017 23:10:35 +1200

Seriously question the Reid Research poll—I think the area that troubles me is the internet percentage—that is an area that can be targeted !!! –100% landline polling is safer. TV1s poll will be interesting tomorrow.

izogi

Wed, 13 Sept 2017 22:40:15 +1200

So we learned on tonight's news that yesterday's poll showed that the 3 most important priorities for the sampled voters were: health, education and the environment. All issues that you would think favour the left. Very strange that this same poll gave National 47% of their support, wouldn't you think?…

BenWilson

Wed, 13 Sept 2017 19:42:28 +1200

Very strange that this same poll gave National 47% of their support, wouldn’t you think?

Nah, further evidence that policy is not the primary factor in people's voting choice. Also random error and unknown systematic error.

i.e. broke American states

Also very much not broke Switzerland.

simon g

Wed, 13 Sept 2017 18:59:20 +1200

That's why we don't have government by referendum. People would vote for better health, education and the environment, and not the taxes to fund them. That's what they say in response to polls, and that's what we would get (i.e. broke American states).

Trevor Nicholls

Wed, 13 Sept 2017 18:28:39 +1200

izogi

Wed, 13 Sept 2017 16:46:55 +1200

The only time you see legitimate electorate polls these days is in seats like Ohariu, which (until recently) could affect the nationwide result.

I'm probably very wrong about this and there are no polls since before Dunne withdrew, but from what I'm seeing in Ohariu I'm getting a vague sense…

Dennis Frank

Wed, 13 Sept 2017 15:59:12 +1200

we need to seriously reform our media landscape

I've felt much the same during the past half-century but there are structural problems that explain why such reform never happens. Primarily the historical fact that private media emerge from an older & more embedded capitalist culture than public media.

Then there's the…

Tom Semmens

Wed, 13 Sept 2017 07:15:39 +1200

Oh and talking about having to stop, I think it is outrageous polls are still being released AFTER VOTING HAS STARTED!!!!

It would be a very simple law change to ban them from the day advance voting opens.

Tom Semmens

Wed, 13 Sept 2017 06:56:59 +1200

The TV3 poll results were presented in a way designed to give TV3 the biggest possible headline. Presumably on discovering there was insufficient movement from their last poll to justify an hysterical headline, the numbers were "re-worked" to give a hysterical headline – namely, the undecided vote was excluded.

Paddy…

simon g

Wed, 13 Sept 2017 05:59:08 +1200

Herald latest:

After two decades of MMP, in a basic comprehension test young people beat old people by 16%.

I think what we really need is for the Communist Party to get the most votes, so a large chunk of the population can suddenly clamour for other parties to start liking…

Dennis Frank

Tue, 12 Sept 2017 19:06:47 +1200

Well, so much for the recent polls showing Labour ahead! If Reid Research polled correctly, what explains National ten points ahead of Labour? Both Gower & Corin Dann explained it as volatility. If the swing-voters really are just going which way the political wind is blowing on the day, there's no…

Katharine Moody

Tue, 12 Sept 2017 18:25:58 +1200

Here it is;

http://www.newshub.co.nz/home/election/2017/09/national-could-govern-alone-in-latest-newshub-poll.html

Trevor Nicholls

Tue, 12 Sept 2017 17:44:38 +1200

TV3 poll out tonight

I predict fear will win over hope. Hope I'm wrong :-)

simon g

Tue, 12 Sept 2017 16:52:25 +1200

TV3 poll out tonight. Patrick Gower doing his usual hype (rventilating).

I'll be shocked if I'm not shocked.

Katharine Moody

Tue, 12 Sept 2017 16:24:42 +1200

Labour’s more socialist platform is relatively foreign compared to National’s/CCP’s low tax, survival of the fittest philosophy – to first generation mainland Chinese.

That poll surprised me. My first thought was it's a real estate investment thing.

This election seems to me to be ending up to be a referendum…

mark taslov

Tue, 12 Sept 2017 13:25:51 +1200

Especially once you start breaking down the figures between 1st-generationers, and 1.5ers and 2nd-generationers.

