Public Address | Cafe | Speaker: What we think and how we vote

David Hood

Tue, 09 Aug 2016 11:34:43 +1200

Just harkening back to the very first comment (about tirades). For the most important issues question, most of the entries were in uppercase. While I assume this is just a transcription thing- like who transited it, you can rank the parties by how many of the voters issues were written…

Mr Mark

Sat, 06 Aug 2016 19:59:51 +1200

Brilliant. Thanks, David. Your data even allows me to calculate movement in and out of non-voting – all I could ask for and more.

On the the left/right median voter theorem being tosh – completely agree. Similar findings in recent analyses of British voters. A significant body of voters do…

David Hood

Sat, 06 Aug 2016 19:18:36 +1200

With my fundamental opinion that the left/right median voter theorem is rubbish when applied to multiple interests MMP New Zealand, I feel thoroughly vindicated by looking at the direct movements between National and Labour.

The people that moved from Labour to National between 2011 and 2014 did not think the…

David Hood

Fri, 05 Aug 2016 22:56:42 +1200

Mr Mark, here are the raw numbers of
(who they say they voted for in 2011), (who they voted for in 2014), raw number
so that people can use the raw number to calculate either the percentage of the 2011 figure or the percentage of the 2014 figure.

I will…

Mr Mark

Wed, 03 Aug 2016 23:31:28 +1200

David, I don't suppose you'd have the NZES stats for % swing (ie vote movement/flows) between the various political parties 2011-2014 would you ?

Danyl Mclauchlan

Wed, 03 Aug 2016 08:27:59 +1200

Great work David. Thanks.

Ian Dalziel

Wed, 03 Aug 2016 06:48:56 +1200

step right up
ladders of opportunity are a public good
'Too rights' make a rung!

Kumara Republic

Tue, 02 Aug 2016 19:43:42 +1200

I know exactly who I'm voting for: anyone who believes that ladders of opportunity are a public good rather than an accident of privilege.

David Hood

Tue, 02 Aug 2016 17:20:42 +1200

Health and education linked, against a bundle of things with no clear theme. Let's call it issues vs people for the moment.

I'm away from my analysis code until the end of the week, so numeric specifics are going to have to wait.

BenWilson

Tue, 02 Aug 2016 16:04:27 +1200

Also interested to know how much variation each axis explains. Does it diminish rapidly so that PC3 is approaching the limit of usefulness?

BenWilson

Tue, 02 Aug 2016 15:50:54 +1200

Is PC2 health vs education? Or are they linked and opposed to less something less easy to summarize? Are you able to show the top 10 word loadings on the graph? Presumably the party positions are centroids?

David Hood

Tue, 02 Aug 2016 12:35:10 +1200

While the Māori Party and Mana seem far away in terms of their voters interests, I wouldn't necessarily say that stops a merger- If it worked it would just pull the points together. At the moment National seems to contain people who voted for economic growth and people voting for…

Sacha

Tue, 02 Aug 2016 11:55:36 +1200

Great work. The Maori Party's positioning is an interesting reminder why they are not likely to merge with Mana any time soon. Any way to make those party name labels bigger?

David Hood

Tue, 02 Aug 2016 11:36:18 +1200

I reran the PCA excluding all but the 50 terms that showed the greatest variation between parties, PCA1 was indeed the Poverty-Economy continuum, PC2 seems education and health related, PCA3 (not shown) was environment and separates out the Greens and Labour, PCA4 was land sales/immigration (NZ First), PCA5 was morality…

David Hood

Tue, 02 Aug 2016 11:01:48 +1200

On my todo eventually list is check previous ones to see if they had the free text option, and see what the terms analysis shows.

David Hood

Tue, 02 Aug 2016 10:41:48 +1200

The correlation between use of economy and poverty by party voters is -0.64. Of course no one knows if that is “good” correlation for this kind of data or not, because this is kind of being made up as we go along.

