And was in the news yet again for that just 10-ish days ago. [sigh] French Polynesian politics.... Meanwhile, back in the Métropole, I've been having a lot of fun watching [[http://www.liberation.fr/politiques/2014/07/05/droite-forte-les-sarkozystes-plaident-la-cause-de-leur-champion-persecute_1058131|the spot of bother Sarkozy has found himself…

Oops, thanks. That was carelessness on my part – context made that perfectly clear.

Another tangent: Sentence 2 of the subtitle of this piece at Le Figaro smacked my gob:

Mercredi, une association…

Oh check out the footage Joe, Cunliffe seemed to have an epiphany of his own right then and expressed it openly and shockingly honestly. If he chose at that…

Not good enough then is it? How about a better look at what the Conference was about? What the Politicians were there for? How about how the Organization can get help to stop the cycle of abuse? Oh, that's right ,you said it
lots of…

So when a Green Politician does it? Jan Logie would probably disagree.

When I have time*, hopefully within the next couple of weeks, I'll post a brief overview (on my blog) of the debate so far, including some of the discussion here. And I'll include my response to some of the points made by you, Thomas, Steve and others. I'll…

National's share of…

I mentioned this on DimPost but I don't know if you saw it. If you ever want to catch up to talk polls and undecideds, or if you have any poll-related questions I can help answer, just flick me an email at

I've got some undecided-related…

Bradford’s report was okay until she decided the most important news was Cunliffe’s alleged “slip-up” and quoted unnamed “sources” in the Labour Party to…

– Although it hasn't been widely publicised, Fairfax-Ipsos provide firm evidence that the Undecideds are disproportionately people who voted Labour in 2011. Thus reinforcing the likelihood that the Undecideds do, indeed, favour a change of Government.

– When I look back at the NZES data,…

Hence, my suggestion that pollsters ask the more specific Do you favour a Labour-led or National-led Government ? question.

I think it's good that pollsters take a very cautious, social science-based approach…

http://www.youtube.com/watch?v=hxZ-scE9mDk

When I wasn't actively angry, I was pretty much in despair about this…

Tell ya what though – I'm so sick to death of these continual and obvious beat-ups on David Cunliffe. Here he is speaking about something incredibly important, and bloggers and the media choose to focus on a single sentence, and to report…

The results for each party are non-independent, so if the…

Yep

Throw wide the doors of perception....

The polls are serving as an instrument that is like a “self fulfilling prophecy”, so to say. We get them all the times, and…

.......But I just don't think there are multiple interpretations or overly-complex nuances here (particularly in the context of the liberties – bordering at times on gross misinterpretation – taken with Party Support data by journos in their Front Page and Op-Ed poll analyses).

Need to…

I really can't see multiple interpretations of this. Except to suggest that possibly – just possibly – a small minority of those favouring change wanted a National-led Government, but one involving NZ First in some capacity (whether in a formal Coalition or other arrangement). But you'd have to…

Yes, it's a sad state of affairs when a perfect storm of factors – including narrowing attention spans and tabloidised political commentary – conspire to produce low-info voting. Civics education has been touted as a partial…

(My Lap-top suddenly can't handle posting longer comments so, unfortunately, I'll have to break it up into different parts. This is Part Two: The Sequel)

If you take October 2013 ( Fairfax-Ipsos ) as an illustrative example, those favouring a Change of Government outnumbered respondents happy with the…

"There are too many different causal models which fit the correlations observed from outside the system. We can't rule out some models based on the evidence we have, so we will be left with multiple interpretations"

I think that's more a criticism of Puddleglum's analysis on __The Political…

Yes my friend we swim in a sea of political apathy. I am shocked when I meet people who are not sure who the blue party is or just don't vote.

I…

Oh please say it is not so... People who don't care and just get on with life? :-)

Glad you handled that question. I saw it and left the room quickly. :-)

Alas, we really need the raw data to make stronger inferences. And in fact we really…

You don’t, and some people may lie. It would have to be a lot of people though to really make much of a difference in a random sample of 1,000. People are much less obsessed with politics…

There are many reasons an individual might give a response contrary to their true intentions, or even just to appear as if they had intentions...

The results for each party are non-independent, so if the number of seats for one party changes, this changes the number of seats other parties will get (irrepective of what their range is). Parties with a range crossing the 5% threshold would then add…

Let's try it again...http://sub-z-p.blogspot.co.nz/2014/06/fairfax-ipsos-poll-february-2014.html (If it doesn't work this time, can I just say Bugger ! – thank you).

I think it works for National at this election because the PM has committed to running and seems fairly healthy. If I was advising a client about their brand though, I'd say don't let it be tied to…

Yeah – interesting question. Polling is actually only about 2-3% of the work I do (well, maybe a bit more in an Election Year). Quite a bit of what I do involves…

When I reread the caution in your methodology about using it to predict the outcome of the election, I also thought about a certain irony:

Polling this far out can’t be used to predict the outcome of elections accurately if campaigning works. Especially if it gets disenfranchised…

Yip, you've got the correct numbers, but they happen to be two of the lowest bases we've seen since I can recall.

