Wellington Business Statistics

A couple of weeks ago we got a phone call one evening from an outfit called ‘Wellington Business Statistics’. They were doing a ‘survey’ and asked for incredibly detailed financial information. Salaries, mortgage size, amount owing, amount saved for retirement etc. It seemed incredibly suspicious. They aren’t registered with the companies office and a Google Search for ‘Wellington Business Statistics’ doesn’t bring up a web site for the them. Mostly it hits people asking about them on twitter, and one tweeter alleging:

If you get a phone survey from “Wellington Business Statistics“, hang up – it’s a front for a finance sales scam – they don’t exist

Someone I follow on twitter tweeted about them again today. Anyone else know anything about ‘Wellington Business Statistics’?

My theory about what’s happening in the polls

Latest aggregated poll, click here for the interactive version (it doesn’t contain the latest TV3 numbers it does now).

My guess about what’s happening at the moment is that centrist voters are soft on National, but if they vote for National they get National plus some insignificant, powerless support parties, while if they vote Labour they’re also effectively endorsing the Greens and Winston Peters since they’ll be major components of the Labour-led government, and most of those center-voters distrust Peters and/or the Greens to the extent that they’ll continue supporting National despite the ongoing blunders and disappointments.

I’ve seen people on Twitter wondering how anyone could still support National, but if you think about the Shearer-led Labour/Greens/New Zealand First alternative, it’s hard to imagine that being anything other than a short-lived disaster. Centrist support for National seems very sensible from that perspective.

Ho ho ho. Here’s a poll chart

Thanks again to Peter Green for the R code. Image is below, but you should really go here for the interactive SVG version.

More poll geekiness over the jump:

An anonymous pollster on the whole cell-phone, land-line thing

From the comments section in the previous post, guess the pollster writes:

The problem with calling cell phones doesn’t really lie in the cost of calls. For a polling company, calling a cell phone doesn’t cost that much more than calling a landline. The problem is the complexity and cost of employing dual sampling frames when the proportion of cell phone users without a landline is still very low. If the purpose of calling cell phones is to reduce non-coverage of likely voters, then you may actually need to ‘screen out’ those you call on cell phones who also have a landline (because they are already covered by the landline sample frame).

If we assume 6% of eligible voters have cell phones and no landline, that means that 94% of the people you call on a cell phone will not be eligible to take part (again, because they are already covered by the landline sample frame). This is where the cost would really begin to build up – all those interviewer hours required just to screen people out (eek!).

This is not the only way to reduce non-coverage – but it’s actually one of the more straight forward and ‘statistically pure’ ways (ie, you can develop some sort of weighting scheme, but the more you weight, the greater the design effect (which increases the margin or error, and decreased the accuracy of a poll).

To make things more complex:

- Some people have more than one cellphone, meaning that the probability of them being called is higher, so additional weighting would need to be applied to adjust for the probability of selection (you may notice that some polls weight by household size and the number of landlines connected to a house – this is adjusting for the probability of section)

- There are a lot of cell phone numbers that are out of use, but when they are called they still go through to a voice mail. Unlike landlines (which you can ‘ping’ to test the connection), it is very difficult (ie, near impossible) to determine if there is actually an eligible person at the end of a number, so you’ve got no measure of the success rate of your sampling approach (ie, refusal rates, response rates, qualifier rates etc).

- At the moment such a small proportion of New Zealanders have a cell phone with no landline that party support would need to be DRAMATICALLY different among those people for this particular type of non-coverage to influence the poll results for party vote (eg, support for Labour among cell phone only voters may need to be TWICE what it is among landline voters for the party vote result to shift by more than, say, the margin of error).

When the proportion of people with cell phones and no landline is considerably larger than it is today (like it is in some other countries), then it will definitely make sense to employ a dual sampling frame approach. In NZ though (at least in 2011) most pollsters got things pretty close to the election day result so this would suggest non-coverage of cell phone only voters isn’t a big issue just yet. If cell phone plans get cheaper, then polling approaches will probably need to change to keep up.

It is not the policy of the Dim-Post to comment on individual polls

But the latest Roy Morgan (with Labour down and National up, and the Roy Morgan sample size seems to get smaller with each poll, and is now just over 800) finds that Labour/Greens/New Zealand First is likely to win an election.

On current settings, isn’t a National-New Zealand First coalition just as likely as a Labour/Greens/New Zealand First coalition? Possibly more so. Given the dynamics of the coalition talks, in which the Greens would have far more seats than New Zealand First, but Winston Peters would have far more leverage than Russel Norman – because Peters can take his votes to National and Norman can’t – it’s hard to imagine Shearer (or whoever) putting together a functional government that lasts for three years. John Key probably won’t have any other significant coalition partners to worry about. He might have the Conservatives, but they’d probably be a luxury (like United Future during his last term) and they’d be smaller than New Zealand First.