I would say the two terms are not…

BenWilson

Tue, 02 Aug 2016 10:23:11 +1200

Link to the PA discussion that went into detail on the NZES 2011. Just for comparison.

BenWilson

Tue, 02 Aug 2016 09:40:34 +1200

Not that there were specific poverty questions in what I looked at. And I guess the general cluster of Left questions was around income differences, housing, benefit cuts, unemployment. I guess what I find interesting is that in the words of the respondents this would be summed up as "poverty".…

BenWilson

Tue, 02 Aug 2016 09:31:14 +1200

I think the left/right axis Ben found in the previous election results from the survey generally looks like it is mirrored in the economy/poverty axis (which are inverses of each other except in the middle).

So “economy” is associated with the “Right” of the PCA1 and “poverty” is associated with…

BenWilson

Tue, 02 Aug 2016 09:26:20 +1200

Perhaps normalizing the size of the groups? You'll have to drop off the smaller parties to do that. Then you can at least explore the associations. Pick a size for each of the top, say, 5 parties, and sample out 5 groups that large.

linger

Mon, 01 Aug 2016 20:00:24 +1200

Yes, pretty much.
Yule's Q is a dimensionless ratio that varies between -1 and +1:
terms with Q=-1 are associated only with sample B
(a=0, hence (a-b)=-b, (a+b)=b, hence Q = -b/b = -1);
those with Q=+1 only with sample A
(b=0, hence (a-b)=a, (a+b)=a, hence Q= a/a = +1);…

David Hood

Mon, 01 Aug 2016 19:28:26 +1200

A basic PCA of the entire data is essentially useless. PCA1 puts National way off by itself with everyone else clumped, PC2 puts Labour off by itself, PC3 puts the Greens off. My working theory is that as National got the most votes/representation in the survey it has the most…

David Hood

Mon, 01 Aug 2016 14:53:07 +1200

So that is the change from a to b as a proportion of the combined proportions? Similar I suspect, but I used an aggregate figure for b to given a common baseline to compare multiple entries, and didn't divide. I imagine the not dividing has the effect that big difference…

linger

Mon, 01 Aug 2016 13:07:40 +1200

What came to mind for me is Yule’s Q = (a – b) / (a + b) which has been used to compare relative word frequency (i.e., word counts normalised for text length) in two language samples (with respective relative frequencies a, b per million words). What you’re doing seems…

David Hood

Mon, 01 Aug 2016 10:55:57 +1200

So you would get a -economy for a group if, for example, economy was not one of the terms mentioned at all for that group, putting it well below the mean?

Correct, assuming that the mean was not just above zero (one group using it and all the rest not…

BenWilson

Mon, 01 Aug 2016 10:32:18 +1200

OK, I think I get that. So you would get a -economy for a group if, for example, economy was not one of the terms mentioned at all for that group, putting it well below the mean?

It’s idiosyncratic but I think I get what you’re trying to do. Kind…

David Hood

Sun, 31 Jul 2016 21:11:31 +1200

Following the term economy through:

I get the number of mentions of every term for every party. This gives the raw number of mentions of every term, for all of the parties tested.

Then I generate the percentages for each term for each party, dividing the raw number by the…

BenWilson

Sun, 31 Jul 2016 19:33:34 +1200

So the + or – is whether the term occurs more or less proportionately per group than the mean proportion across all groups? So if "economy" occurs in, say, 50% of responses, but in 51% of National voter responses, then it's a +? Just trying to get my head around…

David Hood

Sat, 30 Jul 2016 21:33:26 +1200

I did a better way of looking at it: rather than absolute amounts this is how often voter groups are (+) or are not(-) using terms relative to other voter groups use of those terms. The more terms beside each party, the more that part had unusual terms frequencies (I…

David Hood

Fri, 29 Jul 2016 22:07:08 +1200

I should really link up Dirty Politics and Don't Know to be single terms- don't was on my list of excluded terms, hence Conservatives were in the know, rather than don't know

BenWilson

Fri, 29 Jul 2016 21:29:41 +1200

Love it. "Dirty", a reason to vote National, or not at all!