Yes 813 is those people who expressed a party voting preference (sometimes with a second prompt) and were likely to vote. And yes there were other…

(On another note, can bloggers please consider how medium-grey text looks on off-white backgrounds, particularly with a fine sans-serif typeface? Very difficult to read, esp on small screens. Dark grey is more…

I used the numbers on p8 and yes below 800 twice in that series. Excuse me just giving a…

Below is a link to a great textbook on this approach. It is very readable for the non-statistics-minded person.

Survey Methodology. Groves et al.

Yes, I expect these methodological differences may contribute to some of the differences we see between polls. And sampling…

There is a case, however, for reporting parties below 5% to 1dp in some circumstances. If we round to 0dp, then parties that poll 4.5% will…

Great show Russell and everyone else; this looks like it will settle into a fine groove: informative without po-facing.

Andrew and Gavin: thanks for your insights into the trade. It's a minefield of…

It looks like the denominator is down to between 700 and 800 per sample based on party supporters. That would widen the margin of error a little bit compared to 1,000. For example

1,000 and 50% support (95% confidence level)…

In our May poll we had NZ First on 4.8%, so we reported two alternative seat conversations – one where they cross the threshold and one where they don’t.…

same

Though doesn't that play into the example you guys discussed on MediaTake?

I'm pretty much against reporting party support percentages to 1dp, because that suggests a level of precision that no poll can provide. Actually, we've had people tell us that we shouldn't even report to whole numbers – but provide only ranges. If…

Note: The data does not take into account the effects of non-voting and therefore cannot be used to predict the outcome of an election. Undecided voters, non-voters and those who refused to answer are excluded from the data on party support. The results are therefore only indicative…

Very or quite likely refers to likelihood to vote. Anyone else is unlikely to vote, so is not included in the party support analysis.

Weakly decided refers to those who haven’t made a decision, but say they are likely to vote for a…

So you're really only reporting on strongly-decided potential voters. What proportion of the total is that?

On an apparently unrelated issue in another country, I was just looking to see whatever happened with the vote…

Yes, up to 10 days in most cases. Is this what you're suggesting? That's quite different to:

Given that, I’d argue they should be banned.…

Out of all responses to the party vote question.

do you mean out of all respondents or just the ones who have earned the leaner?

just like pubs
and fancy office layouts (Russ will know what that refers to)

What did you actually mean by deceptive? It's a word that carries connotations of dishonesty.

That wasn't what I said. I said the polls are deceptive. that is a totally different reason for banning them.

By the way there are several countries where polls are banned for a period prior to the election date without any collapse in the society.

This could reasonably accurately inform Parliament…

If an issue is already controversial, this is much more valuable than a petition — it's really hard to get…

I was waiting for a kick off for this part of the debate :-)

No way, is my response. Hell no, even. It's news because people want to know it. You have to have a lot stronger argument than "the information is…

True, but there’s a complication in that different polling firms handle the likely-voter issue differently. Some push further towards saying “Okay, if you were going…

I guess so, but every person polled could lie about anything. It's exactly the same problem.

I imagine Farrar will be doing them daily.

Which was a shame, as root vegetable
planting aside, I wanted…

To be completely anal, we don't want a representative sample of the population but only of the population that will actually vote on the day. It's pretty clear that a significant percentage of the population make their political opinions felt by…

I suspect that's a sort of 'we could tell you but...' type situation. :)

Roflnui.

True that. But then again, the Green Party is no longer small. To put it different, the bigger a party gets, the more it needs to retain, including by reactivating previous voters.

Small parties…

That's…

that could be another story for MediaTake to cover some time.

And yes indeed, what we are after is a proper representative sample. There are many more ways of obtaining low quality samples then just a low response rate. :-)

Slight correction (hey, being a statistician means…

One issue we discussed was TV3's reporting of NZ First's poll rating of 4.9% as definitely being below the threshold. That's statistical nonsense, as…

I'm planning a blog post about this. All surveys should report response rates. The problem is, NZ has no agreed upon…

It's really hard to know if that's true. In the case of the Green Party, it would seem less correlated…

As the actress said to the bishop.

Which is curious, if you think about it, because the long term trends are what generates by far the biggest part of where we are, and what happened last night is a tiny contributor.…

Small parties all rely on swing voters, much more so than N or L, who's voters are more likely to know who they'll vote for…

Far easier to do that than actually provide intelligent analysis. It's like we have dogs reporting "arf, the ball went over there. woof, now it's in the air".

And the currency…

I've sometimes…

Well, and there's NZF, whose sudden change in apparent support was a big story for the last election, and could well be again.

That's true, in the sense that an act of industry self-regulation has no jurisdiction over how that…

In the current form, the data don’t really provide any evidence for extrapolation to the election.

I don't really see much that could do that…

In the research industry the clients own the report and all the data. The research company could…