Posts filed under Politics (169)

April 29, 2016

Looking up the index

 

Q: Did you hear that Auckland housing affordability is better now than when the government came to office?

A: No. Surely not.

Q: That’s what Nick Smith says: listen, it’s at 4:38. Is it true?

A: Up to a point.

Q: Up to what point?

A:  As he says, the Massey University Housing Affordability Index for February 2016 is lower than it was for November 2008, for Auckland and everywhere else in the country. For Auckland it was 38.44 then and is 33.8 now.

Q: But The Spinoff says one of the people behind the Index says Nick Smith is wrong, that housing isn’t more affordable than it was then.

A: Indeed she does. That’s because housing isn’t more affordable.

Q: But you said the index was lower?

A: Yes, it is.

Q: And lower is supposed to be better?

A: Yes.

Q: But how can the Housing Affordability Index be lower when housing isn’t more affordable? What is the index?

A: If it’s the same as it was is 2006 (which would make sense) it’s median selling price multiplied by a weighted-average interest rate and divided by the mean individual weekly earnings.

Q: Can you translate that?

A: Roughly,  the number of weeks of average earnings you’d need to pay the first year’s interest on a 100% mortgage.

Q: So if it’s 34, and you’ve got two people making the average, it’s 17 weeks each out of 52 going to mortgage interest? About 32% of income?

A: That’s right, only you don’t get 100% mortgages, so it’s more like 26% of income. And there’s taxes and insurance and you actually pay off a bit of the principal even in the first year, so it’s more complicated. But it’s a simple summary of the interest cost.

Q: And that’s lower now than in November 2008?

A: So it seems. I wasn’t living in New Zealand then, but it looks like mortgage interest rates were near 9%. The combination of the increase in incomes and the fall in interest rates has been slightly more than the increase in house prices, even in Auckland.

Q: But what if rates go back up?

A: Then a lot of houses will retroactively become much less affordable.

Q: And what about saving for down payments? That’s what all the snake people have been complaining about, and low interest rates don’t help there.

A: Down payments don’t go into the affordability index

Q: But they go into actual affordability!

A: Which is presumably why the Minister was talking about the affordability index.

 

April 28, 2016

Marking beliefs to market

Back in August, I wrote

Trump’s lead isn’t sampling error. He has an eleven percentage point lead in the poll averages, with sampling error well under one percentage point. That’s better than the National Party has ever managed. It’s better than the Higgs Boson has ever managed.

Even so, no serious commentator thinks Trump will be the Republican candidate. It’s not out of the question that he’d run as an independent — that’s a question of individual psychology, and much harder to answer — but he isn’t going to win the Republican primaries.

Arguably that was true: no serious commentator, as far as I know, did think Trump would be the Republican candidate.  But he is going to win the Republican primaries, and the opinion polls haven’t been all that badly wrong about him — better than the experts.

Māori imprisonment statistics: not just age

Jarrod Gilbert had a piece in the Herald about prisons

Fifty per cent of the prison population is Maori. It’s a fact regularly cited in official documents, and from time to time it garners attention in the media. Given they make up 15 per cent of the population, it’s immediately clear that Maori incarceration is highly disproportionate, but it’s not until the numbers are given a greater examination that a more accurate perspective emerges.

The numbers seem dystopian, yet they very much reflect the realities of many Maori families and neighbourhoods.

to know what he was talking about, qualitatively. I mean, this isn’t David Brooks.

It turns out that while you can’t easily get data on ethnicity by age in the prison population, you can get data on age, and that this is enough to get a good idea of what’s going on, using what epidemiologists call “indirect standardisation”.

Actually, you can’t even easily get data on age, but you can get a graph of age:
ps_ages_3_16

and I resorted to software that reconstructs the numbers.

Next, I downloaded Māori population estimates by age and total population estimates by age from StatsNZ, for ages 15-84.  The definition of Māori won’t be exactly the same as in Dr Gilbert’s data. Also, the age groups aren’t quite right because we’d really like the age when the offence happened, not the current age.  The data still should be good enough to see how big the age bias is. In these age groups, 13.2% of the population is Māori by the StatsNZ population estimate definition.

We know what proportion of the prison population is in each age group, and we know what the population proportion of Māori is in each age group, so we can combine these to get the expected proportion of Māori in the prison population accounting for age differences. It’s 14.5%.  Now, 14.5% is higher than 13.2%, so the age-adjustment does make a difference, and in the expected direction, just not a very big difference.

We can also see what happens if we use the Māori population proportion from the next-younger five-year group, to allow for offences being committed further in the past. The expected proportion is then 15.3%, which again is higher than 13.2%, but not by very much. Accounting for age, it looks as though Māori are still more than three times as likely to be in prison as non-Māori.

You might then say there are lots of other variables to be looked at. But age is special.  If it turned out that Māori incarceration rates could be explained by poverty, that wouldn’t mean their treatment by society was fair, it would suggest that poverty was how it was unfair. If the rates could be explained by education, that wouldn’t mean their treatment by society was fair; it would suggest education was how it was unfair. But if the rates could be explained by age, that would suggest the system was fair. They can’t be.

April 17, 2016

Overcounting causes

There’s a long story in the Sunday Star-Times about a 2007 report on cannabis from the National Drug Intelligence Bureau (NDIB)

“Perhaps surprisingly,” Maxwell wrote, “cannabis related hospital admissions between 2001 and 2005 exceeded admissions for opiates, amphetamines and cocaine combined”, with about 2000 people a year ending up in hospital because of the drug.

The problem was with hospital diagnostic codes. Discharge summaries include both the primary cause of admission and a lot of other things to be noted. That’s a good thing — you want to know what all was wrong with a patient both for future clinical care and for research and quality control.  For example, if someone is in hospital for bleeding, you want to know they were on warfarin (which is why the bleeding happened), and perhaps why they were on warfarin. It’s not even always the case that the primary cause is the primary cause — if someone has Parkinson’s Disease and is admitted with pneumonia as a complication, which one should be listed? This is a difficult and complex field, and is even slightly less boring than it sounds.

As a result, if you just count up all the discharge summaries where ‘cannabis dependence’ was somewhere on the laundry list of codes, you’re going to get a lot of people who smoke pot but are in hospital for some completely different reason.  And since there’s a lot of cannabis consumption out there, you will get a lot of these false positives.

There are some other things to note about this report, though. The National Drug Foundation says (on Twitter) that they made the same point when it first came out. They also claim


that the Ministry of Health argued against its being published.

Perhaps now the multiple-counting problem has been publicised in the context of hospital admissions the same mistake will be made less often for road crashes, where multiple factors from foreign drivers to speed to alcohol to drugs are repeatedly counted up as ‘the’ cause of any crash where they are present.

March 24, 2016

The fleg

Two StatsChat relevant points to be made.

First, the opinion polls underestimated the ‘change’ vote — not disastrously, but enough that they likely won’t be putting this referendum at the top of their portfolios.  In the four polls for the second phase of the referendum after the first phase was over, the lowest support for the current flag (out of those expressing an opinion) was 62%. The result was 56.6%.  The data are consistent with support for the fern increasing over time, but I wouldn’t call the evidence compelling.

Second, the relationship with party vote. The Herald, as is their wont, have a nice interactive thingy up on the Insights blog giving results by electorate, but they don’t do party vote (yet — it’s only been an hour).  Here are scatterplots for the referendum vote and main(ish) party votes (the open circles are the Māori electorates, and I have ignored the Northland byelection). The data are from here and here.

fleg

The strongest relationship is with National vote, whether because John Key’s endorsement swayed National voters or whether it did whatever the opposite of swayed is for anti-National voters.

Interestingly, given Winston Peters’s expressed views, electorates with higher NZ First vote and the same National vote were more likely to go for the fern.  This graph shows the fern vote vs NZ First vote for electorates divided into six groups based on their National vote. Those with low National vote are on the left; those with high National vote are on the right. (click to embiggen).
winston

There’s an increasing trend across panels because electorates with higher National vote were more fern-friendly. There’s also an increasing trend within each panel, because electorates with similar National vote but higher NZ First vote were more fern-friendly.  For people who care, yes, this is backed up by the regression models.

 

Two cheers for evidence-based policy

Daniel Davies has a post at the Long and Short and a follow-up post at Crooked Timber about the implications for evidence-based policy of non-replicability in science.

Two quotes:

 So the real ‘reproducibility crisis’ for evidence-based policy making would be: if you’re serious about basing policy on evidence, how much are you prepared to spend on research, and how long are you prepared to wait for the answers?

and

“We’ve got to do something“. Well, do we? And equally importantly, do we have to do something right now, rather than waiting quite a long time to get some reproducible evidence? I’ve written at length, several times, in the past, about the regrettable tendency of policymakers and their advisors to underestimate a number of costs; the physical deadweight cost of reorganisation, the stress placed on any organisation by radical change, and the option value of waiting. 

February 28, 2016

Forecasts and betting

The StatsChat rugby predictions are pretty good, but not different enough from general educated opinion that you could make serious money betting with them.

By contrast, there’s a professor of political science who has an election forecasting model with a 97+% chance that Trump will be president if he is the Republican nominee.

If you were in the UK or NZ, and you actually believed this predicted probability, you could go to PaddyPower.com and bet at 9/4 on Trump winning  and at 3/1 on Rubio being the nominee. If you bet $3x on Trump and hedge with $1x on Rubio, you’ll almost certainly get your money back if Trump isn’t the nominee, and the prediction says you’ll have a 97% chance of more than doubling your money if he is.

Since I’m not betting like that, you can deduce I think the 97% chance is wildly inflated.

February 11, 2016

Anti-smacking law

Family First has published an analysis that they say shows the anti-smacking law has been ineffective and harmful.  I think the arguments that it has worsened child abuse are completely unconvincing, but as far as I can tell there isn’t any good evidence that is has helped.  Part of the problem is that the main data we have are reports of (suspected) abuse, and changes in the proportion of cases reported are likely to be larger than changes in the underlying problem.

We can look at  two graphs from the full report. The first is notifications to Child, Youth and Family

ff-1

The second is ‘substantiated abuse’ based on these notifications

ff-2

For the first graph, the report says “There is no evidence that this can be attributed simply to increased reporting or public awareness.” For the second, it says “Is this welcome decrease because of an improving trend, or has CYF reached ‘saturation point’ i.e. they simply can’t cope with the increased level of notifications and the amount of work these notifications entail?”

Notifications have increased almost eight-fold since 2001. I find it hard to believe that this is completely real: that child abuse was rare before the turn of the century and became common in such a straight-line trend. Surely such a rapid breakdown in society would be affected to some extent by the unemployment  of the Global Financial Crisis? Surely it would leak across into better-measured types of violent crime? Is it no longer true that a lot of abusing parents were abused themselves?

Unfortunately, it works both ways. The report is quite right to say that we can’t trust the decrease in notifications;  without supporting evidence it’s not possible to disentangle real changes in child abuse from changes in reporting.

Child homicide rates are also mentioned in the report. These have remained constant, apart from the sort of year to year variation you’d expect from numbers so small. To some extent that argues against a huge societal increase in child abuse, but it also shows the law hasn’t had an impact on the most severe cases.

Family First should be commended on the inclusion of long-range trend data in the report. Graphs like the ones I’ve copied here are the right way to present these data honestly, to allow discussion. It’s a pity that the infographics on the report site don’t follow the same pattern, but infographics tend to be like that.

The law could easily have had quite a worthwhile effect on the number and severity of cases child abuse, or not. Conceivably, it could even have made things worse. We can’t tell from this sort of data.

Even if the law hasn’t “worked” in that sense, some of the supporters would see no reason to change their minds — in a form of argument that should be familiar to Family  First, they would say that some things are just wrong and the law should say so.  On the other hand, people who supported the law because they expected a big reduction in child abuse might want to think about how we could find out whether this reduction has occurred, and what to do if it hasn’t.

November 16, 2015

Measuring gender

So, since we’re having a Transgender Week of Awareness at the moment, it seems like a good time to look at how statisticians ask people about gender, and why it’s harder than it looks.

By ‘harder than it looks’ I don’t just mean that it isn’t a binary question; we’re past that stage, I hope.  Also, this isn’t about biological sex — in genetics I do sometimes care how many X chromosomes someone has, but most questionnaires don’t need to know. It’s harder than it looks because there isn’t just one question.

The basic Male/Female binary question can be extended in (at least) two directions.  The first is to add categories to represent other ways people identify their gender beyond just male/female, which can be fluid over time, or can have more than two categories. Here a write-in option is useful since you almost certainly don’t know all the distinctions people care about across different cultures. In a specialised questionnaire you might even want to separate out questions about fluid/constant identity from non-binary/diversity, but for routine use that might be more than you need.

A second direction is to ask about transgender status, which is relevant for discrimination and (or thus) for some physical and mental health risks.  (Here you might want also want to find out about people who, say, identify as female but present as male.) We have very little idea how many people are transgender — it makes data on sexual orientation look really precise — and that’s a problem for service provision and in many other areas.

Life would get simpler for survey collectors if you combined these into a single question, or if you had a Male/Female/It’s Complicated question with follow-up questions for the third group. On the other hand, it’s pretty clear why trans people don’t like that approach. These really are different questions. For people whose answer to the first question is something like “it depends” or a culturally specific third option, the combination may not be too bad. The problem comes when answer to the second type of question might be “Trans (and yes I sometimes get comments behind my back at work but most people are fine)”, but the answer to the first “Female (and just as female as people with ovaries and a birth certificate, ok)”.

Earlier this year Stats New Zealand ran a discussion and  had a go at a better gender question, and it is definitely better than the old one, especially when it allows for multiple answers and for a write-in answer. They also have a ‘synonym list’ to help people work with free-text answers, although that’s going to be limited if all it does is map back to binary or three-way groups. What they didn’t do was to ask for different types of information separately. [edit: ie, they won’t let you unambiguously say ‘female’ in an identity question then ‘trans’ in a different question]

It’s true that for a lot of purposes you don’t need all this information. But then, for a lot of purposes you don’t actually need to know anything about gender.

(via Writehanded and Jennifer Katherine Shields)

November 13, 2015

Flag text analysis

The group in charge of the flag candidate selection put out a summary of public responses in the form of a word cloud. Today in Insights at the Herald there’s a more accurate word cloud using phrases as well as single words and not throwing out all the negative responses

wordcloud

There’s also some more sophisticated text analysis of the responses, showing what phrases and groups of ideas were common, and an accompanying story by Matt Nippert

Suzanne Stephenson, head of communications for the flag panel, rejected any suggestion of spin and said the wordcloud was never claimed as “statistically significant”.

“I think people misunderstood it as a polling exercise.”

“Statistically significant” is irrelevant misuse of technical jargon. The only use for a word cloud is to show which words are more common. If that wasn’t what the panel wanted to do, they shouldn’t have done it.