BenWilson

Fri, 29 Jul 2016 19:59:57 +1200

There are both a series of questions rating the importance of a standard issues from the last election

Yes, although rating and ranking are not the same thing. Not that either is clearly superior, but I do think that ranking is a pretty normal mental process when faced with massive…

David Hood

Fri, 29 Jul 2016 19:38:02 +1200

I haven't done any stemming (removing suffixes to bring terms together), but here are the commonest 10 terms written by NZES in the most serious issue free text question (removing common stop words like a, the, not, etc) for words that come up at least three times, assuming there are…

David Hood

Fri, 29 Jul 2016 18:33:21 +1200

There are both a series of questions rating the importance of a standard issues from the last election, and a free text "what is the most important issue to you" kind of question where people could write whatever they feel (which has also been coded into general and specific subject…

BenWilson

Fri, 29 Jul 2016 16:44:44 +1200

I'd say prioritizing is a big part of what we do when making decisions. I'd go further, though, to say that most people probably essentialize their thinking, homing in on a small group of issues that they think matter. But these are different for everyone, and even if the same,…

BenWilson

Fri, 29 Jul 2016 16:31:12 +1200

Yes, the NZES was not built for the purpose I was using it, so it's not that surprising it wasn't that fit for it. Still a very interesting resource though, there's nothing else like it in NZ.

linger

Fri, 29 Jul 2016 15:32:09 +1200

Probably questions measuring priorities placed on different issues would be more successful predictors of voting preference than questions measuring reactions to single issues?

linger

Fri, 29 Jul 2016 15:25:38 +1200

Part of the difficulty in attempting to build a general model for voting choices may be that often the same label (e.g. “business-friendly”) will have different meanings and evaluations to voters for different parties.
e.g. National basically owns the label “business-friendly”. However hard Labour tries to market itself on that…

BenWilson

Fri, 29 Jul 2016 14:12:54 +1200

It's kind of interesting that if you ask the right questions, then the left to right scale does seem to form the most important principal component axis, and the parties do seem to order themselves according to the self-rated left/rightness of the respondents. I don't know if that shows more…

Ian Dalziel

Fri, 29 Jul 2016 08:44:23 +1200

tirade unionists...
spittle flecked
Ahh, welcome to the sleepy little hamlet of Spittlefleck, where village idiots outnumber the rest. More colic than bucolic, and the smouldering resentments are abiding proof that it takes a 'child' to raze a village

David Haywood

Thu, 28 Jul 2016 19:25:30 +1200

Very interesting indeed, David! Thank you for all your hard work in investigating this for us.

David Hood

Thu, 28 Jul 2016 19:12:09 +1200

Ben, you might get a sense I have my doubts that the Left-Right umbrella terms have any more use than "I am voting National so I must be on the right but I feel like they are a bit more extreme than me" rather than as a determinant. It is…

BenWilson

Thu, 28 Jul 2016 16:29:08 +1200

Interesting stuff, David. Wish I had the time to go through my own findings on the last survey to compare and contrast. Are the questions mostly similar?

It was an interesting process last time. I think I found out a lot more about statistics than I did about NZ voters'…

David Hood

Thu, 28 Jul 2016 14:46:38 +1200

So National party voters are more likely

Well, not really. There are a pretty big pool of National voters who, from these questions could be ideological or issues voters- we just don't know.

We do know there are a bunch of National voters who see themselves as a bit rightwing…

Tom Semmens

Thu, 28 Jul 2016 14:10:32 +1200

So National party voters are more likely to launch spittle flecked ideolological tirades than Labour ones? You only have to read David Farrar or listen to Mike Hoskings to know one side is still fully engaged in the class war.

Public Address

Thu, 28 Jul 2016 14:10:32 +1200

Discussion from blog post.