Stats Chat

RNZ has a report on the purported costs of weather warnings for (ex-)Cyclone Vaianu a few weeks ago.

Northland spending was down 48 percent. Auckland’s was down 46.5 percent, Waikato was down 52.58 percent, Bay of Plenty down 68.32 percent, Gisborne down 51.6 percent and Hawke’s Bay was down 56.34 percent.

That’s at least two more decimal places than I would want to use, but let’s assume the numbers are correct.  There are still a few issues with the attribution to weather warnings.

First, we can’t easily distinguish the effects of the warnings, the effects of the forecast, and the effects of the storm.  Presumably no-one is suggesting that weather forecasts should be edited to make approaching storms look less scary, but some of the reduction in spending would have been a response to the heavy rain and strong winds in the forecast, regardless of a specific warning.  Even if the forecasts were sanitised, people who remember, say, the Auckland Anniversary Weekend storm or Cyclone Gabrielle might want to be cautious about the risks of an approaching storm.  The report says the reductions in spending were highest in the areas where the forecast storm was most intense, but that’s what you’d expect if people were reacting to the forecast rather than to the North-Island-wide warning.

Second, there’s an economic issue that should be clear already to people in or near local government, because it’s part of how convention centres, stadiums, and major cultural events are oversold.  It’s much easier to get people to change where and when they spend money than to change how much money they spend.  Suppose you were planning a barbeque for your kid’s birthday on April 12th. You might well have cancelled it because of the storm warning, but that wouldn’t mean your kid didn’t get a birthday this year. You’d have the event some other time.  Similarly, if you wanted to see a movie (Project Hail Mary seems popular) or you needed to buy a new vacuum cleaner or you wanted to see the fireworks and racing at Waikaraka Park you might well not go out that day, but you might well go some other day when you could easily get to the cinema or Briscoes or when the racing and fireworks were rescheduled¹.  The reduction in spending on the day of the storm is a substantial overestimate of the impact of the storm on spending. (In the same way, stadiums collect money, but a lot of it is money that people would otherwise still have spent in the city).

And finally, there’s an important issue about uncertain predictions.  The storm didn’t in fact cause major damage across the North Island, but that doesn’t mean the warning was wrong.  If you play Russian roulette and survive, that doesn’t mean it was a good bet and you should do it again, it just means you got lucky.  The report gives no reason whatsoever to assume that less caution was warranted for this storm than for the two big storms in 2023 (one of which was seriously underpredicted).  It’s not inconceivable that our weather warnings are poorly calibrated, but any decision of this sort should be based on some actual evidence that they are.

1. Last night. Ask me how I know.

• Canada is starting its census on Monday
• Another ultraprocessed food headline: CNN says Even a single daily serving of ultraprocessed food may raise dementia risk.  As before, the research didn’t even try to compare people with no ultraprocessed food intake to those with only a single daily serving.  They used a model that approximates the relationship by a curve with no safe level, and so couldn’t address this question — nor did they claim to.  The “even a single daily serving” is CNN.  What the research claimed is that each extra daily serving translated to 10% more dementia risk.  I’m a bit dubious, for the simple reason that ultraprocessed food consumption has gone up but dementia risk (at a given age) hasn’t. But I don’t think anyone’s claiming ultraprocessed food is good.
• Strava makes an app that tracks cycling and running and confidential military locations. Over the last year, Seattle was the top US city for logging bicycle commutes, with Chicago and Minneapolis in the next positions.  The Seattle Times says Seattle front of the pack for bike commuting in U.S. cities, but given Seattle’s status as a West Coast tech and nerd haven, it seems quite possible that we’re seeing selection bias.  It could easily be that Chicago or the Twin Cities are ahead in commuting but people there are just less likely to report it to Strava.
• Nice blog post by Kieran Healy on maps of data and using hexagons to make all the regions visible
• A graph from The Economist. 
  
  I first noticed the unusual definition of Asia in the footnote, especially the exclusion of countries no-one would think to include. The time axis could also be clearer. I presume the slightly longer tick mark is either Dec 2025 or Jan 2026, but a stronger visual cue to past vs future would perhaps be more helpful.  The other aspect, which is very common in graphs of the fuel crisis, is the smoothness of the projected decline in the face of uncertainty as to both supply and attempts to manage demand.

Team Ratings for Week 9

The basic method is described on my Department home page.
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 63 matches played, 46 of which were correctly predicted, a success rate of 73%.
Here are the predictions for last week’s games.

Predictions for Week 9

Here are the predictions for Week 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 15

The basic method is described on my Department home page.
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 70 matches played, 50 of which were correctly predicted, a success rate of 71.4%.
Here are the predictions for last week’s games.