Horse race watch

Interactive version of the chart here.

If you’re Labour you really want to be able to go into coalition with New Zealand First and the Greens, and be able to pass legislation with either party. Current results would see them trying to pass budgets with the support of Greens, New Zealand First and Hone Harawira, which doesn’t seem very sustainable.

(Thanks to Peter Green for getting the tracking poll script working again. Some day I will learn R so I can fix these things myself.)

More armchair strategising

Rob Salmond responds to the attacks on Labour’s centrist strategy by taking a look at the data from the New Zealand Election study surveys:

The results are public up to 2008, and have been pretty consistent. There is never an absolute majority of either left wingers or right wingers, usually not even close, and the proportion of people who say they are perfectly centrist (5 on the scale), is around 25-30%. That is a huge bloc of voters perched right in the middle. Ideology in New Zealand is a bell curve, and a steep one at that.

Given this distribution of voter ideologies, it does not take a statistician to figure out that the left needs to do well with centrist voters in order to win. Same for the right.

I don’t think relying on people’s self-assessment of their political ideology is very valid. Most people consider themselves to be reasonable and moderate. Take a look at the political self-assessment distribution from 2008.

So you look at that and conclude ‘New Zealand is a center-right nation’, right? If you want to get elected you need to pivot to the right, right?

Not really. Respondents to the NZES survey are asked a variety of questions, and you can pick and choose which ones are most representative of true political ideology, but I’d argue that the question:

ONE represents the view that the government should reduce taxes and people should pay
more for their own health and education, and SEVEN the view that there should be a tax
increase so the government can spend more money on health and education. Where would
you place your view?

Gets to the heart of the left-right value debate. And here are the results for 1999 and 2008.

Still a bell-curve, but now strongly skewed to the values of the left – although far less left in 2008 than it was nine years earlier. And you could argue about why that is, but my hypothesis is that the National Party is really good at advocating for its core values. They didn’t look at this chart and think, ‘well, we need to win the center so let’s endorse Labour’s policies of taxation and state spending because they’re popular with voters’, they thought ‘we need to get out and make the case for a low tax economy with less government, because that’s what we believe in.’

Which takes us back to Shearer and his roof-painting sickness beneficiary. Sure, in the NZES survey the majority of voter opinion is bearish towards beneficiaries but that doesn’t mean left-wing parties need to concede the debate on that subject to the right. The numbers on public opinion do move, but they don’t do so by themselves.

Polls, August 2011 to August 2012

TVNZ and TV3 both had new polls out last night. It’s always bearing in mind that each poll is only a single, very error prone data point. Stepping back and looking at the average polls over the last year, adjusted for their bias compared to the election result (thanks again to Peter Green for the R coding), we see the broad trends emerge.

My take on this is that Labour’s small target strategy has entered the realm of diminishing returns. Shearer has kept a low profile ever since his ‘I don’t have a dream’ speeches bombed (presumably this year is now designated his training wheels year) and this resulted in temporary gains for Labour because it coincided with a truly horrible six months for the government. Now they’ve peeled off soft votes, they’ll have to work harder for the rest. The Greens remain pretty steady.

As usual there’s a narrative vacuum from both main opposition parties. There’s no coherent critique of the government or substantive alternate vision. So whenever there’s a scandal or policy failure it takes place in this vacuum. And, as usual, National is very adept at crafting and promoting its own narratives. Unless this changes I don’t see these polls moving much over the next six months.

What next?

Peter has modified the tracking poll script a little, using an adaptive smoother, with the comment:

It gives slightly more credible results (at the cost of some oversensitive end-effect weirdness)

The page is here. Rob Salmond has also updated his poll o’ polls.

It’ll be interesting to see what happens next. I think we’re about to see National’s bid to change the conversation, win back the political initiative, set the agenda, all that good stuff – coming at us in the next few days. This may consist of the standard diversion tactics: ‘cracking down’ on whoever, provoking a fight with the unions or Maori or civil liberty groups, or announcing that they’re considering something crazy which they won’t actually do – but I suspect we’ll see something more substantive.

More poll chart porn

Peter Green put together an R script that generates an svg file showing historical polling trends. It estimates polling bias and factors it into the trend-line. Unfortunately WordPress won’t let me post svg files, so here’s a screen-capture of the result below. If you download the actual file and open it in a browser that isn’t Internet Explorer you can click on individual polls and highlight trends from different pollsters. The yellow lines below the x axis are significant political events. If this was an svg file you could click on them and find out what they were. Peter’s explanation of the statistics below the jump: