Stats Chat

Team Ratings for Round 9

The basic method is described on my Department home page. I have made some changes to the methodology this year, including shrinking the ratings between seasons.

Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.

Performance So Far

So far there have been 64 matches played, 35 of which were correctly predicted, a success rate of 54.7%.

Here are the predictions for last week’s games.

Predictions for Round 9

Here are the predictions for Round 9. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Team Ratings for Round 12

The basic method is described on my Department home page. I have made some changes to the methodology this year, including shrinking the ratings between seasons.

Here are the team ratings prior to this week’s games, along with the ratings at the start of the season.

Performance So Far

So far there have been 67 matches played, 41 of which were correctly predicted, a success rate of 61.2%.

Here are the predictions for last week’s games.

Predictions for Round 12

Here are the predictions for Round 12. The prediction is my estimated expected points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Justice edition

• From the BBC, a historical story about DNA evidence incriminating someone who had been dead for three weeks at the time of the crime.  Even with modern techniques, the upper bound on the strength of DNA evidence is incompetence or fraud (which has happened) rather than random false matches (which may not ever have happened with good samples)

• A new research paper argues that 4% of those sentenced to death in the US would have their convictions overturned if they waited long enough.  That’s not the same as 4% of them being innocent, but it’s still a problem.

• It’s hard to estimate the role of luck in success, because luck isn’t controllable. Ed Yong writes about a new paper where researchers experimentally randomised people to be lucky, and how much it mattered.

If you ask people in the US to estimate the income of someone at the 80th percentile, they underestimate it, thus underestimating income inequality (PDF).

However, if you specify a dollar amount and ask how many people have income above that amount, you get an underestimate of high incomes.

The take-home message? It’s hard to design good survey questions.

The Herald’s story on birth order and education was nominated for Stat of the Week, which is perhaps a bit harsh.   Here’s the particular sentence (in bold) that attracted criticism, in its context

Eldest children were 7 per cent more likely to aspire to stay on in education than younger siblings and first-born girls were 13 per cent more ambitious than first-born boys, findings from the Institute for Social and Economic Research at the UK’s University of Essex show.

The ‘more ambitious’ is just elongated-yellow-fruit syndrome — it means exactly the same as the ‘more likely to aspire to stay on in education’ earlier in the sentence — not that I’m in a strong position when it comes to criticizing elegance of writing. The researchers used survey data where British kids had been asked at age 13 whether they planned to go into tertiary education, and related their answer to family structure and other variables (PDF).

The sentence in bold is not quite correct — the 13% difference is in the report, but it’s the difference between all girls and all boys averaged over birth order, not between first-born girls and boys. Because of the way probabilities are limited at 100%, the difference between first-born girls and boys will be somewhat smaller, though that’s a pretty technical consideration.  What the figures do make clear is that the difference between first-born and later-born children is quite a bit smaller than the difference between boys and girls.

The Guardian has a similar story, with very similar phrasing, though it’s not clear who borrowed from whom. Where the Herald is different is that the illustrative examples are better. The Herald‘s examples look as though they were chosen, appropriately, from famous Kiwis without regard to birth order; the Guardian has gone in for confirmation bias, choosing famous first-borns.

Each week, we would like to invite readers of Stats Chat to submit nominations for our Stat of the Week competition and be in with the chance to win an iTunes voucher.

Here’s how it works:

• Anyone may add a comment on this post to nominate their Stat of the Week candidate before midday Friday May 2 2014.
• Statistics can be bad, exemplary or fascinating.
• The statistic must be in the NZ media during the period of April 26 – May 2 2014 inclusive.
• Quote the statistic, when and where it was published and tell us why it should be our Stat of the Week.

Next Monday at midday we’ll announce the winner of this week’s Stat of the Week competition, and start a new one.

(more…)

From The Times, via Alberto Cairo and junkcharts, an example of how to make an unreadable infographic from two bar charts.  Both are at weird angles, one is 3-d and one is half-missing.

[Yes, the cargo containers on the boats are colour-coded by the national flags. Isn’t that sweet?]

• via Lennart Nout, a map of where people (well, users of the Strava app) cycle in Auckland.
• Nathan Yau, on the difference in his recorded activities since his son was born.
• Another ‘what you can’t do with big data’ piece, from the New Yorker
• Arbitrary goals can make a difference: many more people finish a marathon just under than just over 4 hours.

How can a sham medical procedure provide huge benefits? And why do we still do them in a world of randomised, blinded trials? Thomas Lumley explores the issue in his latest New Zealand Listener column. Click here.

There’s a story in the Herald about the impact of changes in the drinking age. It’s a refreshing change since it’s a sensible analysis of reasonable data to address an interesting question; but I still want to disagree with some of the interpretation.

As those of you who have lived in NZ for longer will remember, the drinking age was lowered from 20 to 18 on December 1, 1999. One of the public-health questions this raises is the effect on driving.  You’d expect an increase in crashes in 18-20 year olds, but it’s not obvious what would happen in older drivers. You could imagine a range of possibilities:

• People are more at risk when they’re learning to manage drinking in the context of needing to drive, but there’s no real difference between doing this at 18 or at 20
• At eighteen, a significant minority of people still have the street smarts of a lemming and so the problem will be worse than at twenty
• At eighteen, fewer people are driving, so the problem will be less bad
• At eighteen, fewer people are driving so there’s more pressure on those with cars to drive, so the problem will be worse
• At eighteen, drivers are less experienced and are relying more on their reflexes, so the problem will be worse.

Data would be helpful, and the research (PDF,$; update: now embedded in the story) is about the relative frequency of serious crashes involving alcohol at various ages for 1994-1999, 2000-2004, 2006-2010, ie, before the change, immediately after the change, and when things had settled down a bit. The analysis uses the ratio of crashes involving alcohol to other crashes, to try to adjust for other changes over the period.  That’s sensible but not perfect: changing the drinking age could end up changing the average number of passengers per car and affecting the risk that way, for example.

The research found that 18-20 year olds were at 11% lower risk than 20-24 year olds when 20 was the drinking age, and 21% higher risk when 18 was the drinking age (with large margins of uncertainty). That seems to fit the first explanation: there’s a training period when you’re less safe, but it doesn’t make a lot of difference when it happens — the 20% increase for two years matches the 11% increase for four years quite closely. We certainly can’t rule out the problem being worse at 18 than at 20, but there doesn’t seem to be a strong signal that way.

The other thing to note is that the research also looked at fatal crashes separately and there was no real sign of the same pattern being present. That could easily just be because of the sparser data, but it seems worth pointing out given that all three of the young people named in the story were in fatal crashes.