I couldn’t find reference to this in the article, and a cursory scan of the research (which was – to be fair – dealing with an evenly split sample of Koreans/Chinese, rather than the Chinese vote…

Ian Dalziel

Tue, 12 Sept 2017 09:30:04 +1200

Upon looking through my voting pack, I had to laugh when I saw ACT has 39 (thirty nine) list candidates!!!

Should be renamed The Optimists Party!

Kumara Republic

Tue, 12 Sept 2017 03:55:26 +1200

Latest oddity: a sort-of poll (illustrated by a not-sort-of propaganda video from the Nats) on NZ Chinese voters, which is described as being "at odds with some other mainstream polls". Well, yes, probably because it isn't one.

It's not a new thing. I remember reading a Scoop or Newsroom.co.nz article…

Tom Semmens

Mon, 11 Sept 2017 17:18:32 +1200

Latest oddity: a sort-of poll (illustrated by a not-sort-of propaganda video from the Nats) on NZ Chinese voters, which is described as being “at odds with some other mainstream polls”.

Given the number of current and ex-National party MPs firmly in the Chinese communist parties NZ fifth column, this doesn't…

simon g

Mon, 11 Sept 2017 09:31:13 +1200

The Herald has had a poor campaign when it comes to poll reporting. I'm starting to miss Digipoll!

Tom Johnson

Sun, 10 Sept 2017 21:50:19 +1200

There is a bluebelt in National Auckland who have been partying up on the blowout of their house equity, and they don't want that party to end. The meme that Bill English saw us through the GFC is a bit sick, chucking away the ladder for the most needy since…

Dennis Frank

Sat, 09 Sept 2017 14:55:17 +1200

A fortnight till election day, and Labour has now established a small lead over National: Colin James quotes the RNZ poll of polls (http://www.radionz.co.nz/news/political/338948/labour-a-nose-ahead-of-national-on-the-averages). The site methodology averages the latest three polls (unspecified).

Confirmed by the latest Bauer Media Insights IQ poll of 1528 Kiwi voters which puts Labour at…

Dennis Frank

Thu, 07 Sept 2017 19:32:58 +1200

I did see him say that, Simon – could've been in a promo, or maybe a back-announce in the bulletin. I registered the second use of 'explosive'. It does indeed imply an advance leak to the newsroom.

Probably the only thing that exploded as a result of the poll was…

John Farrell

Thu, 07 Sept 2017 18:29:15 +1200

Interesting Colmar Brunton. National's own polling must be showing the same thing.

simon g

Thu, 07 Sept 2017 16:22:43 +1200

Again, the Herald creates confusion (cock-up not conspiracy I believe, but still):

A new poll on CGT.

Polling period? The graphic and the article give 2 different answers (for now, anyway – will probably be edited once they notice what an old sub would have seen in 5 seconds).

simon g

Wed, 06 Sept 2017 19:29:03 +1200

I didn't hear Dallow say that in the bulletin I just watched. When was this?

He certainly shouldn't say it, because he doesn't know. The results would not be available yet, even to insiders.

Dennis Frank

Wed, 06 Sept 2017 19:11:51 +1200

Will it be "explosive"?

Simon Dallow said it will. The poll is actually out tomorrow night. Again no reference to what is likely to explode, but their ratings would take a hit if the poll result announcement caused viewers' tv sets or heads to explode, so you can see why…

simon g

Wed, 06 Sept 2017 18:25:58 +1200

Apologies for the fake news, the poll is out tomorrow! (I'm blaming Twitter ... )

Trevor Nicholls

Wed, 06 Sept 2017 16:30:22 +1200

Another TVNZ/Colmar Brunton poll out tonight.

Will it be "explosive"? Or "dramatic"? Will it "turn [our] expectations on their heads"? Might it be "career-ending"? Or herald "desperate times"?

Punters need to be told these things. Pundits need to say them.

Tom Semmens

Wed, 06 Sept 2017 11:55:23 +1200

Since The Greens have polled from 15 to 4% and back to 6% thus far giving them a random point here or there is as good a method as the polls for guessing what they’ll have on election day.

I hear tell the Greens themselves are confident they are polling…

simon g

Wed, 06 Sept 2017 11:19:35 +1200

Another TVNZ/Colmar Brunton poll out tonight.

