Stats Chat

• Violin plots are a useful way to show the whole distribution of a large set of data, or dot plots for a small set

• There’s a new movie out about at the effect of repeated minor brain injuries in US football; the same problem occurs in other sports.

• “The shipping container is one of those rare devices, like the light bulb or the telephone, that can be traced to a single inventor”  — from a review, now ten years old, of an fascinating book about container shipping. Yes, I do know how that sentence sounds.

• Will the new Stars Wars movie beat the original one in (real) ticket income? Will it go further and beat Gone With The Wind?

The northern hemisphere is warmer than usual this Christmas, as you may have heard. To be precise, it’s about 1 Fahrenheit degree above the 1979-2000 average after seasonal adjustment. (via)

Parts of the northern hemisphere are a lot warmer than that, including many parts that have a concentration of news media with a seasonal shortage of stuff to report. It’s hot in the eastern US, and this quite reasonably gets more reporting that it being cold in Siberia.

When the US northeast has unusually cold or snowy periods in winter, you see lots of people carefully explaining how this is weather or short-term variation and doesn’t tell you much about long-term climate patterns.

I’m one of those people, so this year I’m making the same point about warm weather.  The northern hemisphere as a whole is warm by about what the well-known trend suggests. The strong El Niño causing weird local weather in the eastern US could definitely be due in part to the global trend, but conclusions about regional variation are much less reliable than conclusions about this CO2 stuff being a bit of a worry.

Like the snow last year, the hot Christmas this year is consistent with climate change predictions but doesn’t add importantly to the evidence. It’s dramatic that Baltimore is as warm as Auckland this Christmas, but compared to the mass of accumulated evidence on the subject, a few days freak weather in a small part of the world just doesn’t mean much.

(from Wikipedia)

The University has closed until the New Year and we are on compulsory holiday, so from my point of view it’s the StatsChat Silly Season.

An important scientific issue in designing graphics is preattentive perception: for example, it’s easy to see the one different point in this plot

The circle vs triangle distinction is pre-attentively perceived: your visual system annotates it before you get to see the picture.  More complicated distinctions aren’t pre-attentive, and so don’t make as good plotting characters.

Here, as a Christmas card, is a picture from Hungarian cartoonist Gergely Dudás. One of the snowmen is a panda. Pandas are not pre-attentively perceived.

(update: yes, I saw the Herald has it too.)

From the person most likely to be the next President of those United States:

“Now, I wouldn’t keep any school open that wasn’t doing a better than average job. If a school’s not doing a good job, then you know it may not be good for the kids.”

This, as you’d expect, has occasioned some discussion on the internets.

There’s nothing mathematically impossible about the idea of nearly all schools being above average.  Nearly everyone has more than the average number of legs.  Darwin, Australia, has had better than average Christmas weather on 49 of the last 50 years — in 1974, Cyclone Tracy destroyed 80% of houses in the city, which tends to pull the average down.

In other settings, it’s not even an unreasonable idea that you’d routinely close a large fraction of establishments.  It’s roughly what happens to restaurants, for example: lots of them are started, most fail, the remaining ones tend to be pretty close to the optimal price:quality tradeoff line.

In this quote, though, neither explanation really flies: it’s not that nearly all schools are the same except for a few really bad ones, and it doesn’t really make sense to close half the schools in the country, because even if you’re in favour of free competition between schools, most schools are too far apart to compete effectively.

What we’re seeing here is the broadening of ‘average’ to mean ‘ok’, which is one of the reasons it’s less useful as a technical term than it used to be.  If you want to be precise, ‘mean’ is better.

• From a Press Council decision (via Matt Nippert)
  Press releases are a useful way for newspapers to receive information and comment from interested parties. However, as the senior editor concedes, using a release almost verbatim falls well below best practice. Newspapers risk losing the trust of their readership if they print material that is not independent and objective (or otherwise clearly labelled as comment).

• Redrawing a bad slide, by Kieran Healy

• On The Media has a “Consumer’s Handbook” for breaking news. Here’s the election polling edition

• Jeff Leek’s annual “non-comprehensive list of awesome things other people did”. Some of this is more technical, but a lot is of general interest

• Ed Yong writes about false positives in clinical genetics — not data errors, but mutations wrongly thought to be bad

• The Berkeley Earth project have real-time maps of air pollution in China (and, for comparison, Japan). There’s a lot of it, not just in the cities.

• Siouxsie Wiles and Kate Hannah have a crowdfunding appeal to send copies of Nicola Gaston’s book on sexism in science to people who need to read it.

Remember cheese addiction? It’s back (in the Independent)

Using the Yale Food Addiction Scale, designed to measure a person’s dependence on, scientists found that cheese is particularly potent because it contains casein. 

The substance, which is present in all dairy products, can trigger the brain’s opioid receptors which are linked to addiction.

This time there’s enough circumstantial evidence to track down the open-access research paper. It does not contain the word “casein” (or “casomorphin”).

The research paper does not make any assertions about cheese or dairy products and opioid receptors. In fact, it doesn’t single out cheese at all. It says

…we observed that highly processed foods with added levels of fat and/or refined carbohydrates (like white flour and sugar), were most likely to be associated with addictive-like eating behaviors

The cheese obsession in the media coverage is a complete fabrication. It would be interesting to know who’s behind it.

Update: the lead author, Erica Schulte is Not Happy with the cheese claim in this radio interview (at 17:30).

Earlier this year a current affairs program announced that they would have an interview with the man who didn’t get swallowed by a giant anaconda. Taken literally, this doesn’t restrict the options much.  There’s getting on for three billion men who haven’t been swallowed by giant anacondas; you probably know several yourself.  On the other hand, everyone knew which guy they meant.

There’s a branch of linguistics, called ‘pragmatics’, that studies how everyone knows what you mean in cases like this. The “Cooperative Principle” and Grice’s Maxims look at the assumption that everyone’s trying to move the conversation along and isn’t deliberately trolling.

One of the US opinion polling companies, Public Policy Polling, seems to make a habit of trolling its respondents.  This time, they asked whether people were in favour of bombing Agrabah.  30% of Republican supporters were. So were 19% of Democratic supporters, though for some reason this has been less widely reported. As you know, of course, since you are extremely well-read, Agrabah is not a town or region in Syria, nor is it held by Da’esh. It is, in fact, the fictional location of Disney’s Aladdin movie, starring among others the late, great Robin Williams.

I’m pretty sure that less than 30% even of Republican voters really support bombing a fictional country. In fact, I’d guess it’s probably less than 5%. But think about how the question was asked.  You’re a stereotypical Republican voter dragged away from quiet dinner with your stereotypical spouse and 2.3 stereotypical kids by this nice, earnest person on the phone who wants your opinion about important national issues.  You know there’s been argument about whether to bomb this place in the Middle East. You can’t remember if the name matches, but obviously if they’re asking a serious question that must be the place they mean. And it seemed like a good idea when it was explained on the news. Even the British are doing it. So you say “Support”.

The 30% (or 19%) doesn’t mean Republicans (or Democrats) want to bomb Aladdin. It doesn’t even mean they want to bomb arbitrary places they’ve never heard of. It means they were asked a question carefully phrased to sound as if it was about a genuine geopolitical controversy and they answered it that way.

When Ali G does this sort of thing to political figures, it’s comedy. When Borat does it to unsuspecting Americans it’s a bit dubious. When it’s mixed in with serious opinion polling, it risks further damaging what’s already a very limited channel for gauging popular opinion.

XKCD today:

There’s another story today about seizing large quantities of methamphetamine, this time hidden in a coffee table.  The border people also catch at lot of imports of ephedrine or pseudoephedrine. From January 1 to October 31, the authorities seized 293kg of meth and the equivalent of 3 million tablets of pseudoephedrine. And, of course, these are  not available legally in New Zealand. We have phenylephrine instead, which is on the Nice List because it can’t be turned into methamphetamine

Recently, a study in the US compared phenylephrine to placebo for hay fever. That’s not quite the same as looking at effectiveness for colds, but it’s still notable that there was no detectable difference. There were also no detectable side effects, which the researchers attribute to the drug all being zapped by the liver before it gets into general circulation.

At least the ban on pseudoephedrine is making us safe, though? Well, the government is tracking the effectiveness of its strategies. Here’s the summary from the October 2015 report, which is robustly disappointing.

There has been a decrease in use of methamphetamine, but it doesn’t look like the war on cold medicine can explain it.

Update: Before anyone else posts it, the famous joke synthesis

Because the hours of availability of such pharmacies are often limited, it would be of great interest to have a simple synthesis of pseudoephedrine from reagents which can be more readily procured.

A quick search of several neighborhoods of the United States revealed that while pseudoephedrine is difficult to obtain, N-methylamphetamine can be procured at almost any time on short notice and in quantities sufficient for synthesis of useful amounts of the desired material.

Sometimes things are more complicated than they seem.

From the Herald

It might seem like a virtuous choice – but munching lettuce is worse for the planet than eating bacon, a study claims.

Researchers say the amount of energy and water used – and the level of greenhouse gases produced – is far greater per calorie for lettuce than pork.

The second sentence doesn’t look as if it can carry the weight of the first sentence. I mean, yes, maybe per calorie, but who gets most of their calories from lettuce? Not even rabbits.

Later on, the story points this out:

Richard Bennett, dean of food research at Reading University, said: “The calorie is not the most sensible functional unit of comparison.”

and ends

But the study conceded that eating fewer calories would lead to better public health, benefiting the environment and cutting energy use.

That seems to settle it: Study 0, lettuce 1. Until you go and look at the research.

The research isn’t actually about working out the relative impacts of bacon and lettuce, it’s about a much less trivial question. It would probably be a good thing for the US population, on average, to lose weight. It would probably also be a good thing for the US population to eat more fruit and vegetables. What does that imply about food production and resource use?

In the research, they considered three scenarios:  keep eating unhealthy stuff, just less of it to reduce obesity; eat healthier food without reducing calorie intake; and eat healthier food at a lower total calorie intake to reduce obesity. The per-calorie resource demands for various foods are an input to this calculation; they aren’t conclusions in themselves.

The second scenario is the worst environmentally, but that’s not really surprising.  What’s interesting, and basically missed in the reporting is that the third scenario is worse than the first.  If people in the US changed their diets to eat less and to follow dietary recommendations, the result would be an increase in greenhouse-gas emissions, in water use, and in energy use.  Reducing meat consumption, especially beef, would help the environment, but reducing use of cheap fats, sugars, and starches wouldn’t, and increasing consumption of the current mix of fruit and vegetables definitely wouldn’t

To some extent, the conclusions are US-specific. NZ fruit and vegetable production uses less irrigation, and the produce is shipped shorter distances, in milder climates, than in the US. The conclusions also assume business as usual in food production. With cheap petrol and cheap water, it made sense to grow everything in the Imperial Valley and truck it or fly it across the country; in the future, that may not be efficient and the mix of fruits and vegetables consumed may change.

Carbon pricing and water shortages are going to increase the cost of food. The interesting part of this analysis is that they will increase the cost of healthier diets (at least in the US) even more, at least until the industry works out ways to adapt.