Predictions for Round 15

Here are the predictions for Round 15. 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 23

The basic method is described on my Department home page.
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 154 matches played, 119 of which were correctly predicted, a success rate of 77.3%.
Here are the predictions for last week’s games.

Predictions for Round 23

Here are the predictions for Round 23. 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 9

The basic method is described on my Department home page.
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, 36 of which were correctly predicted, a success rate of 56.2%.
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 Week 17

The basic method is described on my Department home page.
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 128 matches played, 88 of which were correctly predicted, a success rate of 68.8%.
Here are the predictions for last week’s games.

Predictions for Week 17

Here are the predictions for Week 17. 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 Week 12

The basic method is described on my Department home page.
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 53 matches played, 37 of which were correctly predicted, a success rate of 69.8%.
Here are the predictions for last week’s games.

Predictions for Week 12

Here are the predictions for Week 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.

If you want to get a health story into the papers it helps if it sounds controversial and it especially helps if it tells people they can eat food they want to eat: thus the frequency of stories about chocolate, wine, and beer.

This week’s version is a not-very-detailed abstract from a conference in the US that purportedly says healthy food gives you lung cancer. And when I say that’s what the study purportedly shows, I mean:

• MSN: Eating fruits, vegetables and whole grains may increase chance of early onset lung cancer
• The Independent: Eating more fruits and vegetables could put you at risk for this cancer
• Newsweek: Fruits and Vegetables May Increase Your Cancer Risk, New Research Shows
• and even the researchers’ own press release: Eating fruits, vegetables and whole grains may increase chance of early onset lung cancer

One exception is Ars Technica, headlining the story as Absurd study suggests eating fruits and vegetables leads to cancer.

The press release says

“Our research shows that younger non-smokers who eat a higher quantity of healthy foods than the general population are more likely to develop lung cancer,” said Jorge Nieva, MD,

and, no, it really doesn’t show that.  For a start, we shouldn’t really be advertising  health advice to the general public based on just a conference abstract, with so little detail. In this case even the limited detail we have is enough to say that this shouldn’t be a big health story.

The research is part of a project to study lung cancer in younger people who don’t smoke. It used to be that nearly all lung cancer cases were in older people who had been smokers, but one of the victories of global public health is to reduce the number of cases like this.    Clearly, if someone has lung cancer at age 30 it isn’t because they’ve been smoking for fifty years — and in fact, many of them haven’t smoked at all. So, there’s interest in studying what causes their lung cancer.  The Epidemiology of Young Lung Cancer study wants to look at genetic attributes and environmental risk factors for lung cancer before age 40.

Finding a control group is hard. You can’t just recruit a whole bunch of young people and see who gets lung cancer, because it’s an very rare disease: you won’t find anyone.  You need to look for diagnosed cases, but then you need to decide who to compare them to. In this research the people with lung cancer were compared to people in a big national survey series, NHANES, which asks about diet.

The primary reported finding is that young people diagnosed with lung cancer had healthier diets (according to one measure) than the average of the US population.  The researchers don’t say they expected to see this, and my guess is they didn’t.  Their theory is that pesticides — in some generic holistic sense — are responsible.  It’s obviously not impossible that pesticides could be carcinogenic, but this doesn’t seem like a very good way to find out. In particular, while the people in the study all have lung cancer, they don’t all have similar mutations in their tumours  — they don’t have the same sort of lung cancer — and there’s literally zero actual data on pesticides, just an assumption that they’re present in healthier food, so this isn’t picking out some sort of ultra-selective cancer effect.

Everything here is correlations, but better correlational studies with controls consistently find that people with lung cancer eat less of the fruit and vegetables and high-fibre foods than people without lung cancer (eg here). There’s a theoretical argument that a diet high in anti-oxidants might reduce the body’s ability destroy cancer, but you wouldn’t look at a small, unusual subset of lung cancers to study this question.  There are perfectly good alternative reasons why the young lung cancer patients might have healthier diets than the US average. They’re young, for a start.  They have had their cancers diagnosed early enough to end up in a study like this one, which will correlate with income and interest in medical science. They’re non-smokers.

If unreliable evidence of a healthier diet in a subset of people with lung cancer is taken as evidence of harm from pesticides, should we take evidence of a less healthy diet in other groups of people with serious illness as evidence that pesticides are beneficial?

Team Ratings for Week 8

The basic method is described on my Department home page.
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 54 matches played, 39 of which were correctly predicted, a success rate of 72.2%.
Here are the predictions for last week’s games.

Predictions for Week 8

Here are the predictions for Week 8. 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.