I don't think it's too far-fetched to suggest that Steven Joyce's innumerate mud-chucking was at least partly motivated to influence this poll, although it would only cover the later stages of the polling period.

(Corin Dann soundbite bingo: "Labour's momentum has stalled ... National…

Sacha

Mon, 04 Sept 2017 12:23:13 +1200

Enabling the Nats to claim that the two polls show Lab support trending down is not professional journalism.

Russell Brown

Mon, 04 Sept 2017 11:16:58 +1200

They matter so much that it should be mandatory to state them when reporting the headline numbers.

It was reported in the story on the website – but not by Gower in his news piece. Naughty.

But in some ways understandable – it would have entailed a comparison with the…

Bart Janssen

Mon, 04 Sept 2017 09:11:21 +1200

gave the Greens an extra point ... because I can!

Since The Greens have polled from 15 to 4% and back to 6% thus far giving them a random point here or there is as good a method as the polls for guessing what they'll have on election day.

Trevor Nicholls

Mon, 04 Sept 2017 04:25:50 +1200

These details matter.

They matter so much that it should be mandatory to state them when reporting the headline numbers. The narrative in some places (being written by journalists who should know better) is that National has arrested if not reversed the Labour surge. The details don't support that at…

simon g

Sun, 03 Sept 2017 18:51:54 +1200

More small print: tonight's Newshub poll was Aug 22-30. Which makes some of the responses older than the TVNZ poll before the leaders' debate.

These details matter.

FletcherB

Fri, 01 Sept 2017 19:19:37 +1200

A nice feature is they actually talk about the limitations, however they fail to mention

They fail to mention that any predictions about the size of the party vote received by United Future based on previous results are unlikely to bear any relationship to what they may receive now that…

simon g

Fri, 01 Sept 2017 10:03:54 +1200

Fortunately last night's TVNZ debate was not accompanied by the text "poll" from previous campaigns that I mentioned above – so that was a plus.

On t'other hand, it was immediately preceded by a proper one. Although I liked the result, I don't think that it should have been used…

Gavin White

Tue, 29 Aug 2017 21:47:47 +1200

Somebody stole my idea from 2014 😉 (using past accuracy to adjust current poll results). See this blog for how that worked out...

http://sayit.co.nz/blog/its-crunch-time

Bart Janssen

Tue, 29 Aug 2017 17:08:50 +1200

The Herald now has it's modelling up and running.

As they say by combining all the polls and data from previous elections to correct for poll vs vote inaccuracies they should be able to get a better prediction.

A nice feature is they actually talk about the limitations, however they…

Trevor Nicholls

Tue, 29 Aug 2017 17:07:24 +1200

Still, there's something deeply symbolic about a senior cabinet minister losing his seat – in the event it happens.

Bart Janssen

Tue, 29 Aug 2017 17:02:33 +1200

they really got creative defining 'Chch Central' electorate last time they tinkered,

Fortunately with MMP the effect of that is moot for the parliament as a whole, but it can still piss of locals who feel they aren't represented correctly at the electorate level.

linger

Tue, 29 Aug 2017 14:48:12 +1200

While it’s nice to think Brownlee could be ousted, it can’t be done through strategic voting. He’s ranked 5th on National’s list, so he'll be in Parliament regardless. Better for Labour and the Greens to focus on the party vote. If they can agree to support one non-Brownlee candidate in…

Rob Stowell

Tue, 29 Aug 2017 14:35:45 +1200

Ilam could be interesting – fingers crossed. At least, if all the green and labour voters strategically voted for Manji. He's a popular councillor, and fairly well-liked and respected locally. Brownlee isn't especially well-liked, even by National people I talk to.

Gavin White

Tue, 29 Aug 2017 13:40:03 +1200

I doubt there's even any private polling Tom – it's too expensive. The only time you see legitimate electorate polls these days is in seats like Ohariu, which (until recently) could affect the nationwide result. Robos may exist, but they'll be unreliable as hell.

Tom Semmens

Tue, 29 Aug 2017 08:59:41 +1200

Just curious, any up to date polling in the public arena for Ilam?

Ian Dalziel

Tue, 29 Aug 2017 08:52:27 +1200

re gerrymandering
they really got creative defining 'Chch Central' electorate last time they tinkered,
there is now a tongue of voters stretching all the way from the central city to Redwood and the main north road – for whatever reason...
...following a rich vein of National voters it seems?

David Bulog

Mon, 28 Aug 2017 19:22:26 +1200

I really dig this UK polling/market research company
http://www.qriously.com/how-it-works/

http://www.qriously.com/blog/poll-uk-general/

WITH 24 HOURS TO GO, LABOUR NUDGES INTO THE LEAD, BUT RESULT STILL TOO CLOSE TO CALL

http://www.qriously.com/blog/raw-data-uk-election-poll/
2213 people polled—you can download results as a csv

Instead of aggregated results tables, we’ve decided to share the raw non-identifiable data…

Gavin White

Mon, 28 Aug 2017 18:12:28 +1200

That's both shocking and not that surprising Trevor. In a similar vein, I recall that one of the resources I used for my 1996 thesis on turnout was a book of NZ election results from 1946 to 1990. The thing that sticks in my mind from that was that there…

Trevor Nicholls

Mon, 28 Aug 2017 17:16:13 +1200

As Bart Janssen says, there's very clearly a relationship between the closeness of the election and turnout (compare 2005 and 2014 as an illustration). Downs' theory on rational voting, if I recall correctly (although he argued that voting was only rational if your vote was almost certain to decide the…

Gavin White

Mon, 28 Aug 2017 16:58:29 +1200

The Herald poll is by TNS, who used to do the TV3 poll (as CM and then TNS) before Reid. My recollection is that Reid split off from TNS. TNS are a big global company, so in theory they should be using a solid methodology, but the global brands haven't…

simon g

Mon, 28 Aug 2017 16:29:26 +1200

As predicted ... the Herald has a "new poll" today.

Small print: it's still the same one. Same polling period (Aug 16-21). This really is not good enough.

simon g

Fri, 25 Aug 2017 08:13:16 +1200

Also the Herald online still doesn't understand how to use quotation marks. Comments (from English? We can only guess) are embedded in the article. Sigh.

simon g

Fri, 25 Aug 2017 08:10:38 +1200

NZ Herald has a new online poll. So it looks like Digipoll has gone.

They've broken down the numbers into various demographics, as they used to do with Digipoll. There was always a question about the size of those samples (taken from within the overall thousand), and we're none the wiser…

Bart Janssen

Thu, 24 Aug 2017 09:06:56 +1200

encouraging voter abstention as through encouraging an actual switch in support.

My understanding of the data is that's the major effect. When voters perceive there is no point in voting because one party already has it won then voter turnout drops.

linger

Wed, 23 Aug 2017 23:04:26 +1200

There's some degree of feedback, most often taking the form of consolidation on the poll-anointed "winner" at the expense of poll-anointed "certain-losers" — though probably just as much through encouraging voter abstention as through encouraging an actual switch in support.

Ianmac

Wed, 23 Aug 2017 22:24:51 +1200

Is it possible that the polls cause the voters to vote to match the polls?

Russell Brown

Wed, 23 Aug 2017 20:10:29 +1200

TL;DR — the expected effects on errors in support estimates arising from lower overall support rates (lower p, hence lower theoretical variance) and regional/demographic restrictions on support (hence lower effective sample size, and higher theoretical variance) seem in practice largely to cancel each other out in NZ data.

As I…

Russell Brown

Wed, 23 Aug 2017 20:08:02 +1200

According to Martyn Bradbury, over at the daily blog. Can anyone confirm if that is true? If so, I am getting in an extra supply of tea of biscuits for election night.

Yup. RNZ don’t get it any more for Colin James’s poll-of-polls.

Although bless you for wanting to fact-check…

Tom Semmens

Wed, 23 Aug 2017 18:47:14 +1200

David Farrar is no longer sharing his polling information to various sites for Poll of Polls.

According to Martyn Bradbury, over at the daily blog. Can anyone confirm if that is true? If so, I am getting in an extra supply of tea of biscuits for election night.

Shaun Lott

Wed, 23 Aug 2017 17:06:36 +1200

Not happening here (I hope!) but of interest...
https://fivethirtyeight.com/features/fake-polls-are-a-real-problem/

linger

Wed, 23 Aug 2017 16:37:10 +1200

TL;DR — the expected effects on errors in support estimates arising from lower overall support rates (lower p, hence lower theoretical variance) and regional/demographic restrictions on support (hence lower effective sample size, and higher theoretical variance) seem in practice largely to cancel each other out in NZ data.

linger

Wed, 23 Aug 2017 16:16:02 +1200

Not disagreeing there — see the last few lines of my comment above. Theoretically extreme case: if a minor party’s support were entirely limited to a small, definable demographic or regional subset of the population, then the relevant sample size for calculating the error in that party’s estimated support would…

Russell Brown

Wed, 23 Aug 2017 15:53:11 +1200

The polls are accurate for parties that poll close to 50%.

For smaller parties the polls are less accurate, hence the “surprising” results for NZ First etc.

Not really. NZ First won 8.66% of the vote. The last five polls: 6.6, 8, 8.4, 7.1, 8.

So three were very close…

mpledger

Wed, 23 Aug 2017 15:28:17 +1200

>> for smaller parties the polls are less accurate

> Only in terms of relative error, not in terms of the absolute error

Only in terms of the sampling error. The non-sampling error for small parties is probably quite large.

National's margin of error is quite close to the survey's…

Bart Janssen

Wed, 23 Aug 2017 14:27:46 +1200

New Zealand sample sizes are not small by international standards.

The point was not that the sample size was small but rather that it is easy to sample a non-representative group.

linger

Wed, 23 Aug 2017 13:39:19 +1200

for smaller parties the polls are less accurate
Only in terms of relative error, not in terms of the absolute error. The theoretical variance, and therefore the theoretical margin of error, in a proportion estimate is proportional to p(1-p), so is largest for p=(1-p)=50%, and falls as either p or…

mpledger

Wed, 23 Aug 2017 13:17:59 +1200

Thomas Lumley wrote a great article about quantifying the actual margin of error compared to the theoretical margin of error. It's a bit statsy though.
http://www.statschat.org.nz/2014/07/02/whats-the-actual-margin-of-error/

mpledger

Wed, 23 Aug 2017 13:16:01 +1200

Sample sizes for national polling in NZ are 750-1000 (Colmar Brunton is usually slightly over 1000). The typical sample size for US national polls is 1000.
~~
Very basically – for polls the margin of error of a survey depends on the number of people sampled not the size of…

Bart Janssen

Wed, 23 Aug 2017 12:01:12 +1200

I wouldn't call that "horribly inaccurate".

The polls are accurate for parties that poll close to 50%.

For smaller parties the polls are less accurate, hence the "surprising" results for NZ First etc.

simon g

Wed, 23 Aug 2017 10:33:32 +1200

The polls (traditional) are generally accurate. The reporting of them generally isn't. Obviously, that's not the fault of the pollsters themselves.

One irritant for me is TV1 and TV3 reporting "our latest poll" over several days. e.g. On a Monday, they'll give the main party vote numbers. Then they will…

Nick Russell

Wed, 23 Aug 2017 10:17:49 +1200

Yeah, there is an enduring myth that polls in NZ are inaccurate but very little evidence. Sooner or later someone will trot out the cellphone line which is a complete red herring as far as I can see. And the discussions around margins of error are always depressing.

Russell Brown

Wed, 23 Aug 2017 10:00:22 +1200

All polls in NZ suffer from biases and small sample sizes. They are always reported with bogus margins of error. And worst of all they are horribly inaccurate.

That last is the worst of their faults. If your sample fails to represent the entire population every time then you’d be…

Bart Janssen

Wed, 23 Aug 2017 09:01:52 +1200

Where did I read recently that NZ's population is far too small to make statistically robust Online polling viable ?

Polling is about getting the results from a small sample that represent the results from the entire population.

The problem with any online poll is it samples a particular portion…

Russell Brown

Wed, 23 Aug 2017 07:59:58 +1200

On your last point Russell, there’s no way Reid surveyed all those people just for a preferred PM poll (which I strongly dislike mainly because they’re usually skewed to the incumbent, which is what is interesting about the NZ ones at the moment). There must be at least a vote…